CVPR 2024 Papers

mini compact topic detail

Circuit Design and Efficient Simulation of Quantum Inner Product and Empirical Studies of Its Effect on Near-Term Hybrid Quantum-Classic Machine Learning

Uncovering What Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly

Learning Discriminative Dynamics with Label Corruption for Noisy Label Detection

CrowdDiff: Multi-hypothesis Crowd Density Estimation using Diffusion Models

PSDPM: Prototype-based Secondary Discriminative Pixels Mining for Weakly Supervised Semantic Segmentation

OpenBias: Open-set Bias Detection in Text-to-Image Generative Models

DreamMatcher: Appearance Matching Self-Attention for Semantically-Consistent Text-to-Image Personalization

COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction

Towards 3D Vision with Low-Cost Single-Photon Cameras

DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Iterative Diffusion-Based Refinement

Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now

Aligning Logits Generatively for Principled Black-Box Knowledge Distillation

SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimation

Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer

EgoGen: An Egocentric Synthetic Data Generator

Point Cloud Pre-training with Diffusion Models

Physics-guided Shape-from-Template: Monocular Video Perception through Neural Surrogate Models

PointOBB: Learning Oriented Object Detection via Single Point Supervision

Deep Video Inverse Tone Mapping Based on Temporal Clues

M&M VTO: Multi-Garment Virtual Try-On and Editing

HEAL-SWIN: A Vision Transformer On The Sphere

GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation

On Train-Test Class Overlap and Detection for Image Retrieval

Orthogonal Adaptation for Modular Customization of Diffusion Models

GDA: Generalized Diffusion for Robust Test-time Adaptation

Exploring the Transferability of Visual Prompting for Multimodal Large Language Models

VSRD: Instance-Aware Volumetric Silhouette Rendering for Weakly Supervised 3D Object Detection

Permutation Equivariance of Transformers and Its Applications

Unified Language-driven Zero-shot Domain Adaptation

Diffusion Models Without Attention

Class Incremental Learning with Multi-Teacher Distillation

GenN2N: Generative NeRF2NeRF Translation

SubT-MRS Dataset: Pushing SLAM Towards All-weather Environments

ViTamin: Designing Scalable Vision Models in the Vision-Language Era

COCONut: Modernizing COCO Segmentation

Parameter Efficient Self-Supervised Geospatial Domain Adaptation

LUWA Dataset: Learning Lithic Use-Wear Analysis on Microscopic Images

SpecNeRF: Gaussian Directional Encoding for Specular Reflections

HomoFormer: Homogenized Transformer for Image Shadow Removal

ALGM: Adaptive Local-then-Global Token Merging for Efficient Semantic Segmentation with Plain Vision Transformers

Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed

Beyond Seen Primitive Concepts and Attribute-Object Compositional Learning

Transductive Zero-Shot and Few-Shot CLIP

HardMo: A Large-Scale Hardcase Dataset for Motion Capture

SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design

PIA: Your Personalized Image Animator via Plug-and-Play Modules in Text-to-Image Models

SLICE: Stabilized LIME for Consistent Explanations for Image Classification

DemoCaricature: Democratising Caricature Generation with a Rough Sketch

Towards Automated Movie Trailer Generation

End-to-End Spatio-Temporal Action Localisation with Video Transformers

GenZI: Zero-Shot 3D Human-Scene Interaction Generation

Customization Assistant for Text-to-Image Generation

360+x: A Panoptic Multi-modal Scene Understanding Dataset

TRINS: Towards Multimodal Language Models that Can Read

EFHQ: Multi-purpose ExtremePose-Face-HQ dataset

Producing and Leveraging Online Map Uncertainty in Trajectory Prediction

Contrastive Learning for DeepFake Classification and Localization via Multi-Label Ranking

FaceLift: Semi-supervised 3D Facial Landmark Localization

Logarithmic Lenses: Exploring Log RGB Data for Image Classification

UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet Diffusion

Learning Group Activity Features Through Person Attribute Prediction

Unlocking Pre-trained Image Backbones for Semantic Image Synthesis

TokenCompose: Text-to-Image Diffusion with Token-level Supervision

Bayesian Diffusion Models for 3D Shape Reconstruction

MICap: A Unified Model for Identity-Aware Movie Descriptions

UFineBench: Towards Text-based Person Retrieval with Ultra-fine Granularity

Zero-Painter: Training-Free Layout Control for Text-to-Image Synthesis

Test-Time Zero-Shot Temporal Action Localization

EFormer: Enhanced Transformer towards Semantic-Contour Features of Foreground for Portraits Matting

HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3D

Language-driven Object Fusion into Neural Radiance Fields with Pose-Conditioned Dataset Updates

VTimeLLM: Empower LLM to Grasp Video Moments

Infer from What You Have Seen Before: Temporally-dependent Classifier for Semi-supervised Video Segmentation

FreeU: Free Lunch in Diffusion U-Net

Seeing the World through Your Eyes

Binding Touch to Everything: Learning Unified Multimodal Tactile Representations

Image Restoration by Denoising Diffusion Models with Iteratively Preconditioned Guidance

Towards Text-guided 3D Scene Composition

HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimation

Fusing Personal and Environmental Cues for Identification and Segmentation of First-Person Camera Wearers in Third-Person Views

Instance-aware Exploration-Verification-Exploitation for Instance ImageGoal Navigation

AnyScene: Customized Image Synthesis with Composited Foreground

Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transform

Accurate Spatial Gene Expression Prediction by Integrating Multi-Resolution Features

PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis

Color Shift Estimation-and-Correction for Image Enhancement

RegionGPT: Towards Region Understanding Vision Language Model

Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors

Relational Matching for Weakly Semi-Supervised Oriented Object Detection

In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing

TE-TAD: Towards Full End-to-End Temporal Action Detection via Time-Aligned Coordinate Expression

JointSQ: Joint Sparsification-Quantization for Distributed Learning

Holo-Relighting: Controllable Volumetric Portrait Relighting from a Single Image

Endow SAM with Keen Eyes: Temporal-spatial Prompt Learning for Video Camouflaged Object Detection

Relightful Harmonization: Lighting-aware Portrait Background Replacement

NICE: Neurogenesis Inspired Contextual Encoding for Replay-free Class Incremental Learning

Taming the Tail in Class-Conditional GANs: Knowledge Sharing via Unconditional Training at Lower Resolutions

Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences

Taming Mode Collapse in Score Distillation for Text-to-3D Generation

MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI

DeiT-LT: Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets

OmniViD: A Generative Framework for Universal Video Understanding

OrthCaps: An Orthogonal CapsNet with Sparse Attention Routing and Pruning

MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation

Fully Exploiting Every Real Sample: SuperPixel Sample Gradient Model Stealing

MorpheuS: Neural Dynamic 360° Surface Reconstruction from Monocular RGB-D Video

Capturing Closely Interacted Two-Person Motions with Reaction Priors

Pre-training Vision Models with Mandelbulb Variations

FocusMAE: Gallbladder Cancer Detection from Ultrasound Videos with Focused Masked Autoencoders

Contrastive Pre-Training with Multi-View Fusion for No-Reference Point Cloud Quality Assessment

Open-Set Domain Adaptation for Semantic Segmentation

LightOctree: Lightweight 3D Spatially-Coherent Indoor Lighting Estimation

One More Step: A Versatile Plug-and-Play Module for Rectifying Diffusion Schedule Flaws and Enhancing Low-Frequency Controls

pix2gestalt: Amodal Segmentation by Synthesizing Wholes

Bi-level Learning of Task-Specific Decoders for Joint Registration and One-Shot Medical Image Segmentation

On the Robustness of Large Multimodal Models Against Image Adversarial Attacks

FairCLIP: Harnessing Fairness in Vision-Language Learning

Noisy One-point Homographies are Surprisingly Good

CSTA: CNN-based Spatiotemporal Attention for Video Summarization

Atom-Level Optical Chemical Structure Recognition with Limited Supervision

Navigate Beyond Shortcuts: Debiased Learning Through the Lens of Neural Collapse

DiVa-360: The Dynamic Visual Dataset for Immersive Neural Fields

SUGAR: Pre-training 3D Visual Representations for Robotics

Separating the "Chirp" from the "Chat": Self-supervised Visual Grounding of Sound and Language

Learning Visual Prompt for Gait Recognition

WateRF: Robust Watermarks in Radiance Fields for Protection of Copyrights

GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models

SnAG: Scalable and Accurate Video Grounding

Epistemic Uncertainty Quantification For Pre-Trained Neural Networks

Active Generalized Category Discovery

CoG-DQA: Chain-of-Guiding Learning with Large Language Models for Diagram Question Answering

ArGue: Attribute-Guided Prompt Tuning for Vision-Language Models

Ranking Distillation for Open-Ended Video Question Answering with Insufficient Labels

Commonsense Prototype for Outdoor Unsupervised 3D Object Detection

PolarRec: Improving Radio Interferometric Data Reconstruction Using Polar Coordinates

LDP: Language-driven Dual-Pixel Image Defocus Deblurring Network

Language-driven All-in-one Adverse Weather Removal

LPSNet: End-to-End Human Pose and Shape Estimation with Lensless Imaging

GLaMM: Pixel Grounding Large Multimodal Model

Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners

ManiFPT: Defining and Analyzing Fingerprints of Generative Models

StyleCineGAN: Landscape Cinemagraph Generation using a Pre-trained StyleGAN

MS-MANO: Enabling Hand Pose Tracking with Biomechanical Constraints

CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion

Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentation

BSNet: Box-Supervised Simulation-assisted Mean Teacher for 3D Instance Segmentation

Question Aware Vision Transformer for Multimodal Reasoning

ICON: Incremental CONfidence for Joint Pose and Radiance Field Optimization

Robust Depth Enhancement via Polarization Prompt Fusion Tuning

Learning to Predict Activity Progress by Self-Supervised Video Alignment

Learning Large-Factor EM Image Super-Resolution with Generative Priors

PI3D: Efficient Text-to-3D Generation with Pseudo-Image Diffusion

Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval

PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation

Learning for Transductive Threshold Calibration in Open-World Recognition

Functional Diffusion

DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes

Self-Calibrating Vicinal Risk Minimisation for Model Calibration

VideoRF: Rendering Dynamic Radiance Fields as 2D Feature Video Streams

Interactive3D: Create What You Want by Interactive 3D Generation

Cinematic Behavior Transfer via NeRF-based Differentiable Filming

On Scaling Up a Multilingual Vision and Language Model

GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning

Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight Pruning

SonicVisionLM: Playing Sound with Vision Language Models

CORE-MPI: Consistency Object Removal with Embedding MultiPlane Image

Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Rendering

A Theory of Joint Light and Heat Transport for Lambertian Scenes

HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models

A Vision Check-up for Language Models

Amodal Ground Truth and Completion in the Wild

MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual Grounding

Novel Class Discovery for Ultra-Fine-Grained Visual Categorization

Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models

Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling

Real-Time Exposure Correction via Collaborative Transformations and Adaptive Sampling

Gaussian Splatting SLAM

UniMix: Towards Domain Adaptive and Generalizable LiDAR Semantic Segmentation in Adverse Weather

PromptCoT: Align Prompt Distribution via Adapted Chain-of-Thought

NeLF-Pro: Neural Light Field Probes for Multi-Scale Novel View Synthesis

A Simple Baseline for Efficient Hand Mesh Reconstruction

LaMPilot: An Open Benchmark Dataset for Autonomous Driving with Language Model Programs

OpenEQA: Embodied Question Answering in the Era of Foundation Models

Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction

Practical Measurements of Translucent Materials with Inter-Pixel Translucency Prior

Koala: Key Frame-Conditioned Long Video-LLM

Dynamic Policy-Driven Adaptive Multi-Instance Learning for Whole Slide Image Classification

Privacy-Preserving Optics for Enhancing Protection in Face De-Identification

PerceptionGPT: Effectively Fusing Visual Perception into LLM

Probing the 3D Awareness of Visual Foundation Models

BilevelPruning: Unified Dynamic and Static Channel Pruning for Convolutional Neural Networks

RTracker: Recoverable Tracking via PN Tree Structured Memory

Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models

View-Category Interactive Sharing Transformer for Incomplete Multi-View Multi-Label Learning

Editable Scene Simulation for Autonomous Driving via Collaborative LLM-Agents

Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models

Data-Efficient Multimodal Fusion on a Single GPU

PAD: Patch-Agnostic Defense against Adversarial Patch Attacks

A Simple and Effective Point-based Network for Event Camera 6-DOFs Pose Relocalization

PAIR Diffusion: A Comprehensive Multimodal Object-Level Image Editor

Learning Continuous 3D Words for Text-to-Image Generation

Region-Based Representations Revisited

Clustering Propagation for Universal Medical Image Segmentation

Content-Adaptive Non-Local Convolution for Remote Sensing Pansharpening

A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsampling

A Versatile Framework for Continual Test-Time Domain Adaptation: Balancing Discriminability and Generalizability

NeuRAD: Neural Rendering for Autonomous Driving

OmniMotionGPT: Animal Motion Generation with Limited Data

Efficient Solution of Point-Line Absolute Pose

SPIN: Simultaneous Perception Interaction and Navigation

V?: Guided Visual Search as a Core Mechanism in Multimodal LLMs

CAMixerSR: Only Details Need More "Attention"

Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs

MM-Narrator: Narrating Long-form Videos with Multimodal In-Context Learning

Gradient Reweighting: Towards Imbalanced Class-Incremental Learning

FISBe: A Real-World Benchmark Dataset for Instance Segmentation of Long-Range Thin Filamentous Structures

Visual Prompting for Generalized Few-shot Segmentation: A Multi-scale Approach

Can I Trust Your Answer? Visually Grounded Video Question Answering

POPDG: Popular 3D Dance Generation with PopDanceSet

RankMatch: Exploring the Better Consistency Regularization for Semi-supervised Semantic Segmentation

APISR: Anime Production Inspired Real-World Anime Super-Resolution

Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions

CoDe: An Explicit Content Decoupling Framework for Image Restoration

Scaling Laws of Synthetic Images for Model Training ... for Now

Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinement

Device-Wise Federated Network Pruning

SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers

ToNNO: Tomographic Reconstruction of a Neural Network’s Output for Weakly Supervised Segmentation of 3D Medical Images

D^4: Dataset Distillation via Disentangled Diffusion Model

Physics-Aware Hand-Object Interaction Denoising

Face2Diffusion for Fast and Editable Face Personalization

HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding

GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting

Active Object Detection with Knowledge Aggregation and Distillation from Large Models

ShapeWalk: Compositional Shape Editing Through Language-Guided Chains

DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement

Score-Guided Diffusion for 3D Human Recovery

An Empirical Study of the Generalization Ability of Lidar 3D Object Detectors to Unseen Domains

PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees

MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Correlation

Rethinking FID: Towards a Better Evaluation Metric for Image Generation

MarkovGen: Structured Prediction for Efficient Text-to-Image Generation

GAFusion: Adaptive Fusing LiDAR and Camera with Multiple Guidance for 3D Object Detection

H-ViT: A Hierarchical Vision Transformer for Deformable Image Registration

RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation

Rethinking the Representation in Federated Unsupervised Learning with Non-IID Data

SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshes

Training-Free Pretrained Model Merging

Neural Visibility Field for Uncertainty-Driven Active Mapping

Progress-Aware Online Action Segmentation for Egocentric Procedural Task Videos

ViLa-MIL: Dual-scale Vision-Language Multiple Instance Learning for Whole Slide Image Classification

MOHO: Learning Single-view Hand-held Object Reconstruction with Multi-view Occlusion-Aware Supervision

Scalable 3D Registration via Truncated Entry-wise Absolute Residuals

Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance

Asymmetric Masked Distillation for Pre-Training Small Foundation Models

Faces that Speak: Jointly Synthesising Talking Face and Speech from Text

Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs

Learning to Segment Referred Objects from Narrated Egocentric Videos

Generative Image Dynamics

CaDeT: a Causal Disentanglement Approach for Robust Trajectory Prediction in Autonomous Driving

EGTR: Extracting Graph from Transformer for Scene Graph Generation

Continual Forgetting for Pre-trained Vision Models

AlignMiF: Geometry-Aligned Multimodal Implicit Field for LiDAR-Camera Joint Synthesis

Distributionally Generative Augmentation for Fair Facial Attribute Classification

CVT-xRF: Contrastive In-Voxel Transformer for 3D Consistent Radiance Fields from Sparse Inputs

BodyMAP - Jointly Predicting Body Mesh and 3D Applied Pressure Map for People in Bed

PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks

Bootstrapping Chest CT Image Understanding by Distilling Knowledge from X-ray Expert Models

Boosting Neural Representations for Videos with a Conditional Decoder

Unsupervised Feature Learning with Emergent Data-Driven Prototypicality

Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence

THRONE: An Object-based Hallucination Benchmark for the Free-form Generations of Large Vision-Language Models

UniVS: Unified and Universal Video Segmentation with Prompts as Queries

Text-Guided 3D Face Synthesis - From Generation to Editing

Clockwork Diffusion: Efficient Generation With Model-Step Distillation

VLP: Vision Language Planning for Autonomous Driving

Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models

Inlier Confidence Calibration for Point Cloud Registration

CLIP-BEVFormer: Enhancing Multi-View Image-Based BEV Detector with Ground Truth Flow

Memory-Scalable and Simplified Functional Map Learning

ADFactory: An Effective Framework for Generalizing Optical Flow with NeRF

IReNe: Instant Recoloring of Neural Radiance Fields

AssistGUI: Task-Oriented PC Graphical User Interface Automation

HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions

Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversity

3D Building Reconstruction from Monocular Remote Sensing Images with Multi-level Supervisions

Improving Physics-Augmented Continuum Neural Radiance Field-Based Geometry-Agnostic System Identification with Lagrangian Particle Optimization

In Search of a Data Transformation That Accelerates Neural Field Training

Constrained Layout Generation with Factor Graphs

FastMAC: Stochastic Spectral Sampling of Correspondence Graph

Learning the 3D Fauna of the Web

Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers

URHand: Universal Relightable Hands

Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions

Modular Blind Video Quality Assessment

Towards Robust 3D Object Detection with LiDAR and 4D Radar Fusion in Various Weather Conditions

Relightable Gaussian Codec Avatars

SIGNeRF: Scene Integrated Generation for Neural Radiance Fields

Synergistic Global-space Camera and Human Reconstruction from Videos

PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution

Neural Implicit Morphing of Face Images

Towards Generalizing to Unseen Domains with Few Labels

Focus on Your Instruction: Fine-grained and Multi-instruction Image Editing by Attention Modulation

What How and When Should Object Detectors Update in Continually Changing Test Domains?

Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts

Distilling CLIP with Dual Guidance for Learning Discriminative Human Body Shape Representation

Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation

Improving Semantic Correspondence with Viewpoint-Guided Spherical Maps

Snapshot Lidar: Fourier Embedding of Amplitude and Phase for Single-Image Depth Reconstruction

CARZero: Cross-Attention Alignment for Radiology Zero-Shot Classification

MedM2G: Unifying Medical Multi-Modal Generation via Cross-Guided Diffusion with Visual Invariant

Programmable Motion Generation for Open-Set Motion Control Tasks

Learning Degradation-Independent Representations for Camera ISP Pipelines

GLID: Pre-training a Generalist Encoder-Decoder Vision Model

Projecting Trackable Thermal Patterns for Dynamic Computer Vision

Your Image is My Video: Reshaping the Receptive Field via Image-To-Video Differentiable AutoAugmentation and Fusion

NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priors

Kernel Adaptive Convolution for Scene Text Detection via Distance Map Prediction

Control4D: Efficient 4D Portrait Editing with Text

ConsistNet: Enforcing 3D Consistency for Multi-view Images Diffusion

A Subspace-Constrained Tyler's Estimator and its Applications to Structure from Motion

Osprey: Pixel Understanding with Visual Instruction Tuning

NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation

Contrastive Denoising Score for Text-guided Latent Diffusion Image Editing

Diffusion-driven GAN Inversion for Multi-Modal Face Image Generation

Domain Prompt Learning with Quaternion Networks

Low-Resource Vision Challenges for Foundation Models

Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis

LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning

Long-Tailed Anomaly Detection with Learnable Class Names

Enhancing 3D Object Detection with 2D Detection-Guided Query Anchors

PlatoNeRF: 3D Reconstruction in Plato's Cave via Single-View Two-Bounce Lidar

Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning

DiffLoc: Diffusion Model for Outdoor LiDAR Localization

Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives

PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization

Estimating Noisy Class Posterior with Part-level Labels for Noisy Label Learning

Low-Latency Neural Stereo Streaming

Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment

Unmixing Diffusion for Self-Supervised Hyperspectral Image Denoising

ZeroShape: Regression-based Zero-shot Shape Reconstruction

Your Transferability Barrier is Fragile: Free-Lunch for Transferring the Non-Transferable Learning

ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe

DPHMs: Diffusion Parametric Head Models for Depth-based Tracking

CNC-Net: Self-Supervised Learning for CNC Machining Operations

MaxQ: Multi-Axis Query for N:M Sparsity Network

High-Quality Facial Geometry and Appearance Capture at Home

Text-Guided Variational Image Generation for Industrial Anomaly Detection and Segmentation

Tackling the Singularities at the Endpoints of Time Intervals in Diffusion Models

The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes

mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration

Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models

Deep Equilibrium Diffusion Restoration with Parallel Sampling

One-Class Face Anti-spoofing via Spoof Cue Map-Guided Feature Learning

Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Data

Efficient Scene Recovery Using Luminous Flux Prior

Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understanding

Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning

Multiple View Geometry Transformers for 3D Human Pose Estimation

Soften to Defend: Towards Adversarial Robustness via Self-Guided Label Refinement

Anatomically Constrained Implicit Face Models

Structured Gradient-based Interpretations via Norm-Regularized Adversarial Training

Revisiting Global Translation Estimation with Feature Tracks

LoCoNet: Long-Short Context Network for Active Speaker Detection

WinSyn: : A High Resolution Testbed for Synthetic Data

Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection

Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learning

Neural Super-Resolution for Real-time Rendering with Radiance Demodulation

Efficient Stitchable Task Adaptation

MeaCap: Memory-Augmented Zero-shot Image Captioning

MuseChat: A Conversational Music Recommendation System for Videos

Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation

Efficient Multitask Dense Predictor via Binarization

Novel View Synthesis with View-Dependent Effects from a Single Image

Wired Perspectives: Multi-View Wire Art Embraces Generative AI

UltrAvatar: A Realistic Animatable 3D Avatar Diffusion Model with Authenticity Guided Textures

Orchestrate Latent Expertise: Advancing Online Continual Learning with Multi-Level Supervision and Reverse Self-Distillation

Small Scale Data-Free Knowledge Distillation

Transfer CLIP for Generalizable Image Denoising

Alchemist: Parametric Control of Material Properties with Diffusion Models

DisCo: Disentangled Control for Realistic Human Dance Generation

Validating Privacy-Preserving Face Recognition under a Minimum Assumption

FLHetBench: Benchmarking Device and State Heterogeneity in Federated Learning

Text Is MASS: Modeling as Stochastic Embedding for Text-Video Retrieval

JRDB-Social: A Multifaceted Robotic Dataset for Understanding of Context and Dynamics of Human Interactions Within Social Groups

Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding

Suppress and Rebalance: Towards Generalized Multi-Modal Face Anti-Spoofing

Constructing and Exploring Intermediate Domains in Mixed Domain Semi-supervised Medical Image Segmentation

Named Entity Driven Zero-Shot Image Manipulation

Non-Rigid Structure-from-Motion: Temporally-Smooth Procrustean Alignment and Spatially-Variant Deformation Modeling

LAMP: Learn A Motion Pattern for Few-Shot Video Generation

CLiC: Concept Learning in Context

IDGuard: Robust General Identity-centric POI Proactive Defense Against Face Editing Abuse

LEAD: Exploring Logit Space Evolution for Model Selection

PixelLM: Pixel Reasoning with Large Multimodal Model

Cross Initialization for Face Personalization of Text-to-Image Models

Towards CLIP-driven Language-free 3D Visual Grounding via 2D-3D Relational Enhancement and Consistency

MR-VNet: Media Restoration using Volterra Networks

iKUN: Speak to Trackers without Retraining

Neural Fields as Distributions: Signal Processing Beyond Euclidean Space

3D Geometry-Aware Deformable Gaussian Splatting for Dynamic View Synthesis

Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-speech Gesture Generation

LaRE^2: Latent Reconstruction Error Based Method for Diffusion-Generated Image Detection

Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology

Stratified Avatar Generation from Sparse Observations

Few-shot Learner Parameterization by Diffusion Time-steps

StreamingFlow: Streaming Occupancy Forecasting with Asynchronous Multi-modal Data Streams via Neural Ordinary Differential Equation

SocialCircle: Learning the Angle-based Social Interaction Representation for Pedestrian Trajectory Prediction

Global and Hierarchical Geometry Consistency Priors for Few-shot NeRFs in Indoor Scenes

Lookahead Exploration with Neural Radiance Representation for Continuous Vision-Language Navigation

Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis

The STVchrono Dataset: Towards Continuous Change Recognition in Time

Event-based Structure-from-Orbit

SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation

VideoMAC: Video Masked Autoencoders Meet ConvNets

Unleashing Channel Potential: Space-Frequency Selection Convolution for SAR Object Detection

Motion Blur Decomposition with Cross-shutter Guidance

Real-time Acquisition and Reconstruction of Dynamic Volumes with Neural Structured Illumination

Mind Marginal Non-Crack Regions: Clustering-Inspired Representation Learning for Crack Segmentation

SpatialTracker: Tracking Any 2D Pixels in 3D Space

TRIP: Temporal Residual Learning with Image Noise Prior for Image-to-Video Diffusion Models

FreePoint: Unsupervised Point Cloud Instance Segmentation

Perceptual Assessment and Optimization of HDR Image Rendering

Pose-Transformed Equivariant Network for 3D Point Trajectory Prediction

FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuning

Object Dynamics Modeling with Hierarchical Point Cloud-based Representations

Pick-or-Mix: Dynamic Channel Sampling for ConvNets

Test-Time Adaptation for Depth Completion

Efficient Hyperparameter Optimization with Adaptive Fidelity Identification

MESA: Matching Everything by Segmenting Anything

Dispel Darkness for Better Fusion: A Controllable Visual Enhancer based on Cross-modal Conditional Adversarial Learning

Time-Efficient Light-Field Acquisition Using Coded Aperture and Events

Video-P2P: Video Editing with Cross-attention Control

LION: Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge

The More You See in 2D the More You Perceive in 3D

Pixel-Aligned Language Model

Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection

Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications

Rethinking the Evaluation Protocol of Domain Generalization

PFStorer: Personalized Face Restoration and Super-Resolution

Dual-Scale Transformer for Large-Scale Single-Pixel Imaging

What When and Where? Self-Supervised Spatio-Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructions

Eclipse: Disambiguating Illumination and Materials using Unintended Shadows

ASAM: Boosting Segment Anything Model with Adversarial Tuning

ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis

2S-UDF: A Novel Two-stage UDF Learning Method for Robust Non-watertight Model Reconstruction from Multi-view Images

A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution

Continuous Optical Zooming: A Benchmark for Arbitrary-Scale Image Super-Resolution in Real World

Multimodal Representation Learning by Alternating Unimodal Adaptation

OmniParser: A Unified Framework for Text Spotting Key Information Extraction and Table Recognition

Compositional Video Understanding with Spatiotemporal Structure-based Transformers

FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models

Boosting Order-Preserving and Transferability for Neural Architecture Search: a Joint Architecture Refined Search and Fine-tuning Approach

Driving Everywhere with Large Language Model Policy Adaptation

Make-It-Vivid: Dressing Your Animatable Biped Cartoon Characters from Text

Exploiting Diffusion Prior for Generalizable Dense Prediction

GSVA: Generalized Segmentation via Multimodal Large Language Models

ElasticDiffusion: Training-free Arbitrary Size Image Generation through Global-Local Content Separation

General Point Model Pretraining with Autoencoding and Autoregressive

Learning Instance-Aware Correspondences for Robust Multi-Instance Point Cloud Registration in Cluttered Scenes

A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions

Fine-grained Prototypical Voting with Heterogeneous Mixup for Semi-supervised 2D-3D Cross-modal Retrieval

Uncertainty Visualization via Low-Dimensional Posterior Projections

GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh

Coherent Temporal Synthesis for Incremental Action Segmentation

Person in Place: Generating Associative Skeleton-Guidance Maps for Human-Object Interaction Image Editing

Real-Time Neural BRDF with Spherically Distributed Primitives

Omni-Q: Omni-Directional Scene Understanding for Unsupervised Visual Grounding

RCL: Reliable Continual Learning for Unified Failure Detection

Correlation-Decoupled Knowledge Distillation for Multimodal Sentiment Analysis with Incomplete Modalities

ES³: Evolving Self-Supervised Learning of Robust Audio-Visual Speech Representations

Depth-aware Test-Time Training for Zero-shot Video Object Segmentation

MSU-4S - The Michigan State University Four Seasons Dataset

Estimating Extreme 3D Image Rotations using Cascaded Attention

KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformation

Communication-Efficient Federated Learning with Accelerated Client Gradient

Taming Stable Diffusion for Text to 360 Panorama Image Generation

Real-time 3D-aware Portrait Video Relighting

CAMEL: CAusal Motion Enhancement Tailored for Lifting Text-driven Video Editing

Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery

Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network

Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular Stereo and RGB-D Cameras

Attention Calibration for Disentangled Text-to-Image Personalization

SmartMask: Context Aware High-Fidelity Mask Generation for Fine-grained Object Insertion and Layout Control

GraCo: Granularity-Controllable Interactive Segmentation

HandDiff: 3D Hand Pose Estimation with Diffusion on Image-Point Cloud

DuPL: Dual Student with Trustworthy Progressive Learning for Robust Weakly Supervised Semantic Segmentation

Segment Every Out-of-Distribution Object

Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution

Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild

A Physics-informed Low-rank Deep Neural Network for Blind and Universal Lens Aberration Correction

DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data

An Interactive Navigation Method with Effect-oriented Affordance

VOODOO 3D: Volumetric Portrait Disentanglement For One-Shot 3D Head Reenactment

Rapid 3D Model Generation with Intuitive 3D Input

NAPGuard: Towards Detecting Naturalistic Adversarial Patches

Descriptor and Word Soups: Overcoming the Parameter Efficiency Accuracy Tradeoff for Out-of-Distribution Few-shot Learning

A Stealthy Wrongdoer: Feature-Oriented Reconstruction Attack against Split Learning

Masked and Shuffled Blind Spot Denoising for Real-World Images

MCD: Diverse Large-Scale Multi-Campus Dataset for Robot Perception

Open-Vocabulary Object 6D Pose Estimation

Bootstrapping SparseFormers from Vision Foundation Models

NARUTO: Neural Active Reconstruction from Uncertain Target Observations

PortraitBooth: A Versatile Portrait Model for Fast Identity-preserved Personalization

DreamPropeller: Supercharge Text-to-3D Generation with Parallel Sampling

Generative Region-Language Pretraining for Open-Ended Object Detection

Diff-Plugin: Revitalizing Details for Diffusion-based Low-level Tasks

Boosting Diffusion Models with Moving Average Sampling in Frequency Domain

Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches

Text-Enhanced Data-free Approach for Federated Class-Incremental Learning

Psychometry: An Omnifit Model for Image Reconstruction from Human Brain Activity

G-NeRF: Geometry-enhanced Novel View Synthesis from Single-View Images

Unsupervised Salient Instance Detection

L-MAGIC: Language Model Assisted Generation of Images with Coherence

MoCha-Stereo: Motif Channel Attention Network for Stereo Matching

Discovering Syntactic Interaction Clues for Human-Object Interaction Detection

GLACE: Global Local Accelerated Coordinate Encoding

Active Prompt Learning in Vision Language Models

HouseCat6D - A Large-Scale Multi-Modal Category Level 6D Object Perception Dataset with Household Objects in Realistic Scenarios

FINER: Flexible Spectral-bias Tuning in Implicit NEural Representation by Variable-periodic Activation Functions

Open-World Human-Object Interaction Detection via Multi-modal Prompts

MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation

Quantifying Uncertainty in Motion Prediction with Variational Bayesian Mixture

VidToMe: Video Token Merging for Zero-Shot Video Editing

Text-Image Alignment for Diffusion-Based Perception

RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback

Neural 3D Strokes: Creating Stylized 3D Scenes with Vectorized 3D Strokes

Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception

CoDi-2: In-Context Interleaved and Interactive Any-to-Any Generation

Generative Latent Coding for Ultra-Low Bitrate Image Compression

Selectively Informative Description can Reduce Undesired Embedding Entanglements in Text-to-Image Personalization

Flexible Depth Completion for Sparse and Varying Point Densities

Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners

Generating Handwritten Mathematical Expressions From Symbol Graphs: An End-to-End Pipeline

On the Robustness of Language Guidance for Low-Level Vision Tasks: Findings from Depth Estimation

SingularTrajectory: Universal Trajectory Predictor Using Diffusion Model

SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Tasks

TexVocab: Texture Vocabulary-conditioned Human Avatars

Sparse Global Matching for Video Frame Interpolation with Large Motion

When Visual Grounding Meets Gigapixel-level Large-scale Scenes: Benchmark and Approach

Mitigating Motion Blur in Neural Radiance Fields with Events and Frames

Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D Features

Alpha-CLIP: A CLIP Model Focusing on Wherever You Want

DemoFusion: Democratising High-Resolution Image Generation With No $$$

PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation

Dr.Hair: Reconstructing Scalp-Connected Hair Strands without Pre-Training via Differentiable Rendering of Line Segments

AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resolution

Domain Separation Graph Neural Networks for Saliency Object Ranking

Solving the Catastrophic Forgetting Problem in Generalized Category Discovery

Improving Image Restoration through Removing Degradations in Textual Representations

SketchINR: A First Look into Sketches as Implicit Neural Representations

Activity-Biometrics: Person Identification from Daily Activities

Holoported Characters: Real-time Free-viewpoint Rendering of Humans from Sparse RGB Cameras

Neighbor Relations Matter in Video Scene Detection

NOPE: Novel Object Pose Estimation from a Single Image

Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving

WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models

MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection

Instance-level Expert Knowledge and Aggregate Discriminative Attention for Radiology Report Generation

HyperSDFusion: Bridging Hierarchical Structures in Language and Geometry for Enhanced 3D Text2Shape Generation

MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Images

Resource-Efficient Transformer Pruning for Finetuning of Large Models

Link-Context Learning for Multimodal LLMs

Fast ODE-based Sampling for Diffusion Models in Around 5 Steps

Referring Image Editing: Object-level Image Editing via Referring Expressions

InNeRF360: Text-Guided 3D-Consistent Object Inpainting on 360-degree Neural Radiance Fields

BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP

The Manga Whisperer: Automatically Generating Transcriptions for Comics

Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes

TeMO: Towards Text-Driven 3D Stylization for Multi-Object Meshes

Morphological Prototyping for Unsupervised Slide Representation Learning in Computational Pathology

From-Ground-To-Objects: Coarse-to-Fine Self-supervised Monocular Depth Estimation of Dynamic Objects with Ground Contact Prior

Deep-TROJ: An Inference Stage Trojan Insertion Algorithm through Efficient Weight Replacement Attack

CLIP-KD: An Empirical Study of CLIP Model Distillation

Dynamic LiDAR Re-simulation using Compositional Neural Fields

Unsupervised Blind Image Deblurring Based on Self-Enhancement

Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model

ProMotion: Prototypes As Motion Learners

Zero-Shot Structure-Preserving Diffusion Model for High Dynamic Range Tone Mapping

Mask Grounding for Referring Image Segmentation

SignGraph: A Sign Sequence is Worth Graphs of Nodes

CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learning

SOAC: Spatio-Temporal Overlap-Aware Multi-Sensor Calibration using Neural Radiance Fields

SemCity: Semantic Scene Generation with Triplane Diffusion

Just Add ?! Pose Induced Video Transformers for Understanding Activities of Daily Living

Language-aware Visual Semantic Distillation for Video Question Answering

3DInAction: Understanding Human Actions in 3D Point Clouds

Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation

VkD: Improving Knowledge Distillation using Orthogonal Projections

Embracing Unimodal Aleatoric Uncertainty for Robust Multimodal Fusion

DiLiGenRT: A Photometric Stereo Dataset with Quantified Roughness and Translucency

StyLitGAN: Image-Based Relighting via Latent Control

Label-Efficient Group Robustness via Out-of-Distribution Concept Curation

DGC-GNN: Leveraging Geometry and Color Cues for Visual Descriptor-Free 2D-3D Matching

Anomaly Score: Evaluating Generative Models and Individual Generated Images based on Complexity and Vulnerability

FreeDrag: Feature Dragging for Reliable Point-based Image Editing

Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation

TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models

Multiplane Prior Guided Few-Shot Aerial Scene Rendering

Coherence As Texture – Passive Textureless 3D Reconstruction by Self-interference

PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics

Viewpoint-Aware Visual Grounding in 3D Scenes

A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectives

VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning

Unsupervised Universal Image Segmentation

Compact 3D Gaussian Representation for Radiance Field

Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer

PTM-VQA: Efficient Video Quality Assessment Leveraging Diverse PreTrained Models from the Wild

FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations

Batch Normalization Alleviates the Spectral Bias in Coordinate Networks

FlowIE: Efficient Image Enhancement via Rectified Flow

Combining Frame and GOP Embeddings for Neural Video Representation

OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation

TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models

GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians

Not All Classes Stand on Same Embeddings: Calibrating a Semantic Distance with Metric Tensor

CodedEvents: Optimal Point-Spread-Function Engineering for 3D-Tracking with Event Cameras

Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling

OMG-Seg: Is One Model Good Enough For All Segmentation?

Pose Adapted Shape Learning for Large-Pose Face Reenactment

Generative Rendering: Controllable 4D-Guided Video Generation with 2D Diffusion Models

Improving Out-of-Distribution Generalization in Graphs via Hierarchical Semantic Environments

Towards Understanding and Improving Adversarial Robustness of Vision Transformers

Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models

ZePT: Zero-Shot Pan-Tumor Segmentation via Query-Disentangling and Self-Prompting

Dynamic Cues-Assisted Transformer for Robust Point Cloud Registration

Improved Self-Training for Test-Time Adaptation

Retrieval-Augmented Open-Vocabulary Object Detection

CADTalk: An Algorithm and Benchmark for Semantic Commenting of CAD Programs

Structure-Aware Sparse-View X-ray 3D Reconstruction

Explaining CLIP's Performance Disparities on Data from Blind/Low Vision Users

MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models

NB-GTR: Narrow-Band Guided Turbulence Removal

LangSplat: 3D Language Gaussian Splatting

Mudslide: A Universal Nuclear Instance Segmentation Method

Long-Tail Class Incremental Learning via Independent Sub-prototype Construction

LaneCPP: Continuous 3D Lane Detection using Physical Priors

Physical Backdoor: Towards Temperature-based Backdoor Attacks in the Physical World

Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining

SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors

Positive-Unlabeled Learning by Latent Group-Aware Meta Disambiguation

Contextrast: Contextual Contrastive Learning for Semantic Segmentation

DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data

PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videos

Text-conditional Attribute Alignment across Latent Spaces for 3D Controllable Face Image Synthesis

MonoCD: Monocular 3D Object Detection with Complementary Depths

Revisiting Spatial-Frequency Information Integration from a Hierarchical Perspective for Panchromatic and Multi-Spectral Image Fusion

LiveHPS: LiDAR-based Scene-level Human Pose and Shape Estimation in Free Environment

JeDi: Joint-Image Diffusion Models for Finetuning-Free Personalized Text-to-Image Generation

G3DR: Generative 3D Reconstruction in ImageNet

Evidential Active Recognition: Intelligent and Prudent Open-World Embodied Perception

SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering

Modeling Collaborator: Enabling Subjective Vision Classification With Minimal Human Effort via LLM Tool-Use

OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning

FineSports: A Multi-person Hierarchical Sports Video Dataset for Fine-grained Action Understanding

An Aggregation-Free Federated Learning for Tackling Data Heterogeneity

Zero-Reference Low-Light Enhancement via Physical Quadruple Priors

Infrared Adversarial Car Stickers

DiffusionPoser: Real-time Human Motion Reconstruction From Arbitrary Sparse Sensors Using Autoregressive Diffusion

HumanRef: Single Image to 3D Human Generation via Reference-Guided Diffusion

MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning

Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localization

Diffusion Time-step Curriculum for One Image to 3D Generation

CurveCloudNet: Processing Point Clouds with 1D Structure

CA-Jaccard: Camera-aware Jaccard Distance for Person Re-identification

Harnessing Meta-Learning for Improving Full-Frame Video Stabilization

CURSOR: Scalable Mixed-Order Hypergraph Matching with CUR Decomposition

FCS: Feature Calibration and Separation for Non-Exemplar Class Incremental Learning

Seg2Reg: Differentiable 2D Segmentation to 1D Regression Rendering for 360 Room Layout Reconstruction

Boosting Adversarial Transferability by Block Shuffle and Rotation

Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving

Discovering and Mitigating Visual Biases through Keyword Explanation

XFibrosis: Explicit Vessel-Fiber Modeling for Fibrosis Staging from Liver Pathology Images

Advancing Saliency Ranking with Human Fixations: Dataset Models and Benchmarks

GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs

GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting

SeaBird: Segmentation in Bird’s View with Dice Loss Improves Monocular 3D Detection of Large Objects

DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection

MoML: Online Meta Adaptation for 3D Human Motion Prediction

Move as You Say Interact as You Can: Language-guided Human Motion Generation with Scene Affordance

Exploring Regional Clues in CLIP for Zero-Shot Semantic Segmentation

GALA: Generating Animatable Layered Assets from a Single Scan

Improving Graph Contrastive Learning via Adaptive Positive Sampling

Unveiling the Power of Audio-Visual Early Fusion Transformers with Dense Interactions through Masked Modeling

Single Mesh Diffusion Models with Field Latents for Texture Generation

PEM: Prototype-based Efficient MaskFormer for Image Segmentation

VILA: On Pre-training for Visual Language Models

Hearing Anything Anywhere

Dr2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning

Vision-and-Language Navigation via Causal Learning

Diffusion-EDFs: Bi-equivariant Denoising Generative Modeling on SE(3) for Visual Robotic Manipulation

BOTH2Hands: Inferring 3D Hands from Both Text Prompts and Body Dynamics

Move Anything with Layered Scene Diffusion

A Closer Look at the Few-Shot Adaptation of Large Vision-Language Models

A Noisy Elephant in the Room: Is Your Out-of-Distribution Detector Robust to Label Noise?

Learning with Structural Labels for Learning with Noisy Labels

Learning Diffusion Texture Priors for Image Restoration

What If the TV Was Off? Examining Counterfactual Reasoning Abilities of Multi-modal Language Models

Rethinking Diffusion Model for Multi-Contrast MRI Super-Resolution

Bayesian Exploration of Pre-trained Models for Low-shot Image Classification

PLGSLAM: Progressive Neural Scene Represenation with Local to Global Bundle Adjustment

RecDiffusion: Rectangling for Image Stitching with Diffusion Models

Incremental Nuclei Segmentation from Histopathological Images via Future-class Awareness and Compatibility-inspired Distillation

DriveTrack: A Benchmark for Long-Range Point Tracking in Real-World Videos

Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions

Arbitrary-Scale Image Generation and Upsampling using Latent Diffusion Model and Implicit Neural Decoder

Implicit Event-RGBD Neural SLAM

Three Pillars Improving Vision Foundation Model Distillation for Lidar

Retraining-Free Model Quantization via One-Shot Weight-Coupling Learning

DreamControl: Control-Based Text-to-3D Generation with 3D Self-Prior

No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentation

Model Inversion Robustness: Can Transfer Learning Help?

Scene-adaptive and Region-aware Multi-modal Prompt for Open Vocabulary Object Detection

Seamless Human Motion Composition with Blended Positional Encodings

Single Domain Generalization for Crowd Counting

Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Tracking

Collaborative Learning of Anomalies with Privacy (CLAP) for Unsupervised Video Anomaly Detection: A New Baseline

RepKPU: Point Cloud Upsampling with Kernel Point Representation and Deformation

InteractDiffusion: Interaction Control in Text-to-Image Diffusion Models

SG-BEV: Satellite-Guided BEV Fusion for Cross-View Semantic Segmentation

MAP: MAsk-Pruning for Source-Free Model Intellectual Property Protection

4K4D: Real-Time 4D View Synthesis at 4K Resolution

PELA: Learning Parameter-Efficient Models with Low-Rank Approximation

Context-Guided Spatio-Temporal Video Grounding

Exploring Efficient Asymmetric Blind-Spots for Self-Supervised Denoising in Real-World Scenarios

Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis

Reconstruction-free Cascaded Adaptive Compressive Sensing

From Coarse to Fine-Grained Open-Set Recognition

DSL-FIQA: Assessing Facial Image Quality via Dual-Set Degradation Learning and Landmark-Guided Transformer

Exploiting Inter-sample and Inter-feature Relations in Dataset Distillation

Discriminative Pattern Calibration Mechanism for Source-Free Domain Adaptation

RAM-Avatar: Real-time Photo-Realistic Avatar from Monocular Videos with Full-body Control

Multi-Level Neural Scene Graphs for Dynamic Urban Environments

Towards Generalizable Multi-Object Tracking

DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation

EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation

One-step Diffusion with Distribution Matching Distillation

Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction

Differentiable Display Photometric Stereo

TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation

On Exact Inversion of DPM-Solvers

Generate Like Experts: Multi-Stage Font Generation by Incorporating Font Transfer Process into Diffusion Models

A Unified Diffusion Framework for Scene-aware Human Motion Estimation from Sparse Signals

Towards Surveillance Video-and-Language Understanding: New Dataset Baselines and Challenges

Re-thinking Data Availability Attacks Against Deep Neural Networks

PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding

Privacy-Preserving Face Recognition Using Trainable Feature Subtraction

Consistent3D: Towards Consistent High-Fidelity Text-to-3D Generation with Deterministic Sampling Prior

Locally Adaptive Neural 3D Morphable Models

Benchmarking Segmentation Models with Mask-Preserved Attribute Editing

MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning

DePT: Decoupled Prompt Tuning

GROUNDHOG: Grounding Large Language Models to Holistic Segmentation

DAVE - A Detect-and-Verify Paradigm for Low-Shot Counting

Improving Spectral Snapshot Reconstruction with Spectral-Spatial Rectification

D3T: Distinctive Dual-Domain Teacher Zigzagging Across RGB-Thermal Gap for Domain-Adaptive Object Detection

Logit Standardization in Knowledge Distillation

Progressive Divide-and-Conquer via Subsampling Decomposition for Accelerated MRI

A Unified Approach for Text- and Image-guided 4D Scene Generation

MAGICK: A Large-scale Captioned Dataset from Matting Generated Images using Chroma Keying

Intrinsic Image Diffusion for Indoor Single-view Material Estimation

CONFORM: Contrast is All You Need for High-Fidelity Text-to-Image Diffusion Models

RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection

Prompt Highlighter: Interactive Control for Multi-Modal LLMs

One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models

Self-Supervised Multi-Object Tracking with Path Consistency

Arbitrary Motion Style Transfer with Multi-condition Motion Latent Diffusion Model

3DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labelling

Sequential Modeling Enables Scalable Learning for Large Vision Models

SPECAT: SPatial-spEctral Cumulative-Attention Transformer for High-Resolution Hyperspectral Image Reconstruction

Video-Based Human Pose Regression via Decoupled Space-Time Aggregation

Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?

NetTrack: Tracking Highly Dynamic Objects with a Net

Scaling Up Video Summarization Pretraining with Large Language Models

Neural Refinement for Absolute Pose Regression with Feature Synthesis

CLIPtone: Unsupervised Learning for Text-based Image Tone Adjustment

VGGSfM: Visual Geometry Grounded Deep Structure From Motion

Single-View Scene Point Cloud Human Grasp Generation

Boosting Image Restoration via Priors from Pre-trained Models

UVEB: A Large-scale Benchmark and Baseline Towards Real-World Underwater Video Enhancement

CPP-Net: Embracing Multi-Scale Feature Fusion into Deep Unfolding CP-PPA Network for Compressive Sensing

Video Recognition in Portrait Mode

Online Task-Free Continual Generative and Discriminative Learning via Dynamic Cluster Memory

FADES: Fair Disentanglement with Sensitive Relevance

Versatile Navigation Under Partial Observability via Value-guided Diffusion Policy

Point Segment and Count: A Generalized Framework for Object Counting

CPR-Coach: Recognizing Composite Error Actions based on Single-class Training

A Generative Approach for Wikipedia-Scale Visual Entity Recognition

GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objects

PKU-DyMVHumans: A Multi-View Video Benchmark for High-Fidelity Dynamic Human Modeling

DiffCast: A Unified Framework via Residual Diffusion for Precipitation Nowcasting

Improving Depth Completion via Depth Feature Upsampling

GEARS: Local Geometry-aware Hand-object Interaction Synthesis

GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions

Deep Single Image Camera Calibration by Heatmap Regression to Recover Fisheye Images Under Manhattan World Assumption

MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers

3D-Aware Face Editing via Warping-Guided Latent Direction Learning

RadarDistill: Boosting Radar-based Object Detection Performance via Knowledge Distillation from LiDAR Features

MatFuse: Controllable Material Generation with Diffusion Models

Fair-VPT: Fair Visual Prompt Tuning for Image Classification

Restoration by Generation with Constrained Priors

Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer

Cache Me if You Can: Accelerating Diffusion Models through Block Caching

Learning to Visually Localize Sound Sources from Mixtures without Prior Source Knowledge

Task-Conditioned Adaptation of Visual Features in Multi-Task Policy Learning

ESR-NeRF: Emissive Source Reconstruction Using LDR Multi-view Images

Autoregressive Queries for Adaptive Tracking with Spatio-Temporal Transformers

OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning

MRFS: Mutually Reinforcing Image Fusion and Segmentation

Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning

EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protection

VidLA: Video-Language Alignment at Scale

Revisiting Single Image Reflection Removal In the Wild

Facial Identity Anonymization via Intrinsic and Extrinsic Attention Distraction

OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning

3D-LFM: Lifting Foundation Model

Localization Is All You Evaluate: Data Leakage in Online Mapping Datasets and How to Fix It

CLOVA: A Closed-LOop Visual Assistant with Tool Usage and Update

EasyDrag: Efficient Point-based Manipulation on Diffusion Models

TutteNet: Injective 3D Deformations by Composition of 2D Mesh Deformations

Point2RBox: Combine Knowledge from Synthetic Visual Patterns for End-to-end Oriented Object Detection with Single Point Supervision

Generating Illustrated Instructions

LASIL: Learner-Aware Supervised Imitation Learning For Long-term Microscopic Traffic Simulation

Rethinking the Spatial Inconsistency in Classifier-Free Diffusion Guidance

Learning Equi-angular Representations for Online Continual Learning

Unified Entropy Optimization for Open-Set Test-Time Adaptation

Poly Kernel Inception Network for Remote Sensing Detection

Distraction is All You Need: Memory-Efficient Image Immunization against Diffusion-Based Image Editing

One-dimensional Adapter to Rule Them All: Concepts Diffusion Models and Erasing Applications

Turb-Seg-Res: A Segment-then-Restore Pipeline for Dynamic Videos with Atmospheric Turbulence

Learned Lossless Image Compression based on Bit Plane Slicing

BEM: Balanced and Entropy-based Mix for Long-Tailed Semi-Supervised Learning

HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces

Single-Model and Any-Modality for Video Object Tracking

IIRP-Net: Iterative Inference Residual Pyramid Network for Enhanced Image Registration

SEED-Bench: Benchmarking Multimodal Large Language Models

Dancing with Still Images: Video Distillation via Static-Dynamic Disentanglement

SC-Tune: Unleashing Self-Consistent Referential Comprehension in Large Vision Language Models

Frequency-Adaptive Dilated Convolution for Semantic Segmentation

LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels

Parameter Efficient Fine-tuning via Cross Block Orchestration for Segment Anything Model

MGMap: Mask-Guided Learning for Online Vectorized HD Map Construction

ViT-Lens: Towards Omni-modal Representations

Leak and Learn: An Attacker's Cookbook to Train Using Leaked Data from Federated Learning

Style Aligned Image Generation via Shared Attention

Rewrite the Stars

NeRFDeformer: NeRF Transformation from a Single View via 3D Scene Flows

Steganographic Passport: An Owner and User Verifiable Credential for Deep Model IP Protection Without Retraining

VideoSwap: Customized Video Subject Swapping with Interactive Semantic Point Correspondence

TexTile: A Differentiable Metric for Texture Tileability

MatSynth: A Modern PBR Materials Dataset

Image Processing GNN: Breaking Rigidity in Super-Resolution

MonoDiff: Monocular 3D Object Detection and Pose Estimation with Diffusion Models

Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm Regularization

RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding

BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models

ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation

Blur-aware Spatio-temporal Sparse Transformer for Video Deblurring

Bi-Causal: Group Activity Recognition via Bidirectional Causality

X-MIC: Cross-Modal Instance Conditioning for Egocentric Action Generalization

Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creation

Active Domain Adaptation with False Negative Prediction for Object Detection

Prompt-Driven Referring Image Segmentation with Instance Contrasting

CosmicMan: A Text-to-Image Foundation Model for Humans

MTMMC: A Large-Scale Real-World Multi-Modal Camera Tracking Benchmark

LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content

How to Train Neural Field Representations: A Comprehensive Study and Benchmark

Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation

PairAug: What Can Augmented Image-Text Pairs Do for Radiology?

Language-conditioned Detection Transformer

Riemannian Multinomial Logistics Regression for SPD Neural Networks

Distilled Datamodel with Reverse Gradient Matching

LED: A Large-scale Real-world Paired Dataset for Event Camera Denoising

NoiseCollage: A Layout-Aware Text-to-Image Diffusion Model Based on Noise Cropping and Merging

OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM

Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models

Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer

Digital Life Project: Autonomous 3D Characters with Social Intelligence

Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias

Semantic-Aware Multi-Label Adversarial Attacks

MonoHair: High-Fidelity Hair Modeling from a Monocular Video

Learned Scanpaths Aid Blind Panoramic Video Quality Assessment

S²MVTC: a Simple yet Efficient Scalable Multi-View Tensor Clustering

Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding

Continual Self-supervised Learning: Towards Universal Multi-modal Medical Data Representation Learning

Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring

SCoFT: Self-Contrastive Fine-Tuning for Equitable Image Generation

Smart Help: Strategic Opponent Modeling for Proactive and Adaptive Robot Assistance in Households

The Unreasonable Effectiveness of Pre-Trained Features for Camera Pose Refinement

CMA: A Chromaticity Map Adapter for Robust Detection of Screen-Recapture Document Images

Virtual Immunohistochemistry Staining for Histological Images Assisted by Weakly-supervised Learning

Efficiently Assemble Normalization Layers and Regularization for Federated Domain Generalization

Unsupervised Gaze Representation Learning from Multi-view Face Images

PEEKABOO: Interactive Video Generation via Masked-Diffusion

Adapting Short-Term Transformers for Action Detection in Untrimmed Videos

Align and Aggregate: Compositional Reasoning with Video Alignment and Answer Aggregation for Video Question-Answering

Summarize the Past to Predict the Future: Natural Language Descriptions of Context Boost Multimodal Object Interaction Anticipation

MAS: Multi-view Ancestral Sampling for 3D Motion Generation Using 2D Diffusion

PointInfinity: Resolution-Invariant Point Diffusion Models

CoralSCOP: Segment any COral Image on this Planet

Reg-PTQ: Regression-specialized Post-training Quantization for Fully Quantized Object Detector

GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding

Towards HDR and HFR Video from Rolling-Mixed-Bit Spikings

Learn from View Correlation: An Anchor Enhancement Strategy for Multi-view Clustering

SplaTAM: Splat Track & Map 3D Gaussians for Dense RGB-D SLAM

Passive Snapshot Coded Aperture Dual-Pixel RGB-D Imaging

OpticalDR: A Deep Optical Imaging Model for Privacy-Protective Depression Recognition

F3Loc: Fusion and Filtering for Floorplan Localization

FREE: Faster and Better Data-Free Meta-Learning

ADA-Track: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Association

Open Vocabulary Semantic Scene Sketch Understanding

Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors

UniPAD: A Universal Pre-training Paradigm for Autonomous Driving

ECLIPSE: A Resource-Efficient Text-to-Image Prior for Image Generations

Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning

Distilling ODE Solvers of Diffusion Models into Smaller Steps

Improving Bird's Eye View Semantic Segmentation by Task Decomposition

You Only Need Less Attention at Each Stage in Vision Transformers

3DiffTection: 3D Object Detection with Geometry-Aware Diffusion Features

Hierarchical Patch Diffusion Models for High-Resolution Video Generation

Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection

XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies

Neural Video Compression with Feature Modulation

ScoreHypo: Probabilistic Human Mesh Estimation with Hypothesis Scoring

Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks

Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perception

Loose Inertial Poser: Motion Capture with IMU-attached Loose-Wear Jacket

BoQ: A Place is Worth a Bag of Learnable Queries

Dynamic Graph Representation with Knowledge-aware Attention for Histopathology Whole Slide Image Analysis

Learning from One Continuous Video Stream

Overload: Latency Attacks on Object Detection for Edge Devices

MonoNPHM: Dynamic Head Reconstruction from Monocular Videos

Neural Exposure Fusion for High-Dynamic Range Object Detection

GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understanding

Dual DETRs for Multi-Label Temporal Action Detection

Observation-Guided Diffusion Probabilistic Models

Discriminative Probing and Tuning for Text-to-Image Generation

CDFormer: When Degradation Prediction Embraces Diffusion Model for Blind Image Super-Resolution

UFC-Net: Unrolling Fixed-point Continuous Network for Deep Compressive Sensing

Symphonize 3D Semantic Scene Completion with Contextual Instance Queries

TEA: Test-time Energy Adaptation

Model Adaptation for Time Constrained Embodied Control

GigaTraj: Predicting Long-term Trajectories of Hundreds of Pedestrians in Gigapixel Complex Scenes

Outdoor Scene Extrapolation with Hierarchical Generative Cellular Automata

End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames

Comparing the Decision-Making Mechanisms by Transformers and CNNs via Explanation Methods

KD-DETR: Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling

CPLIP: Zero-Shot Learning for Histopathology with Comprehensive Vision-Language Alignment

AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning

Adaptive VIO: Deep Visual-Inertial Odometry with Online Continual Learning

Quantifying Task Priority for Multi-Task Optimization

Tri-Modal Motion Retrieval by Learning a Joint Embedding Space

HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splatting

Continual Segmentation with Disentangled Objectness Learning and Class Recognition

Image Sculpting: Precise Object Editing with 3D Geometry Control

UniGarmentManip: A Unified Framework for Category-Level Garment Manipulation via Dense Visual Correspondence

Supervised Anomaly Detection for Complex Industrial Images

Audio-Visual Segmentation via Unlabeled Frame Exploitation

Interactive Continual Learning: Fast and Slow Thinking

Doubly Abductive Counterfactual Inference for Text-based Image Editing

Attribute-Guided Pedestrian Retrieval: Bridging Person Re-ID with Internal Attribute Variability

Weakly Misalignment-free Adaptive Feature Alignment for UAVs-based Multimodal Object Detection

Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion

Prompt-Driven Dynamic Object-Centric Learning for Single Domain Generalization

Distilling Semantic Priors from SAM to Efficient Image Restoration Models

UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory

In-Context Matting

MaskPLAN: Masked Generative Layout Planning from Partial Input

EscherNet: A Generative Model for Scalable View Synthesis

FlowTrack: Revisiting Optical Flow for Long-Range Dense Tracking

Mirasol3B: A Multimodal Autoregressive Model for Time-Aligned and Contextual Modalities

MVCPS-NeuS: Multi-view Constrained Photometric Stereo for Neural Surface Reconstruction

Solving Masked Jigsaw Puzzles with Diffusion Vision Transformers

LLaFS: When Large Language Models Meet Few-Shot Segmentation

Towards Memorization-Free Diffusion Models

Semantics Distortion and Style Matter: Towards Source-free UDA for Panoramic Segmentation

PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awareness

Evaluating Transferability in Retrieval Tasks: An Approach Using MMD and Kernel Methods

ParameterNet: Parameters Are All You Need for Large-scale Visual Pretraining of Mobile Networks

PH-Net: Semi-Supervised Breast Lesion Segmentation via Patch-wise Hardness

AV-RIR: Audio-Visual Room Impulse Response Estimation

RELI11D: A Comprehensive Multimodal Human Motion Dataset and Method

Entangled View-Epipolar Information Aggregation for Generalizable Neural Radiance Fields

OHTA: One-shot Hand Avatar via Data-driven Implicit Priors

E-GPS: Explainable Geometry Problem Solving via Top-Down Solver and Bottom-Up Generator

MultiPhys: Multi-Person Physics-aware 3D Motion Estimation

LMDrive: Closed-Loop End-to-End Driving with Large Language Models

A-Teacher: Asymmetric Network for 3D Semi-Supervised Object Detection

HanDiffuser: Text-to-Image Generation With Realistic Hand Appearances

Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks

Instance Tracking in 3D Scenes from Egocentric Videos

ID-Blau: Image Deblurring by Implicit Diffusion-based reBLurring AUgmentation

Adversarial Score Distillation: When score distillation meets GAN

Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification

CAGE: Controllable Articulation GEneration

GauHuman: Articulated Gaussian Splatting from Monocular Human Videos

BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection

AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents

HumanNeRF-SE: A Simple yet Effective Approach to Animate HumanNeRF with Diverse Poses

Cyclic Learning for Binaural Audio Generation and Localization

DMR: Decomposed Multi-Modality Representations for Frames and Events Fusion in Visual Reinforcement Learning

3D Feature Tracking via Event Camera

Frequency-aware Event-based Video Deblurring for Real-World Motion Blur

Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)

Communication-Efficient Collaborative Perception via Information Filling with Codebook

QUADify: Extracting Meshes with Pixel-level Details and Materials from Images

FedHCA2: Towards Hetero-Client Federated Multi-Task Learning

Improving Unsupervised Hierarchical Representation with Reinforcement Learning

All Rivers Run to the Sea: Private Learning with Asymmetric Flows

Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset

Global Latent Neural Rendering

Text-IF: Leveraging Semantic Text Guidance for Degradation-Aware and Interactive Image Fusion

DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data

SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation

Semantics-aware Motion Retargeting with Vision-Language Models

SurMo: Surface-based 4D Motion Modeling for Dynamic Human Rendering

LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model

Data Poisoning based Backdoor Attacks to Contrastive Learning

DART: Implicit Doppler Tomography for Radar Novel View Synthesis

RoHM: Robust Human Motion Reconstruction via Diffusion

ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation

Video Interpolation with Diffusion Models

Unveiling Parts Beyond Objects: Towards Finer-Granularity Referring Expression Segmentation

PanoPose: Self-supervised Relative Pose Estimation for Panoramic Images

Enhancing Post-training Quantization Calibration through Contrastive Learning

LASO: Language-guided Affordance Segmentation on 3D Object

DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization

Dispersed Structured Light for Hyperspectral 3D Imaging

DualAD: Disentangling the Dynamic and Static World for End-to-End Driving

DiffHuman: Probabilistic Photorealistic 3D Reconstruction of Humans

DeMatch: Deep Decomposition of Motion Field for Two-View Correspondence Learning

SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videos

Mask4Align: Aligned Entity Prompting with Color Masks for Multi-Entity Localization Problems

Intriguing Properties of Diffusion Models: An Empirical Study of the Natural Attack Capability in Text-to-Image Generative Models

Global and Local Prompts Cooperation via Optimal Transport for Federated Learning

VSCode: General Visual Salient and Camouflaged Object Detection with 2D Prompt Learning

Classes Are Not Equal: An Empirical Study on Image Recognition Fairness

SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution

FAR: Flexible Accurate and Robust 6DoF Relative Camera Pose Estimation

Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation

Self-supervised Debiasing Using Low Rank Regularization

Dense Optical Tracking: Connecting the Dots

ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object

Neural Markov Random Field for Stereo Matching

BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition

Dynamic Inertial Poser (DynaIP): Part-Based Motion Dynamics Learning for Enhanced Human Pose Estimation with Sparse Inertial Sensors

Multi-agent Collaborative Perception via Motion-aware Robust Communication Network

Ungeneralizable Examples

Learning with Unreliability: Fast Few-shot Voxel Radiance Fields with Relative Geometric Consistency

Language-only Training of Zero-shot Composed Image Retrieval

Focus on Hiders: Exploring Hidden Threats for Enhancing Adversarial Training

ColorPCR: Color Point Cloud Registration with Multi-Stage Geometric-Color Fusion

Unifying Correspondence Pose and NeRF for Generalized Pose-Free Novel View Synthesis

Person-in-WiFi 3D: End-to-End Multi-Person 3D Pose Estimation with Wi-Fi

MemFlow: Optical Flow Estimation and Prediction with Memory

ERMVP: Communication-Efficient and Collaboration-Robust Multi-Vehicle Perception in Challenging Environments

Causal-CoG: A Causal-Effect Look at Context Generation for Boosting Multi-modal Language Models

A Unified and Interpretable Emotion Representation and Expression Generation

SPAD: Spatially Aware Multi-View Diffusers

GRAM: Global Reasoning for Multi-Page VQA

Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning

HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data

Tri-Perspective View Decomposition for Geometry-Aware Depth Completion

Rapid Motor Adaptation for Robotic Manipulator Arms

Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors

Instruct-Imagen: Image Generation with Multi-modal Instruction

Any-Shift Prompting for Generalization over Distributions

DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction

VP3D: Unleashing 2D Visual Prompt for Text-to-3D Generation

SCE-MAE: Selective Correspondence Enhancement with Masked Autoencoder for Self-Supervised Landmark Estimation

Robust Image Denoising through Adversarial Frequency Mixup

TurboSL: Dense Accurate and Fast 3D by Neural Inverse Structured Light

MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric

Diffeomorphic Template Registration for Atmospheric Turbulence Mitigation

Adapting to Length Shift: FlexiLength Network for Trajectory Prediction

Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis

Style Blind Domain Generalized Semantic Segmentation via Covariance Alignment and Semantic Consistence Contrastive Learning

Mixed-Precision Quantization for Federated Learning on Resource-Constrained Heterogeneous Devices

DiffusionRegPose: Enhancing Multi-Person Pose Estimation using a Diffusion-Based End-to-End Regression Approach

MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis

CausalPC: Improving the Robustness of Point Cloud Classification by Causal Effect Identification

Entity-NeRF: Detecting and Removing Moving Entities in Urban Scenes

Time- Memory- and Parameter-Efficient Visual Adaptation

DiffPerformer: Iterative Learning of Consistent Latent Guidance for Diffusion-based Human Video Generation

Test-Time Domain Generalization for Face Anti-Spoofing

Behind the Veil: Enhanced Indoor 3D Scene Reconstruction with Occluded Surfaces Completion

LiSA: LiDAR Localization with Semantic Awareness

Rethinking Prior Information Generation with CLIP for Few-Shot Segmentation

In2SET: Intra-Inter Similarity Exploiting Transformer for Dual-Camera Compressive Hyperspectral Imaging

Adaptive Slot Attention: Object Discovery with Dynamic Slot Number

Unknown Prompt the only Lacuna: Unveiling CLIP's Potential for Open Domain Generalization

Tumor Micro-environment Interactions Guided Graph Learning for Survival Analysis of Human Cancers from Whole-slide Pathological Images

Perception-Oriented Video Frame Interpolation via Asymmetric Blending

Cooperation Does Matter: Exploring Multi-Order Bilateral Relations for Audio-Visual Segmentation

Exact Fusion via Feature Distribution Matching for Few-shot Image Generation

Fooling Polarization-Based Vision using Locally Controllable Polarizing Projection

Affine Equivariant Networks Based on Differential Invariants

Diffusion-based Blind Text Image Super-Resolution

Learning Coupled Dictionaries from Unpaired Data for Image Super-Resolution

C3: High-Performance and Low-Complexity Neural Compression from a Single Image or Video

AttriHuman-3D: Editable 3D Human Avatar Generation with Attribute Decomposition and Indexing

iToF-flow-based High Frame Rate Depth Imaging

ZeroRF: Fast Sparse View 360° Reconstruction with Zero Pretraining

Revisiting Counterfactual Problems in Referring Expression Comprehension

Monocular Identity-Conditioned Facial Reflectance Reconstruction

Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names

Continual Learning for Motion Prediction Model via Meta-Representation Learning and Optimal Memory Buffer Retention Strategy

FlowDiffuser: Advancing Optical Flow Estimation with Diffusion Models

3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting

Rethinking Human Motion Prediction with Symplectic Integral

Detector-Free Structure from Motion

Holodeck: Language Guided Generation of 3D Embodied AI Environments

Unleashing Network Potentials for Semantic Scene Completion

Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic Propagation

AdaRevD: Adaptive Patch Exiting Reversible Decoder Pushes the Limit of Image Deblurring

Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attention

DiVAS: Video and Audio Synchronization with Dynamic Frame Rates

Fully Geometric Panoramic Localization

BiTT: Bi-directional Texture Reconstruction of Interacting Two Hands from a Single Image

Towards Robust 3D Pose Transfer with Adversarial Learning

Puff-Net: Efficient Style Transfer with Pure Content and Style Feature Fusion Network

SynSP: Synergy of Smoothness and Precision in Pose Sequences Refinement

Building Vision-Language Models on Solid Foundations with Masked Distillation

DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassembly

MS-DETR: Efficient DETR Training with Mixed Supervision

Material Palette: Extraction of Materials from a Single Image

Benchmarking Audio Visual Segmentation for Long-Untrimmed Videos

Inter-X: Towards Versatile Human-Human Interaction Analysis

Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld

One-Shot Open Affordance Learning with Foundation Models

Self-Supervised Dual Contouring

Differentiable Point-based Inverse Rendering

VMINer: Versatile Multi-view Inverse Rendering with Near- and Far-field Light Sources

Towards Accurate and Robust Architectures via Neural Architecture Search

FairDeDup: Detecting and Mitigating Vision-Language Fairness Disparities in Semantic Dataset Deduplication

On the Test-Time Zero-Shot Generalization of Vision-Language Models: Do We Really Need Prompt Learning?

FedMef: Towards Memory-efficient Federated Dynamic Pruning

FaceChain-SuDe: Building Derived Class to Inherit Category Attributes for One-shot Subject-Driven Generation

SpikingResformer: Bridging ResNet and Vision Transformer in Spiking Neural Networks

C^2RV: Cross-Regional and Cross-View Learning for Sparse-View CBCT Reconstruction

Tactile-Augmented Radiance Fields

SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction

Towards High-fidelity Artistic Image Vectorization via Texture-Encapsulated Shape Parameterization

OmniSDF: Scene Reconstruction using Omnidirectional Signed Distance Functions and Adaptive Binoctrees

Extreme Point Supervised Instance Segmentation

Mean-Shift Feature Transformer

Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model

Consistent Prompting for Rehearsal-Free Continual Learning

Degrees of Freedom Matter: Inferring Dynamics from Point Trajectories

MedBN: Robust Test-Time Adaptation against Malicious Test Samples

Open-Vocabulary Video Anomaly Detection

Beyond First-Order Tweedie: Solving Inverse Problems using Latent Diffusion

ActiveDC: Distribution Calibration for Active Finetuning

AUEditNet: Dual-Branch Facial Action Unit Intensity Manipulation with Implicit Disentanglement

KVQ: Kwai Video Quality Assessment for Short-form Videos

Language Model Guided Interpretable Video Action Reasoning

Purified and Unified Steganographic Network

Deformable One-shot Face Stylization via DINO Semantic Guidance

Density-Guided Semi-Supervised 3D Semantic Segmentation with Dual-Space Hardness Sampling

CoSeR: Bridging Image and Language for Cognitive Super-Resolution

Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework

PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation

NeRF Analogies: Example-Based Visual Attribute Transfer for NeRFs

InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning

SmartRefine: A Scenario-Adaptive Refinement Framework for Efficient Motion Prediction

Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer

Bayes' Rays: Uncertainty Quantification for Neural Radiance Fields

Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model

Skeleton-in-Context: Unified Skeleton Sequence Modeling with In-Context Learning

Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training

Fast Adaptation for Human Pose Estimation via Meta-Optimization

Previously on ... From Recaps to Story Summarization

VecFusion: Vector Font Generation with Diffusion

Generating Non-Stationary Textures using Self-Rectification

OOSTraj: Out-of-Sight Trajectory Prediction With Vision-Positioning Denoising

SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detection

LP++: A Surprisingly Strong Linear Probe for Few-Shot CLIP

Frozen Feature Augmentation for Few-Shot Image Classification

1-Lipschitz Layers Compared: Memory Speed and Certifiable Robustness

VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models

Building Optimal Neural Architectures using Interpretable Knowledge

Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detection

L4D-Track: Language-to-4D Modeling Towards 6-DoF Tracking and Shape Reconstruction in 3D Point Cloud Stream

MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labeling

BerfScene: Bev-conditioned Equivariant Radiance Fields for Infinite 3D Scene Generation

GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfaces

Bridging Remote Sensors with Multisensor Geospatial Foundation Models

Scaling Laws for Data Filtering— Data Curation cannot be Compute Agnostic

IBD-SLAM: Learning Image-Based Depth Fusion for Generalizable SLAM

Multimodal Industrial Anomaly Detection by Crossmodal Feature Mapping

Bilateral Event Mining and Complementary for Event Stream Super-Resolution

PoNQ: a Neural QEM-based Mesh Representation

M3-UDA: A New Benchmark for Unsupervised Domain Adaptive Fetal Cardiac Structure Detection

Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians

CyberDemo: Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation

Improving Plasticity in Online Continual Learning via Collaborative Learning

Video Harmonization with Triplet Spatio-Temporal Variation Patterns

Semantic Line Combination Detector

Segment Any Event Streams via Weighted Adaptation of Pivotal Tokens

Learning Transferable Negative Prompts for Out-of-Distribution Detection

3D Multi-frame Fusion for Video Stabilization

Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning

Fun with Flags: Robust Principal Directions via Flag Manifolds

Beyond Image Super-Resolution for Image Recognition with Task-Driven Perceptual Loss

Boosting Image Quality Assessment through Efficient Transformer Adaptation with Local Feature Enhancement

Learning without Exact Guidance: Updating Large-scale High-resolution Land Cover Maps from Low-resolution Historical Labels

Multi-Modal Hallucination Control by Visual Information Grounding

Towards Realistic Scene Generation with LiDAR Diffusion Models

Point-VOS: Pointing Up Video Object Segmentation

Laplacian-guided Entropy Model in Neural Codec with Blur-dissipated Synthesis

Instruct 4D-to-4D: Editing 4D Scenes as Pseudo-3D Scenes Using 2D Diffusion

VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation

Exploring Orthogonality in Open World Object Detection

Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detection

Compositional Chain-of-Thought Prompting for Large Multimodal Models

As-Plausible-As-Possible: Plausibility-Aware Mesh Deformation Using 2D Diffusion Priors

Unifying Automatic and Interactive Matting with Pretrained ViTs

3D Face Tracking from 2D Video through Iterative Dense UV to Image Flow

HIT: Estimating Internal Human Implicit Tissues from the Body Surface

HMD-Poser: On-Device Real-time Human Motion Tracking from Scalable Sparse Observations

DynVideo-E: Harnessing Dynamic NeRF for Large-Scale Motion- and View-Change Human-Centric Video Editing

SD-DiT: Unleashing the Power of Self-supervised Discrimination in Diffusion Transformer

Traffic Scene Parsing through the TSP6K Dataset

Investigating and Mitigating the Side Effects of Noisy Views for Self-Supervised Clustering Algorithms in Practical Multi-View Scenarios

Rethinking Interactive Image Segmentation with Low Latency High Quality and Diverse Prompts

Garment Recovery with Shape and Deformation Priors

Boosting Spike Camera Image Reconstruction from a Perspective of Dealing with Spike Fluctuations

DreamComposer: Controllable 3D Object Generation via Multi-View Conditions

NViST: In the Wild New View Synthesis from a Single Image with Transformers

Authentic Hand Avatar from a Phone Scan via Universal Hand Model

Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture

KPConvX: Modernizing Kernel Point Convolution with Kernel Attention

Multiscale Vision Transformers Meet Bipartite Matching for Efficient Single-stage Action Localization

Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation

Latency Correction for Event-guided Deblurring and Frame Interpolation

DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models

MoReVQA: Exploring Modular Reasoning Models for Video Question Answering

SeMoLi: What Moves Together Belongs Together

An N-Point Linear Solver for Line and Motion Estimation with Event Cameras

Task-Driven Exploration: Decoupling and Inter-Task Feedback for Joint Moment Retrieval and Highlight Detection

Multiway Point Cloud Mosaicking with Diffusion and Global Optimization

A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames

NeRSP: Neural 3D Reconstruction for Reflective Objects with Sparse Polarized Images

HDRFlow: Real-Time HDR Video Reconstruction with Large Motions

DIMAT: Decentralized Iterative Merging-And-Training for Deep Learning Models

NTO3D: Neural Target Object 3D Reconstruction with Segment Anything

Instance-Aware Group Quantization for Vision Transformers

Text-Driven Image Editing via Learnable Regions

ZERO-IG: Zero-Shot Illumination-Guided Joint Denoising and Adaptive Enhancement for Low-Light Images

HINTED: Hard Instance Enhanced Detector with Mixed-Density Feature Fusion for Sparsely-Supervised 3D Object Detection

NAYER: Noisy Layer Data Generation for Efficient and Effective Data-free Knowledge Distillation

Domain-Specific Block Selection and Paired-View Pseudo-Labeling for Online Test-Time Adaptation

Improving Visual Recognition with Hyperbolical Visual Hierarchy Mapping

Collaborating Foundation Models for Domain Generalized Semantic Segmentation

CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognition

pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction

Make-Your-Anchor: A Diffusion-based 2D Avatar Generation Framework

Representing Part-Whole Hierarchies in Foundation Models by Learning Localizability Composability and Decomposability from Anatomy via Self Supervision

Self-Supervised Representation Learning from Arbitrary Scenarios

Rethinking Few-shot 3D Point Cloud Semantic Segmentation

Beyond Average: Individualized Visual Scanpath Prediction

Frozen CLIP: A Strong Backbone for Weakly Supervised Semantic Segmentation

Robust Distillation via Untargeted and Targeted Intermediate Adversarial Samples

Rethinking Multi-domain Generalization with A General Learning Objective

NEAT: Distilling 3D Wireframes from Neural Attraction Fields

Beyond Text: Frozen Large Language Models in Visual Signal Comprehension

LEDITS++: Limitless Image Editing using Text-to-Image Models

Doodle Your 3D: From Abstract Freehand Sketches to Precise 3D Shapes

Emu Edit: Precise Image Editing via Recognition and Generation Tasks

OVER-NAV: Elevating Iterative Vision-and-Language Navigation with Open-Vocabulary Detection and StructurEd Representation

Revamping Federated Learning Security from a Defender's Perspective: A Unified Defense with Homomorphic Encrypted Data Space

LLMs are Good Sign Language Translators

PeerAiD: Improving Adversarial Distillation from a Specialized Peer Tutor

Adversarial Distillation Based on Slack Matching and Attribution Region Alignment

HIPTrack: Visual Tracking with Historical Prompts

FSRT: Facial Scene Representation Transformer for Face Reenactment from Factorized Appearance Head-pose and Facial Expression Features

CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization Perspective

Learning Disentangled Identifiers for Action-Customized Text-to-Image Generation

Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models

DETRs Beat YOLOs on Real-time Object Detection

AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation

Universal Robustness via Median Randomized Smoothing for Real-World Super-Resolution

Regularized Parameter Uncertainty for Improving Generalization in Reinforcement Learning

Robust Noisy Correspondence Learning with Equivariant Similarity Consistency

PanoRecon: Real-Time Panoptic 3D Reconstruction from Monocular Video

TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding

RCBEVDet: Radar-camera Fusion in Bird's Eye View for 3D Object Detection

Differentiable Information Bottleneck for Deterministic Multi-view Clustering

Learning by Correction: Efficient Tuning Task for Zero-Shot Generative Vision-Language Reasoning

Situational Awareness Matters in 3D Vision Language Reasoning

Generative Proxemics: A Prior for 3D Social Interaction from Images

FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment

Decentralized Directed Collaboration for Personalized Federated Learning

The Neglected Tails in Vision-Language Models

Learning to Rank Patches for Unbiased Image Redundancy Reduction

Multi-View Attentive Contextualization for Multi-View 3D Object Detection

Task-Driven Wavelets using Constrained Empirical Risk Minimization

SeNM-VAE: Semi-Supervised Noise Modeling with Hierarchical Variational Autoencoder

SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction

OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning

SODA: Bottleneck Diffusion Models for Representation Learning

Text-to-3D using Gaussian Splatting

AHIVE: Anatomy-aware Hierarchical Vision Encoding for Interactive Radiology Report Retrieval

Diffusion Reflectance Map: Single-Image Stochastic Inverse Rendering of Illumination and Reflectance

Probing Synergistic High-Order Interaction in Infrared and Visible Image Fusion

InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion

Scaling Up Dynamic Human-Scene Interaction Modeling

Calibrating Multi-modal Representations: A Pursuit of Group Robustness without Annotations

Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particle

Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with LLMs

SPU-PMD: Self-Supervised Point Cloud Upsampling via Progressive Mesh Deformation

Enhancing the Power of OOD Detection via Sample-Aware Model Selection

SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes

Self-Supervised Class-Agnostic Motion Prediction with Spatial and Temporal Consistency Regularizations

Theoretically Achieving Continuous Representation of Oriented Bounding Boxes

Source-Free Domain Adaptation with Frozen Multimodal Foundation Model

Utility-Fairness Trade-Offs and How to Find Them

Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement

Adversarially Robust Few-shot Learning via Parameter Co-distillation of Similarity and Class Concept Learners

MMA-Diffusion: MultiModal Attack on Diffusion Models

MMA: Multi-Modal Adapter for Vision-Language Models

Linguistic-Aware Patch Slimming Framework for Fine-grained Cross-Modal Alignment

Grounding and Enhancing Grid-based Models for Neural Fields

Blind Image Quality Assessment Based on Geometric Order Learning

Data-Free Quantization via Pseudo-label Filtering

Unsupervised Deep Unrolling Networks for Phase Unwrapping

Neural Sign Actors: A Diffusion Model for 3D Sign Language Production from Text

Fitting Flats to Flats

Seeing Motion at Nighttime with an Event Camera

Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering

CCEdit: Creative and Controllable Video Editing via Diffusion Models

Can Biases in ImageNet Models Explain Generalization?

HOIST-Former: Hand-held Objects Identification Segmentation and Tracking in the Wild

UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenes

A Category Agnostic Model for Visual Rearrangment

Boosting Flow-based Generative Super-Resolution Models via Learned Prior

REACTO: Reconstructing Articulated Objects from a Single Video

Towards More Unified In-context Visual Understanding

Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentation

ConsistDreamer: 3D-Consistent 2D Diffusion for High-Fidelity Scene Editing

Towards Robust Learning to Optimize with Theoretical Guarantees

Animating General Image with Large Visual Motion Model

Efficient Test-Time Adaptation of Vision-Language Models

MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning

Towards Progressive Multi-Frequency Representation for Image Warping

Fourier-basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image Classification

Would Deep Generative Models Amplify Bias in Future Models?

HumMUSS: Human Motion Understanding using State Space Models

Modeling Multimodal Social Interactions: New Challenges and Baselines with Densely Aligned Representations

SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World

FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition

Cloud-Device Collaborative Learning for Multimodal Large Language Models

Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learning

De-confounded Data-free Knowledge Distillation for Handling Distribution Shifts

VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction

Retrieval-Augmented Embodied Agents

EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams

LAKE-RED: Camouflaged Images Generation by Latent Background Knowledge Retrieval-Augmented Diffusion

What Do You See in Vehicle? Comprehensive Vision Solution for In-Vehicle Gaze Estimation

Adapters Strike Back

Molecular Data Programming: Towards Molecule Pseudo-labeling with Systematic Weak Supervision

OTE: Exploring Accurate Scene Text Recognition Using One Token

How to Make Cross Encoder a Good Teacher for Efficient Image-Text Retrieval?

Revisiting Adversarial Training at Scale

ModaVerse: Efficiently Transforming Modalities with LLMs

Revisiting Sampson Approximations for Geometric Estimation Problems

TTA-EVF: Test-Time Adaptation for Event-based Video Frame Interpolation via Reliable Pixel and Sample Estimation

HUGS: Human Gaussian Splats

GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis

Improving Generalization via Meta-Learning on Hard Samples

WaveFace: Authentic Face Restoration with Efficient Frequency Recovery

MAPLM: A Real-World Large-Scale Vision-Language Benchmark for Map and Traffic Scene Understanding

Hierarchical Histogram Threshold Segmentation – Auto-terminating High-detail Oversegmentation

Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models

Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions

G-FARS: Gradient-Field-based Auto-Regressive Sampling for 3D Part Grouping

Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformers

LiDAR-based Person Re-identification

CogAgent: A Visual Language Model for GUI Agents

Do Vision and Language Encoders Represent the World Similarly?

MVBench: A Comprehensive Multi-modal Video Understanding Benchmark

DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing

Mocap Everyone Everywhere: Lightweight Motion Capture With Smartwatches and a Head-Mounted Camera

Residual Denoising Diffusion Models

Towards Robust Event-guided Low-Light Image Enhancement: A Large-Scale Real-World Event-Image Dataset and Novel Approach

Learning Adaptive Spatial Coherent Correlations for Speech-Preserving Facial Expression Manipulation

UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and Unfavorable Sets

Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data

Universal Novelty Detection Through Adaptive Contrastive Learning

DVMNet: Computing Relative Pose for Unseen Objects Beyond Hypotheses

Make Pixels Dance: High-Dynamic Video Generation

Masked AutoDecoder is Effective Multi-Task Vision Generalist

EventDance: Unsupervised Source-free Cross-modal Adaptation for Event-based Object Recognition

Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization

A Semi-supervised Nighttime Dehazing Baseline with Spatial-Frequency Aware and Realistic Brightness Constraint

AVID: Any-Length Video Inpainting with Diffusion Model

Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network

A Call to Reflect on Evaluation Practices for Age Estimation: Comparative Analysis of the State-of-the-Art and a Unified Benchmark

Hyper-MD: Mesh Denoising with Customized Parameters Aware of Noise Intensity and Geometric Characteristics

Discontinuity-preserving Normal Integration with Auxiliary Edges

Dual-Enhanced Coreset Selection with Class-wise Collaboration for Online Blurry Class Incremental Learning

Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers

Complementing Event Streams and RGB Frames for Hand Mesh Reconstruction

Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion

Generative Multi-modal Models are Good Class Incremental Learners

Deciphering ‘What’ and ‘Where’ Visual Pathways from Spectral Clustering of Layer-Distributed Neural Representations

Visual In-Context Prompting

TULIP: Multi-camera 3D Precision Assessment of Parkinson’s Disease

Distribution-aware Knowledge Prototyping for Non-exemplar Lifelong Person Re-identification

WaveMo: Learning Wavefront Modulations to See Through Scattering

HiLo: Detailed and Robust 3D Clothed Human Reconstruction with High-and Low-Frequency Information of Parametric Models

KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation

Optimal Transport Aggregation for Visual Place Recognition

BANF: Band-Limited Neural Fields for Levels of Detail Reconstruction

HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting

Human Motion Prediction Under Unexpected Perturbation

LLMs are Good Action Recognizers

Weakly Supervised Point Cloud Semantic Segmentation via Artificial Oracle

MFP: Making Full Use of Probability Maps for Interactive Image Segmentation

DiG-IN: Diffusion Guidance for Investigating Networks - Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations

Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Mining

Finsler-Laplace-Beltrami Operators with Application to Shape Analysis

StraightPCF: Straight Point Cloud Filtering

SynFog: A Photo-realistic Synthetic Fog Dataset based on End-to-end Imaging Simulation for Advancing Real-World Defogging in Autonomous Driving

NeRFiller: Completing Scenes via Generative 3D Inpainting

Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning

An Empirical Study of Scaling Law for Scene Text Recognition

Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching

PeVL: Pose-Enhanced Vision-Language Model for Fine-Grained Human Action Recognition

Customize your NeRF: Adaptive Source Driven 3D Scene Editing via Local-Global Iterative Training

MPOD123: One Image to 3D Content Generation Using Mask-enhanced Progressive Outline-to-Detail Optimization

Slice3D: Multi-Slice Occlusion-Revealing Single View 3D Reconstruction

Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detection

LLaMA-Excitor: General Instruction Tuning via Indirect Feature Interaction

EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Models

Learning to Produce Semi-dense Correspondences for Visual Localization

When StyleGAN Meets Stable Diffusion: a W+ Adapter for Personalized Image Generation

ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and More

Differentiable Neural Surface Refinement for Modeling Transparent Objects

UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model

Look-Up Table Compression for Efficient Image Restoration

Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation

RepAn: Enhanced Annealing through Re-parameterization

PAPR in Motion: Seamless Point-level 3D Scene Interpolation

Learning to Navigate Efficiently and Precisely in Real Environments

Low-power Continuous Remote Behavioral Localization with Event Cameras

4D-DRESS: A 4D Dataset of Real-World Human Clothing With Semantic Annotations

Attention-Propagation Network for Egocentric Heatmap to 3D Pose Lifting

Towards Modern Image Manipulation Localization: A Large-Scale Dataset and Novel Methods

Dense Vision Transformer Compression with Few Samples

Revisiting the Domain Shift and Sample Uncertainty in Multi-source Active Domain Transfer

Weak-to-Strong 3D Object Detection with X-Ray Distillation

Weakly Supervised Monocular 3D Detection with a Single-View Image

Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks Methods and Applications

AM-RADIO: Agglomerative Vision Foundation Model Reduce All Domains Into One

Towards Co-Evaluation of Cameras HDR and Algorithms for Industrial-Grade 6DoF Pose Estimation

Tune-An-Ellipse: CLIP Has Potential to Find What You Want

YolOOD: Utilizing Object Detection Concepts for Multi-Label Out-of-Distribution Detection

LISA: Reasoning Segmentation via Large Language Model

Fantastic Animals and Where to Find Them: Segment Any Marine Animal with Dual SAM

IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracing

Exploring Pose-Aware Human-Object Interaction via Hybrid Learning

Correcting Diffusion Generation through Resampling

Multi-modal Learning for Geospatial Vegetation Forecasting

An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated Learning

Partial-to-Partial Shape Matching with Geometric Consistency

Deep Imbalanced Regression via Hierarchical Classification Adjustment

All in One Framework for Multimodal Re-identification in the Wild

Leveraging Cross-Modal Neighbor Representation for Improved CLIP Classification

Bilateral Adaptation for Human-Object Interaction Detection with Occlusion-Robustness

BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model

Text-guided Explorable Image Super-resolution

From Feature to Gaze: A Generalizable Replacement of Linear Layer for Gaze Estimation

DiffMorpher: Unleashing the Capability of Diffusion Models for Image Morphing

NC-SDF: Enhancing Indoor Scene Reconstruction Using Neural SDFs with View-Dependent Normal Compensation

PIN: Positional Insert Unlocks Object Localisation Abilities in VLMs

Correspondence-Free Non-Rigid Point Set Registration Using Unsupervised Clustering Analysis

MVIP-NeRF: Multi-view 3D Inpainting on NeRF Scenes via Diffusion Prior

Composed Video Retrieval via Enriched Context and Discriminative Embeddings

TCP:Textual-based Class-aware Prompt tuning for Visual-Language Model

RMT: Retentive Networks Meet Vision Transformers

FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning

Low-Rank Approximation for Sparse Attention in Multi-Modal LLMs

LAENeRF: Local Appearance Editing for Neural Radiance Fields

Learning Dynamic Tetrahedra for High-Quality Talking Head Synthesis

Don't Look into the Dark: Latent Codes for Pluralistic Image Inpainting

Learning Multi-Dimensional Human Preference for Text-to-Image Generation

Neural Point Cloud Diffusion for Disentangled 3D Shape and Appearance Generation

Construct to Associate: Cooperative Context Learning for Domain Adaptive Point Cloud Segmentation

EarthLoc: Astronaut Photography Localization by Indexing Earth from Space

BioCLIP: A Vision Foundation Model for the Tree of Life

PairDETR : Joint Detection and Association of Human Bodies and Faces

Self-Supervised Facial Representation Learning with Facial Region Awareness

Language Models as Black-Box Optimizers for Vision-Language Models

Improved Visual Grounding through Self-Consistent Explanations

Relation Rectification in Diffusion Model

Versatile Medical Image Segmentation Learned from Multi-Source Datasets via Model Self-Disambiguation

Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft

Close Imitation of Expert Retouching for Black-and-White Photography

GES : Generalized Exponential Splatting for Efficient Radiance Field Rendering

OmniLocalRF: Omnidirectional Local Radiance Fields from Dynamic Videos

Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model

Steerers: A Framework for Rotation Equivariant Keypoint Descriptors

Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shifts

Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation

AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Search

On the Faithfulness of Vision Transformer Explanations

Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restoration

Transferable Structural Sparse Adversarial Attack Via Exact Group Sparsity Training

Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation

FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization

Synthesize Step-by-Step: Tools Templates and LLMs as Data Generators for Reasoning-Based Chart VQA

Generating Content for HDR Deghosting from Frequency View

Holistic Autonomous Driving Understanding by Bird’s-Eye-View Injected Multi-Modal Large Models

Querying as Prompt: Parameter-Efficient Learning for Multimodal Language Model

Reconstructing Hands in 3D with Transformers

XFeat: Accelerated Features for Lightweight Image Matching

Systematic Comparison of Semi-supervised and Self-supervised Learning for Medical Image Classification

GoodSAM: Bridging Domain and Capacity Gaps via Segment Anything Model for Distortion-aware Panoramic Semantic Segmentation

Accelerating Diffusion Sampling with Optimized Time Steps

VRP-SAM: SAM with Visual Reference Prompt

Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression

VideoBooth: Diffusion-based Video Generation with Image Prompts

CHAIN: Enhancing Generalization in Data-Efficient GANs via lipsCHitz continuity constrAIned Normalization

OneFormer3D: One Transformer for Unified Point Cloud Segmentation

Hierarchical Correlation Clustering and Tree Preserving Embedding

Day-Night Cross-domain Vehicle Re-identification

DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis

IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection

SaCo Loss: Sample-wise Affinity Consistency for Vision-Language Pre-training

One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion

C2KD: Bridging the Modality Gap for Cross-Modal Knowledge Distillation

StrokeFaceNeRF: Stroke-based Facial Appearance Editing in Neural Radiance Field

One-Shot Structure-Aware Stylized Image Synthesis

ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Rendering

Distilling Vision-Language Models on Millions of Videos

DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision

StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On

Structure-Guided Adversarial Training of Diffusion Models

Looking Similar Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning

MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training

SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models

Grounded Text-to-Image Synthesis with Attention Refocusing

TetraSphere: A Neural Descriptor for O(3)-Invariant Point Cloud Analysis

Neural Modes: Self-supervised Learning of Nonlinear Modal Subspaces

WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion

TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding

InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks

SHAP-EDITOR: Instruction-Guided Latent 3D Editing in Seconds

3D Neural Edge Reconstruction

YOLO-World: Real-Time Open-Vocabulary Object Detection

Jointly Training and Pruning CNNs via Learnable Agent Guidance and Alignment

Direct2.5: Diverse Text-to-3D Generation via Multi-view 2.5D Diffusion

Unexplored Faces of Robustness and Out-of-Distribution: Covariate Shifts in Environment and Sensor Domains

Bézier Everywhere All at Once: Learning Drivable Lanes as Bézier Graphs

CLOAF: CoLlisiOn-Aware Human Flow

FedUV: Uniformity and Variance for Heterogeneous Federated Learning

Efficient 3D Implicit Head Avatar with Mesh-anchored Hash Table Blendshapes

Explaining the Implicit Neural Canvas: Connecting Pixels to Neurons by Tracing their Contributions

Unleashing the Potential of SAM for Medical Adaptation via Hierarchical Decoding

FaceCom: Towards High-fidelity 3D Facial Shape Completion via Optimization and Inpainting Guidance

Learning Correlation Structures for Vision Transformers

Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes

Taming Self-Training for Open-Vocabulary Object Detection

Equivariant Plug-and-Play Image Reconstruction

DiffusionAvatars: Deferred Diffusion for High-fidelity 3D Head Avatars

Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation

Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection

Adversarial Backdoor Attack by Naturalistic Data Poisoning on Trajectory Prediction in Autonomous Driving

Visual Objectification in Films: Towards a New AI Task for Video Interpretation

Learning Occupancy for Monocular 3D Object Detection

LightIt: Illumination Modeling and Control for Diffusion Models

Ink Dot-Oriented Differentiable Optimization for Neural Image Halftoning

GeoChat: Grounded Large Vision-Language Model for Remote Sensing

Bring Event into RGB and LiDAR: Hierarchical Visual-Motion Fusion for Scene Flow

Language-driven Grasp Detection

Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation

Each Test Image Deserves A Specific Prompt: Continual Test-Time Adaptation for 2D Medical Image Segmentation

FACT: Frame-Action Cross-Attention Temporal Modeling for Efficient Action Segmentation

Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detection

SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting

AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings

LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model

Prompt Learning via Meta-Regularization

Instance-based Max-margin for Practical Few-shot Recognition

GARField: Group Anything with Radiance Fields

Rethinking Multi-view Representation Learning via Distilled Disentangling

GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians

Grounding Everything: Emerging Localization Properties in Vision-Language Transformers

ShapeMatcher: Self-Supervised Joint Shape Canonicalization Segmentation Retrieval and Deformation

Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning

SVDTree: Semantic Voxel Diffusion for Single Image Tree Reconstruction

OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers

Addressing Background Context Bias in Few-Shot Segmentation through Iterative Modulation

Enhancing Intrinsic Features for Debiasing via Investigating Class-Discerning Common Attributes in Bias-Contrastive Pair

Abductive Ego-View Accident Video Understanding for Safe Driving Perception

Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpses

Prompting Vision Foundation Models for Pathology Image Analysis

EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning

Unmixing Before Fusion: A Generalized Paradigm for Multi-Source-based Hyperspectral Image Synthesis

KITRO: Refining Human Mesh by 2D Clues and Kinematic-tree Rotation

Error Detection in Egocentric Procedural Task Videos

SuperNormal: Neural Surface Reconstruction via Multi-View Normal Integration

Patch2Self2: Self-supervised Denoising on Coresets via Matrix Sketching

Optimizing Diffusion Noise Can Serve As Universal Motion Priors

Efficient Vision-Language Pre-training by Cluster Masking

Generalizable Whole Slide Image Classification with Fine-Grained Visual-Semantic Interaction

Robust Self-calibration of Focal Lengths from the Fundamental Matrix

Navigating Beyond Dropout: An Intriguing Solution towards Generalizable Image Super Resolution

FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition

SlowFormer: Adversarial Attack on Compute and Energy Consumption of Efficient Vision Transformers

Towards the Uncharted: Density-Descending Feature Perturbation for Semi-supervised Semantic Segmentation

Generative Unlearning for Any Identity

Enhancing Multimodal Cooperation via Sample-level Modality Valuation

OVFoodSeg: Elevating Open-Vocabulary Food Image Segmentation via Image-Informed Textual Representation

AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection

CaKDP: Category-aware Knowledge Distillation and Pruning Framework for Lightweight 3D Object Detection

Friendly Sharpness-Aware Minimization

Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch

SCINeRF: Neural Radiance Fields from a Snapshot Compressive Image

Learning to Control Camera Exposure via Reinforcement Learning

Regressor-Segmenter Mutual Prompt Learning for Crowd Counting

SfmCAD: Unsupervised CAD Reconstruction by Learning Sketch-based Feature Modeling Operations

Efficient Detection of Long Consistent Cycles and its Application to Distributed Synchronization

Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange

Vector Graphics Generation via Mutually Impulsed Dual-domain Diffusion

Spectral Meets Spatial: Harmonising 3D Shape Matching and Interpolation

FocSAM: Delving Deeply into Focused Objects in Segmenting Anything

Neural Redshift: Random Networks are not Random Functions

Efficient Privacy-Preserving Visual Localization Using 3D Ray Clouds

Multi-scale Dynamic and Hierarchical Relationship Modeling for Facial Action Units Recognition

Tailored Visions: Enhancing Text-to-Image Generation with Personalized Prompt Rewriting

Imagine Before Go: Self-Supervised Generative Map for Object Goal Navigation

Multi-view Aggregation Network for Dichotomous Image Segmentation

Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior

Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles

SVDinsTN: A Tensor Network Paradigm for Efficient Structure Search from Regularized Modeling Perspective

Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection

Modality-Agnostic Structural Image Representation Learning for Deformable Multi-Modality Medical Image Registration

CustomListener: Text-guided Responsive Interaction for User-friendly Listening Head Generation

Brain Decodes Deep Nets

MoSAR: Monocular Semi-Supervised Model for Avatar Reconstruction using Differentiable Shading

Adapt or Perish: Adaptive Sparse Transformer with Attentive Feature Refinement for Image Restoration

Defense without Forgetting: Continual Adversarial Defense with Anisotropic & Isotropic Pseudo Replay

Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extension

Fully Convolutional Slice-to-Volume Reconstruction for Single-Stack MRI

DiffAvatar: Simulation-Ready Garment Optimization with Differentiable Simulation

PoseIRM: Enhance 3D Human Pose Estimation on Unseen Camera Settings via Invariant Risk Minimization

On the Estimation of Image-matching Uncertainty in Visual Place Recognition

UniHuman: A Unified Model For Editing Human Images in the Wild

Learning to Transform Dynamically for Better Adversarial Transferability

Spin-UP: Spin Light for Natural Light Uncalibrated Photometric Stereo

SEAS: ShapE-Aligned Supervision for Person Re-Identification

Learning to Select Views for Efficient Multi-View Understanding

LidaRF: Delving into Lidar for Neural Radiance Field on Street Scenes

Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs

LoS: Local Structure-Guided Stereo Matching

Geometry-aware Reconstruction and Fusion-refined Rendering for Generalizable Neural Radiance Fields

AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Error

Point2CAD: Reverse Engineering CAD Models from 3D Point Clouds

3DFIRES: Few Image 3D REconstruction for Scenes with Hidden Surfaces

A Unified Framework for Microscopy Defocus Deblur with Multi-Pyramid Transformer and Contrastive Learning

Structure Matters: Tackling the Semantic Discrepancy in Diffusion Models for Image Inpainting

Task2Box: Box Embeddings for Modeling Asymmetric Task Relationships

UniGS: Unified Representation for Image Generation and Segmentation

ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations

DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling

RadSimReal: Bridging the Gap Between Synthetic and Real Data in Radar Object Detection With Simulation

OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation

Meta-Point Learning and Refining for Category-Agnostic Pose Estimation

FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer

Mip-Splatting: Alias-free 3D Gaussian Splatting

Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers

Text2QR: Harmonizing Aesthetic Customization and Scanning Robustness for Text-Guided QR Code Generation

A Unified Framework for Human-centric Point Cloud Video Understanding

UV-IDM: Identity-Conditioned Latent Diffusion Model for Face UV-Texture Generation

UniPTS: A Unified Framework for Proficient Post-Training Sparsity

PBWR: Parametric-Building-Wireframe Reconstruction from Aerial LiDAR Point Clouds

LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding Reasoning and Planning

GenH2R: Learning Generalizable Human-to-Robot Handover via Scalable Simulation Demonstration and Imitation

SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery

ProMark: Proactive Diffusion Watermarking for Causal Attribution

MMM: Generative Masked Motion Model

Bridging the Gap Between End-to-End and Two-Step Text Spotting

DiffSCI: Zero-Shot Snapshot Compressive Imaging via Iterative Spectral Diffusion Model

Content-Style Decoupling for Unsupervised Makeup Transfer without Generating Pseudo Ground Truth

UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs

GenTron: Diffusion Transformers for Image and Video Generation

ODM: A Text-Image Further Alignment Pre-training Approach for Scene Text Detection and Spotting

Misalignment-Robust Frequency Distribution Loss for Image Transformation

Hyperspherical Classification with Dynamic Label-to-Prototype Assignment

WildlifeMapper: Aerial Image Analysis for Multi-Species Detection and Identification

Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts

DiffForensics: Leveraging Diffusion Prior to Image Forgery Detection and Localization

VideoGrounding-DINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding

Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Models

SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos

ODIN: A Single Model for 2D and 3D Segmentation

SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimation

Context-Aware Integration of Language and Visual References for Natural Language Tracking

360Loc: A Dataset and Benchmark for Omnidirectional Visual Localization with Cross-device Queries

Neural Directional Encoding for Efficient and Accurate View-Dependent Appearance Modeling

Prompt Augmentation for Self-supervised Text-guided Image Manipulation

VideoLLM-online: Online Video Large Language Model for Streaming Video

Open-Vocabulary Segmentation with Semantic-Assisted Calibration

FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Models

Physical Property Understanding from Language-Embedded Feature Fields

Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifacts

MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation

SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object Detection

MemoNav: Working Memory Model for Visual Navigation

RCooper: A Real-world Large-scale Dataset for Roadside Cooperative Perception

Task-Customized Mixture of Adapters for General Image Fusion

PointBeV: A Sparse Approach for BeV Predictions

Learning Spatial Adaptation and Temporal Coherence in Diffusion Models for Video Super-Resolution

Ensemble Diversity Facilitates Adversarial Transferability

ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding

SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples

SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking

EvalCrafter: Benchmarking and Evaluating Large Video Generation Models

Implicit Discriminative Knowledge Learning for Visible-Infrared Person Re-Identification

Sheared Backpropagation for Fine-tuning Foundation Models

On the Content Bias in Fréchet Video Distance

NeRF-HuGS: Improved Neural Radiance Fields in Non-static Scenes Using Heuristics-Guided Segmentation

Hyperbolic Learning with Synthetic Captions for Open-World Detection

CFAT: Unleashing Triangular Windows for Image Super-resolution

Towards Language-Driven Video Inpainting via Multimodal Large Language Models

Convolutional Prompting meets Language Models for Continual Learning

From Activation to Initialization: Scaling Insights for Optimizing Neural Fields

Multiview Aerial Visual RECognition (MAVREC): Can Multi-view Improve Aerial Visual Perception?

High-fidelity Person-centric Subject-to-Image Synthesis

Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning

Fixed Point Diffusion Models

Contextual Augmented Global Contrast for Multimodal Intent Recognition

Intraoperative 2D/3D Image Registration via Differentiable X-ray Rendering

SchurVINS: Schur Complement-Based Lightweight Visual Inertial Navigation System

Depth Information Assisted Collaborative Mutual Promotion Network for Single Image Dehazing

MACE: Mass Concept Erasure in Diffusion Models

JDEC: JPEG Decoding via Enhanced Continuous Cosine Coefficients

MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model

SpikeNeRF: Learning Neural Radiance Fields from Continuous Spike Stream

Revisiting Adversarial Training Under Long-Tailed Distributions

Integrating Efficient Optimal Transport and Functional Maps For Unsupervised Shape Correspondence Learning

VINECS: Video-based Neural Character Skinning

Generative Powers of Ten

Plug and Play Active Learning for Object Detection

SuperPrimitive: Scene Reconstruction at a Primitive Level

Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose Estimation

Towards a Simultaneous and Granular Identity-Expression Control in Personalized Face Generation

Relaxed Contrastive Learning for Federated Learning

EVCap: Retrieval-Augmented Image Captioning with External Visual-Name Memory for Open-World Comprehension

GlitchBench: Can Large Multimodal Models Detect Video Game Glitches?

Plug-and-Play Diffusion Distillation

CLIB-FIQA: Face Image Quality Assessment with Confidence Calibration

TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding

Polos: Multimodal Metric Learning from Human Feedback for Image Captioning

XScale-NVS: Cross-Scale Novel View Synthesis with Hash Featurized Manifold

LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation

LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry

Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understanding

FFF: Fixing Flawed Foundations in Contrastive Pre-Training Results in Very Strong Vision-Language Models

DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations

AvatarGPT: All-in-One Framework for Motion Understanding Planning Generation and Beyond

Learning Degradation-unaware Representation with Prior-based Latent Transformations for Blind Face Restoration

Differentiable Micro-Mesh Construction

HOIDiffusion: Generating Realistic 3D Hand-Object Interaction Data

CPGA: Coding Priors-Guided Aggregation Network for Compressed Video Quality Enhancement

Enhancing Vision-Language Pre-training with Rich Supervisions

Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery

HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields

CycleINR: Cycle Implicit Neural Representation for Arbitrary-Scale Volumetric Super-Resolution of Medical Data

Beyond Textual Constraints: Learning Novel Diffusion Conditions with Fewer Examples

ProxyCap: Real-time Monocular Full-body Capture in World Space via Human-Centric Proxy-to-Motion Learning

Learning from Synthetic Human Group Activities

Can’t Make an Omelette Without Breaking Some Eggs: Plausible Action Anticipation Using Large Video-Language Models

Task-aligned Part-aware Panoptic Segmentation through Joint Object-Part Representations

FreeKD: Knowledge Distillation via Semantic Frequency Prompt

Enhanced Motion-Text Alignment for Image-to-Video Transfer Learning

ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection

Unsupervised 3D Structure Inference from Category-Specific Image Collections

Video2Game: Real-time Interactive Realistic and Browser-Compatible Environment from a Single Video

Identifying Important Group of Pixels using Interactions

360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model

Alpha Invariance: On Inverse Scaling Between Distance and Volume Density in Neural Radiance Fields

Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring

Countering Personalized Text-to-Image Generation with Influence Watermarks

ContextSeg: Sketch Semantic Segmentation by Querying the Context with Attention

Multi-Modal Proxy Learning Towards Personalized Visual Multiple Clustering

Adaptive Bidirectional Displacement for Semi-Supervised Medical Image Segmentation

Curriculum Point Prompting for Weakly-Supervised Referring Image Segmentation

Targeted Representation Alignment for Open-World Semi-Supervised Learning

Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding

SNIDA: Unlocking Few-Shot Object Detection with Non-linear Semantic Decoupling Augmentation

Edit One for All: Interactive Batch Image Editing

TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentation

Automatic Controllable Colorization via Imagination

DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models

Genuine Knowledge from Practice: Diffusion Test-Time Adaptation for Video Adverse Weather Removal

Are Conventional SNNs Really Efficient? A Perspective from Network Quantization

RILA: Reflective and Imaginative Language Agent for Zero-Shot Semantic Audio-Visual Navigation

Adaptive Multi-Modal Cross-Entropy Loss for Stereo Matching

FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embedding

Driving-Video Dehazing with Non-Aligned Regularization for Safety Assistance

Teeth-SEG: An Efficient Instance Segmentation Framework for Orthodontic Treatment based on Multi-Scale Aggregation and Anthropic Prior Knowledge

SportsSloMo: A New Benchmark and Baselines for Human-centric Video Frame Interpolation

Mind Artist: Creating Artistic Snapshots with Human Thought

Sharingan: A Transformer Architecture for Multi-Person Gaze Following

OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation

Unifying Top-down and Bottom-up Scanpath Prediction Using Transformers

DAP: A Dynamic Adversarial Patch for Evading Person Detectors

Exploring Region-Word Alignment in Built-in Detector for Open-Vocabulary Object Detection

L0-Sampler: An L0 Model Guided Volume Sampling for NeRF

Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing

T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memory

SAI3D: Segment Any Instance in 3D Scenes

Implicit Motion Function

Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features

Dynamic Support Information Mining for Category-Agnostic Pose Estimation

Coupled Laplacian Eigenmaps for Locally-Aware 3D Rigid Point Cloud Matching

Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness

De-Diffusion Makes Text a Strong Cross-Modal Interface

MART: Masked Affective RepresenTation Learning via Masked Temporal Distribution Distillation

Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis

ICP-Flow: LiDAR Scene Flow Estimation with ICP

Unsupervised Occupancy Learning from Sparse Point Cloud

Benchmarking Implicit Neural Representation and Geometric Rendering in Real-Time RGB-D SLAM

GLOW: Global Layout Aware Attacks on Object Detection

Context-based and Diversity-driven Specificity in Compositional Zero-Shot Learning

DeepCache: Accelerating Diffusion Models for Free

The Devil is in the Fine-Grained Details: Evaluating Open-Vocabulary Object Detectors for Fine-Grained Understanding

HPNet: Dynamic Trajectory Forecasting with Historical Prediction Attention

CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection

Neural Underwater Scene Representation

Semantic Human Mesh Reconstruction with Textures

Scaled Decoupled Distillation

T-VSL: Text-Guided Visual Sound Source Localization in Mixtures

CN-RMA: Combined Network with Ray Marching Aggregation for 3D Indoor Object Detection from Multi-view Images

PolarMatte: Fully Computational Ground-Truth-Quality Alpha Matte Extraction for Images and Video using Polarized Screen Matting

MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World

CosalPure: Learning Concept from Group Images for Robust Co-Saliency Detection

Neural Clustering based Visual Representation Learning

ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models

BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation

CrossMAE: Cross-Modality Masked Autoencoders for Region-Aware Audio-Visual Pre-Training

Concept Weaver: Enabling Multi-Concept Fusion in Text-to-Image Models

CapHuman: Capture Your Moments in Parallel Universes

VISTA-LLAMA: Reducing Hallucination in Video Language Models via Equal Distance to Visual Tokens

CDMAD: Class-Distribution-Mismatch-Aware Debiasing for Class-Imbalanced Semi-Supervised Learning

Low-Rank Rescaled Vision Transformer Fine-Tuning: A Residual Design Approach

Hierarchical Intra-modal Correlation Learning for Label-free 3D Semantic Segmentation

Real-World Mobile Image Denoising Dataset with Efficient Baselines

NeRF Director: Revisiting View Selection in Neural Volume Rendering

Map-Relative Pose Regression for Visual Re-Localization

MANUS: Markerless Grasp Capture using Articulated 3D Gaussians

Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection

ChAda-ViT : Channel Adaptive Attention for Joint Representation Learning of Heterogeneous Microscopy Images

Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation

HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models

PARA-Drive: Parallelized Architecture for Real-time Autonomous Driving

Towards Generalizable Tumor Synthesis

4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling

GenNBV: Generalizable Next-Best-View Policy for Active 3D Reconstruction

Adaptive Hyper-graph Aggregation for Modality-Agnostic Federated Learning

VS: Reconstructing Clothed 3D Human from Single Image via Vertex Shift

Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation

En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data

Diversified and Personalized Multi-rater Medical Image Segmentation

ANIM: Accurate Neural Implicit Model for Human Reconstruction from a single RGB-D Image

VicTR: Video-conditioned Text Representations for Activity Recognition

vid-TLDR: Training Free Token Merging for Light-weight Video Transformer

Towards Automatic Power Battery Detection: New Challenge Benchmark Dataset and Baseline

Point Transformer V3: Simpler Faster Stronger

Improving Distant 3D Object Detection Using 2D Box Supervision

Bi-SSC: Geometric-Semantic Bidirectional Fusion for Camera-based 3D Semantic Scene Completion

Efficient and Effective Weakly-Supervised Action Segmentation via Action-Transition-Aware Boundary Alignment

Depth-Aware Concealed Crop Detection in Dense Agricultural Scenes

FC-GNN: Recovering Reliable and Accurate Correspondences from Interferences

Infrared Small Target Detection with Scale and Location Sensitivity

DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models

Wonder3D: Single Image to 3D using Cross-Domain Diffusion

Honeybee: Locality-enhanced Projector for Multimodal LLM

Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?

MoMask: Generative Masked Modeling of 3D Human Motions

CapsFusion: Rethinking Image-Text Data at Scale

Gradient-based Parameter Selection for Efficient Fine-Tuning

UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio Video Point Cloud Time-Series and Image Recognition

Real-Time Simulated Avatar from Head-Mounted Sensors

ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Models

MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception

Mining Supervision for Dynamic Regions in Self-Supervised Monocular Depth Estimation

Initialization Matters for Adversarial Transfer Learning

Stationary Representations: Optimally Approximating Compatibility and Implications for Improved Model Replacements

Text2Loc: 3D Point Cloud Localization from Natural Language

Gaussian Shadow Casting for Neural Characters

SleepVST: Sleep Staging from Near-Infrared Video Signals using Pre-Trained Transformers

Enhancing 3D Fidelity of Text-to-3D using Cross-View Correspondences

A General and Efficient Training for Transformer via Token Expansion

BigGait: Learning Gait Representation You Want by Large Vision Models

Event-based Visible and Infrared Fusion via Multi-task Collaboration

Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval

Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models

Language-Driven Anchors for Zero-Shot Adversarial Robustness

Breathing Life Into Sketches Using Text-to-Video Priors

Gaussian Shell Maps for Efficient 3D Human Generation

AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation

Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environments

Learning Vision from Models Rivals Learning Vision from Data

Byzantine-robust Decentralized Federated Learning via Dual-domain Clustering and Trust Bootstrapping

Incorporating Geo-Diverse Knowledge into Prompting for Increased Geographical Robustness in Object Recognition

MotionEditor: Editing Video Motion via Content-Aware Diffusion

EVS-assisted Joint Deblurring Rolling-Shutter Correction and Video Frame Interpolation through Sensor Inverse Modeling

DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protection

Open-World Semantic Segmentation Including Class Similarity

MindBridge: A Cross-Subject Brain Decoding Framework

Loopy-SLAM: Dense Neural SLAM with Loop Closures

Weakly-Supervised Audio-Visual Video Parsing with Prototype-based Pseudo-Labeling

State Space Models for Event Cameras

DiffInDScene: Diffusion-based High-Quality 3D Indoor Scene Generation

Towards Calibrated Multi-label Deep Neural Networks

TIM: A Time Interval Machine for Audio-Visual Action Recognition

Universal Segmentation at Arbitrary Granularity with Language Instruction

Empowering Resampling Operation for Ultra-High-Definition Image Enhancement with Model-Aware Guidance

READ: Retrieval-Enhanced Asymmetric Diffusion for Motion Planning

From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models

Spectrum AUC Difference (SAUCD): Human-aligned 3D Shape Evaluation

MeshPose: Unifying DensePose and 3D Body Mesh Reconstruction

Jack of All Tasks Master of Many: Designing General-Purpose Coarse-to-Fine Vision-Language Model

AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation

Test-Time Linear Out-of-Distribution Detection

Matching Anything by Segmenting Anything

MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models

InstaGen: Enhancing Object Detection by Training on Synthetic Dataset

Narrative Action Evaluation with Prompt-Guided Multimodal Interaction

Multi-Space Alignments Towards Universal LiDAR Segmentation

Exploiting Style Latent Flows for Generalizing Deepfake Video Detection

DeCoTR: Enhancing Depth Completion with 2D and 3D Attentions

Bayesian Differentiable Physics for Cloth Digitalization

MemSAM: Taming Segment Anything Model for Echocardiography Video Segmentation

SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing

ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts

LeGO: Leveraging a Surface Deformation Network for Animatable Stylized Face Generation with One Example

Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning

Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers

Prompting Hard or Hardly Prompting: Prompt Inversion for Text-to-Image Diffusion Models

OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion

Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision Language Audio and Action

PTQ4SAM: Post-Training Quantization for Segment Anything

Leveraging Predicate and Triplet Learning for Scene Graph Generation

Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment

HHMR: Holistic Hand Mesh Recovery by Enhancing the Multimodal Controllability of Graph Diffusion Models

PixelRNN: In-pixel Recurrent Neural Networks for End-to-end–optimized Perception with Neural Sensors

Codebook Transfer with Part-of-Speech for Vector-Quantized Image Modeling

Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis

Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships

DeconfuseTrack: Dealing with Confusion for Multi-Object Tracking

ChatPose: Chatting about 3D Human Pose

Modality-agnostic Domain Generalizable Medical Image Segmentation by Multi-Frequency in Multi-Scale Attention

NC-TTT: A Noise Constrastive Approach for Test-Time Training

Improved Baselines with Visual Instruction Tuning

DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks

DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis

Enhancing Visual Continual Learning with Language-Guided Supervision

PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI

Video Prediction by Modeling Videos as Continuous Multi-Dimensional Processes

MoST: Motion Style Transformer Between Diverse Action Contents

Bilateral Propagation Network for Depth Completion

Training Diffusion Models Towards Diverse Image Generation with Reinforcement Learning

Rotation-Agnostic Image Representation Learning for Digital Pathology

Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimation

Unsupervised Keypoints from Pretrained Diffusion Models

Generating Human Motion in 3D Scenes from Text Descriptions

Visual Point Cloud Forecasting enables Scalable Autonomous Driving

Light the Night: A Multi-Condition Diffusion Framework for Unpaired Low-Light Enhancement in Autonomous Driving

MaGGIe: Masked Guided Gradual Human Instance Matting

JRDB-PanoTrack: An Open-world Panoptic Segmentation and Tracking Robotic Dataset in Crowded Human Environments

Perturbing Attention Gives You More Bang for the Buck: Subtle Imaging Perturbations That Efficiently Fool Customized Diffusion Models

DreamSalon: A Staged Diffusion Framework for Preserving Identity-Context in Editable Face Generation

On the Road to Portability: Compressing End-to-End Motion Planner for Autonomous Driving

Uncertainty-Aware Source-Free Adaptive Image Super-Resolution with Wavelet Augmentation Transformer

Generalizing 6-DoF Grasp Detection via Domain Prior Knowledge

Bridging the Synthetic-to-Authentic Gap: Distortion-Guided Unsupervised Domain Adaptation for Blind Image Quality Assessment

Backpropagation-free Network for 3D Test-time Adaptation

Intensity-Robust Autofocus for Spike Camera

NoiseCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions in Diffusion Models

Grid Diffusion Models for Text-to-Video Generation

Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstruction

Making Vision Transformers Truly Shift-Equivariant

DreamVideo: Composing Your Dream Videos with Customized Subject and Motion

Few-Shot Object Detection with Foundation Models

Posterior Distillation Sampling

RankED: Addressing Imbalance and Uncertainty in Edge Detection Using Ranking-based Losses

TransNeXt: Robust Foveal Visual Perception for Vision Transformers

MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

Elite360D: Towards Efficient 360 Depth Estimation via Semantic- and Distance-Aware Bi-Projection Fusion

Learning Triangular Distribution in Visual World

Your Student is Better Than Expected: Adaptive Teacher-Student Collaboration for Text-Conditional Diffusion Models

Generative Multimodal Models are In-Context Learners

Free3D: Consistent Novel View Synthesis without 3D Representation

Fine-Grained Bipartite Concept Factorization for Clustering

GLiDR: Topologically Regularized Graph Generative Network for Sparse LiDAR Point Clouds

Sherpa3D: Boosting High-Fidelity Text-to-3D Generation via Coarse 3D Prior

HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation

Generalized Event Cameras

Multimodal Prompt Perceiver: Empower Adaptiveness Generalizability and Fidelity for All-in-One Image Restoration

Generate Subgoal Images before Act: Unlocking the Chain-of-Thought Reasoning in Diffusion Model for Robot Manipulation with Multimodal Prompts

BEVSpread: Spread Voxel Pooling for Bird’s-Eye-View Representation in Vision-based Roadside 3D Object Detection

ESCAPE: Encoding Super-keypoints for Category-Agnostic Pose Estimation

GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinement

Minimal Perspective Autocalibration

ReGenNet: Towards Human Action-Reaction Synthesis

ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models

Unbiased Estimator for Distorted Conics in Camera Calibration

Siamese Learning with Joint Alignment and Regression for Weakly-Supervised Video Paragraph Grounding

Dual Pose-invariant Embeddings: Learning Category and Object-specific Discriminative Representations for Recognition and Retrieval

Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer

NIVeL: Neural Implicit Vector Layers for Text-to-Vector Generation

Hyperbolic Anomaly Detection

Selective Nonlinearities Removal from Digital Signals

Enhancing Quality of Compressed Images by Mitigating Enhancement Bias Towards Compression Domain

Accurate Training Data for Occupancy Map Prediction in Automated Driving Using Evidence Theory

The Audio-Visual Conversational Graph: From an Egocentric-Exocentric Perspective

Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline

FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation

TIGER: Time-Varying Denoising Model for 3D Point Cloud Generation with Diffusion Process

MLP Can Be A Good Transformer Learner

HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video

Learning Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification

InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning

Backdoor Defense via Test-Time Detecting and Repairing

Towards a Perceptual Evaluation Framework for Lighting Estimation

SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution

ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions

RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos

Aligning and Prompting Everything All at Once for Universal Visual Perception

ZONE: Zero-Shot Instruction-Guided Local Editing

Learning to Count without Annotations

DanceCamera3D: 3D Camera Movement Synthesis with Music and Dance

HIVE: Harnessing Human Feedback for Instructional Visual Editing

OmniGlue: Generalizable Feature Matching with Foundation Model Guidance

HoloVIC: Large-scale Dataset and Benchmark for Multi-Sensor Holographic Intersection and Vehicle-Infrastructure Cooperative

LoSh: Long-Short Text Joint Prediction Network for Referring Video Object Segmentation

Towards Backward-Compatible Continual Learning of Image Compression

Clustering for Protein Representation Learning

RoDLA: Benchmarking the Robustness of Document Layout Analysis Models

Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos

Diffusion-FOF: Single-View Clothed Human Reconstruction via Diffusion-Based Fourier Occupancy Field

What Sketch Explainability Really Means for Downstream Tasks?

Leveraging Frame Affinity for sRGB-to-RAW Video De-rendering

X-Adapter: Adding Universal Compatibility of Plugins for Upgraded Diffusion Model

SURE: SUrvey REcipes for building reliable and robust deep networks

Spanning Training Progress: Temporal Dual-Depth Scoring (TDDS) for Enhanced Dataset Pruning

Learning CNN on ViT: A Hybrid Model to Explicitly Class-specific Boundaries for Domain Adaptation

GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereo

Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models

From Correspondences to Pose: Non-minimal Certifiably Optimal Relative Pose without Disambiguation

Cross-Dimension Affinity Distillation for 3D EM Neuron Segmentation

AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving

Open-Vocabulary Attention Maps with Token Optimization for Semantic Segmentation in Diffusion Models

Attentive Illumination Decomposition Model for Multi-Illuminant White Balancing

Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaption

Text Grouping Adapter: Adapting Pre-trained Text Detector for Layout Analysis

Label Propagation for Zero-shot Classification with Vision-Language Models

VRetouchEr: Learning Cross-frame Feature Interdependence with Imperfection Flow for Face Retouching in Videos

3D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation

Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learning

Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation

A&B BNN: Add&Bit-Operation-Only Hardware-Friendly Binary Neural Network

CommonCanvas: Open Diffusion Models Trained on Creative-Commons Images

Choose What You Need: Disentangled Representation Learning for Scene Text Recognition Removal and Editing

Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generation

LEOD: Label-Efficient Object Detection for Event Cameras

MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers

Unsegment Anything by Simulating Deformation

OpenESS: Event-based Semantic Scene Understanding with Open Vocabularies

Z*: Zero-shot Style Transfer via Attention Reweighting

VAREN: Very Accurate and Realistic Equine Network

Memory-based Adapters for Online 3D Scene Perception

Atlantis: Enabling Underwater Depth Estimation with Stable Diffusion

Ranni: Taming Text-to-Image Diffusion for Accurate Instruction Following

Cross-spectral Gated-RGB Stereo Depth Estimation

GeoAuxNet: Towards Universal 3D Representation Learning for Multi-sensor Point Clouds

SuperSVG: Superpixel-based Scalable Vector Graphics Synthesis

Video ReCap: Recursive Captioning of Hour-Long Videos

Self-Adaptive Reality-Guided Diffusion for Artifact-Free Super-Resolution

G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis

3D Face Reconstruction with the Geometric Guidance of Facial Part Segmentation

MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation

EfficientDreamer: High-Fidelity and Robust 3D Creation via Orthogonal-view Diffusion Priors

IQ-VFI: Implicit Quadratic Motion Estimation for Video Frame Interpolation

Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition

HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models

CAPE: CAM as a Probabilistic Ensemble for Enhanced DNN Interpretation

Probabilistic Sampling of Balanced K-Means using Adiabatic Quantum Computing

Semantic-aware SAM for Point-Prompted Instance Segmentation

Spike-guided Motion Deblurring with Unknown Modal Spatiotemporal Alignment

Multi-Task Dense Prediction via Mixture of Low-Rank Experts

EASE-DETR: Easing the Competition among Object Queries

GSNeRF: Generalizable Semantic Neural Radiance Fields with Enhanced 3D Scene Understanding

CAT-DM: Controllable Accelerated Virtual Try-on with Diffusion Model

CoGS: Controllable Gaussian Splatting

A Bayesian Approach to OOD Robustness in Image Classification

Multimodal Pathway: Improve Transformers with Irrelevant Data from Other Modalities

ConCon-Chi: Concept-Context Chimera Benchmark for Personalized Vision-Language Tasks

Readout Guidance: Learning Control from Diffusion Features

Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning

Action Detection via an Image Diffusion Process

Transcriptomics-guided Slide Representation Learning in Computational Pathology

Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous and Instruction-guided Driving

ConTex-Human: Free-View Rendering of Human from a Single Image with Texture-Consistent Synthesis

Structured Model Probing: Empowering Efficient Transfer Learning by Structured Regularization

CRKD: Enhanced Camera-Radar Object Detection with Cross-modality Knowledge Distillation

Instance-aware Contrastive Learning for Occluded Human Mesh Reconstruction

InstructDiffusion: A Generalist Modeling Interface for Vision Tasks

BrainWash: A Poisoning Attack to Forget in Continual Learning

SurroundSDF: Implicit 3D Scene Understanding Based on Signed Distance Field

WALT3D: Generating Realistic Training Data from Time-Lapse Imagery for Reconstructing Dynamic Objects Under Occlusion

Data Valuation and Detections in Federated Learning

MLIP: Enhancing Medical Visual Representation with Divergence Encoder and Knowledge-guided Contrastive Learning

Making Visual Sense of Oracle Bones for You and Me

S2MAE: A Spatial-Spectral Pretraining Foundation Model for Spectral Remote Sensing Data

ProTeCt: Prompt Tuning for Taxonomic Open Set Classification

UnO: Unsupervised Occupancy Fields for Perception and Forecasting

Active Open-Vocabulary Recognition: Let Intelligent Moving Mitigate CLIP Limitations

Mosaic-SDF for 3D Generative Models

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World Conditions

DITTO: Dual and Integrated Latent Topologies for Implicit 3D Reconstruction

Unveiling the Unknown: Unleashing the Power of Unknown to Known in Open-Set Source-Free Domain Adaptation

AutoAD III: The Prequel – Back to the Pixels

Towards More Accurate Diffusion Model Acceleration with A Timestep Tuner

Characteristics Matching Based Hash Codes Generation for Efficient Fine-grained Image Retrieval

Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing

DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Video

Learning Spatial Features from Audio-Visual Correspondence in Egocentric Videos

TUMTraf V2X Cooperative Perception Dataset

Disentangled Prompt Representation for Domain Generalization

Visual Concept Connectome (VCC): Open World Concept Discovery and their Interlayer Connections in Deep Models

UniMODE: Unified Monocular 3D Object Detection

HPL-ESS: Hybrid Pseudo-Labeling for Unsupervised Event-based Semantic Segmentation

PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarios

Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving

A Recipe for Scaling up Text-to-Video Generation with Text-free Videos

SAOR: Single-View Articulated Object Reconstruction

GenHowTo: Learning to Generate Actions and State Transformations from Instructional Videos

TULIP: Transformer for Upsampling of LiDAR Point Clouds

Incremental Residual Concept Bottleneck Models

Neural Implicit Representation for Building Digital Twins of Unknown Articulated Objects

Improving Transferable Targeted Adversarial Attacks with Model Self-Enhancement

Human Gaussian Splatting: Real-time Rendering of Animatable Avatars

Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigation

DiffAgent: Fast and Accurate Text-to-Image API Selection with Large Language Model

Density-Adaptive Model Based on Motif Matrix for Multi-Agent Trajectory Prediction

Towards Accurate Post-training Quantization for Diffusion Models

Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training

KeyPoint Relative Position Encoding for Face Recognition

QDFormer: Towards Robust Audiovisual Segmentation in Complex Environments with Quantization-based Semantic Decomposition

Open-Vocabulary Semantic Segmentation with Image Embedding Balancing

MoST: Multi-Modality Scene Tokenization for Motion Prediction

View-decoupled Transformer for Person Re-identification under Aerial-ground Camera Network

Gear-NeRF: Free-Viewpoint Rendering and Tracking with Motion-aware Spatio-Temporal Sampling

NECA: Neural Customizable Human Avatar

EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World

From a Bird's Eye View to See: Joint Camera and Subject Registration without the Camera Calibration

Self-correcting LLM-controlled Diffusion Models

Efficient Dataset Distillation via Minimax Diffusion

DUSt3R: Geometric 3D Vision Made Easy

Enhancing Video Super-Resolution via Implicit Resampling-based Alignment

Adversarial Text to Continuous Image Generation

InceptionNeXt: When Inception Meets ConvNeXt

MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild

MultiDiff: Consistent Novel View Synthesis from a Single Image

Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSM

Joint2Human: High-Quality 3D Human Generation via Compact Spherical Embedding of 3D Joints

Inversion-Free Image Editing with Language-Guided Diffusion Models

Investigating Compositional Challenges in Vision-Language Models for Visual Grounding

Generalizable Face Landmarking Guided by Conditional Face Warping

Multi-Scale Video Anomaly Detection by Multi-Grained Spatio-Temporal Representation Learning

Uncertainty-aware Action Decoupling Transformer for Action Anticipation

Boosting Adversarial Training via Fisher-Rao Norm-based Regularization

InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization

SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation

How to Configure Good In-Context Sequence for Visual Question Answering

FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis

DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving

eTraM: Event-based Traffic Monitoring Dataset

PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection

SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes

Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis

FakeInversion: Learning to Detect Images from Unseen Text-to-Image Models by Inverting Stable Diffusion

SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion

VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

TextNeRF: A Novel Scene-Text Image Synthesis Method based on Neural Radiance Fields

DiffusionLight: Light Probes for Free by Painting a Chrome Ball

Accept the Modality Gap: An Exploration in the Hyperbolic Space

MirageRoom: 3D Scene Segmentation with 2D Pre-trained Models by Mirage Projection

Describing Differences in Image Sets with Natural Language

GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence

Object Pose Estimation via the Aggregation of Diffusion Features

6D-Diff: A Keypoint Diffusion Framework for 6D Object Pose Estimation

Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement

Stronger Fewer & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation

OpenStreetView-5M: The Many Roads to Global Visual Geolocation

An Asymmetric Augmented Self-Supervised Learning Method for Unsupervised Fine-Grained Image Hashing

MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model

Action Scene Graphs for Long-Form Understanding of Egocentric Videos

Multi-Session SLAM with Differentiable Wide-Baseline Pose Optimization

Neural Lineage

RNb-NeuS: Reflectance and Normal-based Multi-View 3D Reconstruction

Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation

Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Models

Polarization Wavefront Lidar: Learning Large Scene Reconstruction from Polarized Wavefronts

Multi-Attribute Interactions Matter for 3D Visual Grounding

CAD: Photorealistic 3D Generation via Adversarial Distillation

UnionFormer: Unified-Learning Transformer with Multi-View Representation for Image Manipulation Detection and Localization

Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D

DiffusionTrack: Point Set Diffusion Model for Visual Object Tracking

EmoGen: Emotional Image Content Generation with Text-to-Image Diffusion Models

Decoupled Pseudo-labeling for Semi-Supervised Monocular 3D Object Detection

SpiderMatch: 3D Shape Matching with Global Optimality and Geometric Consistency

Towards Better Vision-Inspired Vision-Language Models

Gated Fields: Learning Scene Reconstruction from Gated Videos

Realigning Confidence with Temporal Saliency Information for Point-Level Weakly-Supervised Temporal Action Localization

3D Facial Expressions through Analysis-by-Neural-Synthesis

Selective Interpretable and Motion Consistent Privacy Attribute Obfuscation for Action Recognition

Segment and Caption Anything

ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image

A2XP: Towards Private Domain Generalization

Training Like a Medical Resident: Context-Prior Learning Toward Universal Medical Image Segmentation

CityDreamer: Compositional Generative Model of Unbounded 3D Cities

Noisy-Correspondence Learning for Text-to-Image Person Re-identification

ParamISP: Learned Forward and Inverse ISPs using Camera Parameters

Diversity-aware Channel Pruning for StyleGAN Compression

LEMON: Learning 3D Human-Object Interaction Relation from 2D Images

Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection

Prompt-Enhanced Multiple Instance Learning for Weakly Supervised Video Anomaly Detection

VoCo: A Simple-yet-Effective Volume Contrastive Learning Framework for 3D Medical Image Analysis

Brush2Prompt: Contextual Prompt Generator for Object Inpainting

NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild

Random Entangled Tokens for Adversarially Robust Vision Transformer

PNeRV: Enhancing Spatial Consistency via Pyramidal Neural Representation for Videos

Step Differences in Instructional Video

OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition

G^3-LQ: Marrying Hyperbolic Alignment with Explicit Semantic-Geometric Modeling for 3D Visual Grounding

Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images

NightCC: Nighttime Color Constancy via Adaptive Channel Masking

SyncMask: Synchronized Attentional Masking for Fashion-centric Vision-Language Pretraining

DYSON: Dynamic Feature Space Self-Organization for Online Task-Free Class Incremental Learning

Harnessing Large Language Models for Training-free Video Anomaly Detection

EvDiG: Event-guided Direct and Global Components Separation

Condition-Aware Neural Network for Controlled Image Generation

Sparse Views Near Light: A Practical Paradigm for Uncalibrated Point-light Photometric Stereo

Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences

Total Selfie: Generating Full-Body Selfies

LayoutFormer: Hierarchical Text Detection Towards Scene Text Understanding

ODCR: Orthogonal Decoupling Contrastive Regularization for Unpaired Image Dehazing

Accelerating Neural Field Training via Soft Mining

PEGASUS: Personalized Generative 3D Avatars with Composable Attributes

PanoContext-Former: Panoramic Total Scene Understanding with a Transformer

LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding

PrPSeg: Universal Proposition Learning for Panoramic Renal Pathology Segmentation

SimAC: A Simple Anti-Customization Method for Protecting Face Privacy against Text-to-Image Synthesis of Diffusion Models

On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm

Continuous Pose for Monocular Cameras in Neural Implicit Representation

RobustSAM: Segment Anything Robustly on Degraded Images

Learned Trajectory Embedding for Subspace Clustering

ExtDM: Distribution Extrapolation Diffusion Model for Video Prediction

HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting

Depth Prompting for Sensor-Agnostic Depth Estimation

Modality-Collaborative Test-Time Adaptation for Action Recognition

DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback

BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning

Rethinking the Objectives of Vector-Quantized Tokenizers for Image Synthesis

Weakly Supervised Video Individual Counting

Rethinking Inductive Biases for Surface Normal Estimation

SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wild

Total-Decom: Decomposed 3D Scene Reconstruction with Minimal Interaction

Dynamic Prompt Optimizing for Text-to-Image Generation

Hallucination Augmented Contrastive Learning for Multimodal Large Language Model

LORS: Low-rank Residual Structure for Parameter-Efficient Network Stacking

Grounded Question-Answering in Long Egocentric Videos

FairRAG: Fair Human Generation via Fair Retrieval Augmentation

MicroDiffusion: Implicit Representation-Guided Diffusion for 3D Reconstruction from Limited 2D Microscopy Projections

Learning Inclusion Matching for Animation Paint Bucket Colorization

DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery

Visual Layout Composer: Image-Vector Dual Diffusion Model for Design Layout Generation

Pose-Guided Self-Training with Two-Stage Clustering for Unsupervised Landmark Discovery

DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction

Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding

LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching

Preserving Fairness Generalization in Deepfake Detection

RepViT: Revisiting Mobile CNN From ViT Perspective

Simple Semantic-Aided Few-Shot Learning

OVMR: Open-Vocabulary Recognition with Multi-Modal References

AETTA: Label-Free Accuracy Estimation for Test-Time Adaptation

A Video is Worth 256 Bases: Spatial-Temporal Expectation-Maximization Inversion for Zero-Shot Video Editing

A Simple Recipe for Language-guided Domain Generalized Segmentation

An Edit Friendly DDPM Noise Space: Inversion and Manipulations

AdaShift: Learning Discriminative Self-Gated Neural Feature Activation With an Adaptive Shift Factor

Improved Implicit Neural Representation with Fourier Reparameterized Training

Gradient Alignment for Cross-Domain Face Anti-Spoofing

U-VAP: User-specified Visual Appearance Personalization via Decoupled Self Augmentation

Multi-Object Tracking in the Dark

RoMa: Robust Dense Feature Matching

DaReNeRF: Direction-aware Representation for Dynamic Scenes

DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning

Federated Online Adaptation for Deep Stereo

MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer

ReconFusion: 3D Reconstruction with Diffusion Priors

PredToken: Predicting Unknown Tokens and Beyond with Coarse-to-Fine Iterative Decoding

ReCoRe: Regularized Contrastive Representation Learning of World Model

Learning Object State Changes in Videos: An Open-World Perspective

FSC: Few-point Shape Completion

Prompt-Free Diffusion: Taking “Text” out of Text-to-Image Diffusion Models

Data-Efficient Unsupervised Interpolation Without Any Intermediate Frame for 4D Medical Images

Holistic Features are almost Sufficient for Text-to-Video Retrieval

Causal Mode Multiplexer: A Novel Framework for Unbiased Multispectral Pedestrian Detection

Seeing the Unseen: Visual Common Sense for Semantic Placement

Diffuse Attend and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion

GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation

How to Handle Sketch-Abstraction in Sketch-Based Image Retrieval?

You'll Never Walk Alone: A Sketch and Text Duet for Fine-Grained Image Retrieval

It's All About Your Sketch: Democratising Sketch Control in Diffusion Models

Text-to-Image Diffusion Models are Great Sketch-Photo Matchmakers

One-Prompt to Segment All Medical Images

Insights from the Use of Previously Unseen Neural Architecture Search Datasets

General Object Foundation Model for Images and Videos at Scale

A Pedestrian is Worth One Prompt: Towards Language Guidance Person Re-Identification

CFPL-FAS: Class Free Prompt Learning for Generalizable Face Anti-spoofing

WonderJourney: Going from Anywhere to Everywhere

From Isolated Islands to Pangea: Unifying Semantic Space for Human Action Understanding

MoDE: CLIP Data Experts via Clustering

POCE: Primal Policy Optimization with Conservative Estimation for Multi-constraint Offline Reinforcement Learning

Flow-Guided Online Stereo Rectification for Wide Baseline Stereo

4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training

Instantaneous Perception of Moving Objects in 3D

CLIP-Driven Open-Vocabulary 3D Scene Graph Generation via Cross-Modality Contrastive Learning

Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning

Layout-Agnostic Scene Text Image Synthesis with Diffusion Models

Fourier Priors-Guided Diffusion for Zero-Shot Joint Low-Light Enhancement and Deblurring

Collaborative Semantic Occupancy Prediction with Hybrid Feature Fusion in Connected Automated Vehicles

GOV-NeSF: Generalizable Open-Vocabulary Neural Semantic Fields

CoDi: Conditional Diffusion Distillation for Higher-Fidelity and Faster Image Generation

Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation

Density-guided Translator Boosts Synthetic-to-Real Unsupervised Domain Adaptive Segmentation of 3D Point Clouds

HIMap: HybrId Representation Learning for End-to-end Vectorized HD Map Construction

LTA-PCS: Learnable Task-Agnostic Point Cloud Sampling

Traceable Federated Continual Learning

EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling

Binarized Low-light Raw Video Enhancement

FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio

StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translation

Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generation

Real Acoustic Fields: An Audio-Visual Room Acoustics Dataset and Benchmark

Towards Effective Usage of Human-Centric Priors in Diffusion Models for Text-based Human Image Generation

From SAM to CAMs: Exploring Segment Anything Model for Weakly Supervised Semantic Segmentation

Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding

Hybrid Proposal Refiner: Revisiting DETR Series from the Faster R-CNN Perspective

Referring Expression Counting

Multi-Scale 3D Gaussian Splatting for Anti-Aliased Rendering

HRVDA: High-Resolution Visual Document Assistant

A Dual-Augmentor Framework for Domain Generalization in 3D Human Pose Estimation

Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model

Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models

PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection

Multimodal Sense-Informed Forecasting of 3D Human Motions

Resolution Limit of Single-Photon LiDAR

SinSR: Diffusion-Based Image Super-Resolution in a Single Step

VBench: Comprehensive Benchmark Suite for Video Generative Models

A Study of Dropout-Induced Modality Bias on Robustness to Missing Video Frames for Audio-Visual Speech Recognition

Vlogger: Make Your Dream A Vlog

EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion

SRTube: Video-Language Pre-Training with Action-Centric Video Tube Features and Semantic Role Labeling

Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos

MCPNet: An Interpretable Classifier via Multi-Level Concept Prototypes

Correlation-aware Coarse-to-fine MLPs for Deformable Medical Image Registration

Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives

Tyche: Stochastic In-Context Learning for Medical Image Segmentation

How Far Can We Compress Instant-NGP-Based NeRF?

CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention

LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake Detection

SHiNe: Semantic Hierarchy Nexus for Open-vocabulary Object Detection

IPoD: Implicit Field Learning with Point Diffusion for Generalizable 3D Object Reconstruction from Single RGB-D Images

Normalizing Flows on the Product Space of SO(3) Manifolds for Probabilistic Human Pose Modeling

The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing

Generalized Predictive Model for Autonomous Driving

HAVE-FUN: Human Avatar Reconstruction from Few-Shot Unconstrained Images

LASA: Instance Reconstruction from Real Scans using A Large-scale Aligned Shape Annotation Dataset

PICTURE: PhotorealistIC virtual Try-on from UnconstRained dEsigns

RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D

MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures

GenesisTex: Adapting Image Denoising Diffusion to Texture Space

USE: Universal Segment Embeddings for Open-Vocabulary Image Segmentation

MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding

SVGDreamer: Text Guided SVG Generation with Diffusion Model

Unbiased Faster R-CNN for Single-source Domain Generalized Object Detection

Learning to Remove Wrinkled Transparent Film with Polarized Prior

GeneAvatar: Generic Expression-Aware Volumetric Head Avatar Editing from a Single Image

Adaptive Random Feature Regularization on Fine-tuning Deep Neural Networks

Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement

Generating Enhanced Negatives for Training Language-Based Object Detectors

Joint-Task Regularization for Partially Labeled Multi-Task Learning

Why Not Use Your Textbook? Knowledge-Enhanced Procedure Planning of Instructional Videos

Spatio-Temporal Turbulence Mitigation: A Translational Perspective

Generative Quanta Color Imaging

SI-MIL: Taming Deep MIL for Self-Interpretability in Gigapixel Histopathology

Learned Representation-Guided Diffusion Models for Large-Image Generation

Guided Slot Attention for Unsupervised Video Object Segmentation

Dual Prototype Attention for Unsupervised Video Object Segmentation

R-Cyclic Diffuser: Reductive and Cyclic Latent Diffusion for 3D Clothed Human Digitalization

MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation

HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation

Object Recognition as Next Token Prediction

MuGE: Multiple Granularity Edge Detection

Contrastive Mean-Shift Learning for Generalized Category Discovery

Hunting Attributes: Context Prototype-Aware Learning for Weakly Supervised Semantic Segmentation

Panacea: Panoramic and Controllable Video Generation for Autonomous Driving

Flexible Biometrics Recognition: Bridging the Multimodality Gap through Attention Alignment and Prompt Tuning

SIRA: Scalable Inter-frame Relation and Association for Radar Perception

Large Language Models are Good Prompt Learners for Low-Shot Image Classification

EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentation

Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On

Harnessing the Power of MLLMs for Transferable Text-to-Image Person ReID

Disentangled Pre-training for Human-Object Interaction Detection

Local-consistent Transformation Learning for Rotation-invariant Point Cloud Analysis

Towards Variable and Coordinated Holistic Co-Speech Motion Generation