Wei Zhai

papers

745

total citations

papers (22)

Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning

CVPR 2021arXiv

182

citations

Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning

CVPR 2022arXiv

175

citations

Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection

CVPR 2023arXiv

citations

Improved Video VAE for Latent Video Diffusion Model

CVPR 2025arXiv

citations

Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning

CVPR 2025arXiv

citations

Spatial-Aware Token for Weakly Supervised Object Localization

ICCV 2023arXiv

citations

MMAR: Towards Lossless Multi-Modal Auto-Regressive Probabilistic Modeling

CVPR 2025arXiv

citations

GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding

CVPR 2025arXiv

citations

SIGMAN: Scaling 3D Human Gaussian Generation with Millions of Assets

ICCV 2025

citations

Bidirectional Progressive Transformer for Interaction Intention Anticipation

ECCV 2024arXiv

citations

HERO: Human Reaction Generation from Videos

ICCV 2025arXiv

citations

Hypercorrelation Evolution for Video Class-Incremental Learning

AAAI 2024

citations

Efficient Test-time Adaptive Object Detection via Sensitivity-Guided Pruning

CVPR 2025arXiv

citations

Exploring Figure-Ground Assignment Mechanism in Perceptual Organization

NEURIPS 2022

citations

Deep Structure-Revealed Network for Texture Recognition

CVPR 2020

citations

Leverage Interactive Affinity for Affordance Learning

CVPR 2023

citations

EMoTive: Event-guided Trajectory Modeling for 3D Motion Estimation

ICCV 2025arXiv

citations

MATE: Motion-Augmented Temporal Consistency for Event-based Point Tracking

ICCV 2025arXiv

citations

Wei Zhai

papers (22)

Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning

Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning

Learning Affordance Grounding From Exocentric Images

Background Activation Suppression for Weakly Supervised Object Localization

Grounding 3D Object Affordance from 2D Interactions in Images

LEMON: Learning 3D Human-Object Interaction Relation from 2D Images

Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection

Improved Video VAE for Latent Video Diffusion Model

Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning

Spatial-Aware Token for Weakly Supervised Object Localization

MMAR: Towards Lossless Multi-Modal Auto-Regressive Probabilistic Modeling

GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding

SIGMAN: Scaling 3D Human Gaussian Generation with Millions of Assets

Bidirectional Progressive Transformer for Interaction Intention Anticipation

HERO: Human Reaction Generation from Videos

Hypercorrelation Evolution for Video Class-Incremental Learning

Efficient Test-time Adaptive Object Detection via Sensitivity-Guided Pruning

Exploring Figure-Ground Assignment Mechanism in Perceptual Organization

Deep Structure-Revealed Network for Texture Recognition

Leverage Interactive Affinity for Affordance Learning

EMoTive: Event-guided Trajectory Modeling for 3D Motion Estimation

MATE: Motion-Augmented Temporal Consistency for Event-based Point Tracking

papers (22)

Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning

Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning

Learning Affordance Grounding From Exocentric Images

Background Activation Suppression for Weakly Supervised Object Localization

Grounding 3D Object Affordance from 2D Interactions in Images

LEMON: Learning 3D Human-Object Interaction Relation from 2D Images

Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection

Improved Video VAE for Latent Video Diffusion Model

Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning

Spatial-Aware Token for Weakly Supervised Object Localization

MMAR: Towards Lossless Multi-Modal Auto-Regressive Probabilistic Modeling

GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding

SIGMAN: Scaling 3D Human Gaussian Generation with Millions of Assets

Bidirectional Progressive Transformer for Interaction Intention Anticipation

HERO: Human Reaction Generation from Videos

Hypercorrelation Evolution for Video Class-Incremental Learning

Efficient Test-time Adaptive Object Detection via Sensitivity-Guided Pruning

Exploring Figure-Ground Assignment Mechanism in Perceptual Organization

Deep Structure-Revealed Network for Texture Recognition

Leverage Interactive Affinity for Affordance Learning

EMoTive: Event-guided Trajectory Modeling for 3D Motion Estimation

MATE: Motion-Augmented Temporal Consistency for Event-based Point Tracking