Kecheng Zheng

papers

1,116

total citations

papers (26)

Group-aware Label Transfer for Domain Adaptive Person Re-identification

CVPR 2021arXiv

191

citations

Cloth-Changing Person Re-Identification From a Single Image With Gait Prediction and Regularization

CVPR 2022arXiv

172

citations

Paying More Attention to Images: A Training-Free Method for Alleviating Hallucination in LVLMs

ECCV 2024arXiv

134

citations

CoDeF: Content Deformation Fields for Temporally Consistent Video Processing

CVPR 2024arXiv

120

citations

Customizable Image Synthesis with Multiple Subjects

NEURIPS 2023arXiv

110

citations

Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videos

CVPR 2021arXiv

citations

Language-Image Pre-training with Long Captions

ECCV 2024arXiv

citations

Animate-X: Universal Character Image Animation with Enhanced Motion Representation

ICLR 2025arXiv

citations

Rank Diminishing in Deep Neural Networks

NEURIPS 2022arXiv

citations

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

CVPR 2023arXiv

citations

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

CVPR 2025arXiv

citations

MotionStone: Decoupled Motion Intensity Modulation with Diffusion Transformer for Image-to-Video Generation

CVPR 2025arXiv

citations

Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-Trained Vision-Language Models

ICCV 2023arXiv

citations

Aligned Better, Listen Better for Audio-Visual Large Language Models

ICLR 2025arXiv

citations

Contextual AD Narration with Interleaved Multimodal Sequence

CVPR 2025arXiv

citations

Benchmarking and Analyzing 3D-aware Image Synthesis with a Modularized Codebase

NEURIPS 2023arXiv

citations

Learning Visual Generative Priors without Text

CVPR 2025arXiv

citations

Neural Dependencies Emerging From Learning Massive Categories

CVPR 2023arXiv

citations

Uncertainty-Aware Hierarchical Refinement for Incremental Implicitly-Refined Classification

NEURIPS 2022

citations

Temporal Complementarity-Guided Reinforcement Learning for Image-to-Video Person Re-Identification

CVPR 2022

citations

Unleashing Potential of Unsupervised Pre-Training With Intra-Identity Regularization for Person Re-Identification

CVPR 2022

citations

Self-Organizing Pathway Expansion for Non-Exemplar Class-Incremental Learning

ICCV 2023

citations

CrossMAE: Cross-Modality Masked Autoencoders for Region-Aware Audio-Visual Pre-Training

CVPR 2024

citations

Kecheng Zheng

papers (26)

Group-aware Label Transfer for Domain Adaptive Person Re-identification

Cloth-Changing Person Re-Identification From a Single Image With Gait Prediction and Regularization

Paying More Attention to Images: A Training-Free Method for Alleviating Hallucination in LVLMs

CoDeF: Content Deformation Fields for Temporally Consistent Video Processing

Customizable Image Synthesis with Multiple Subjects

Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videos

Language-Image Pre-training with Long Captions

Animate-X: Universal Character Image Animation with Enhanced Motion Representation

Rank Diminishing in Deep Neural Networks

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

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

Framer: Interactive Frame Interpolation

Mimir: Improving Video Diffusion Models for Precise Text Understanding

Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis

MotionStone: Decoupled Motion Intensity Modulation with Diffusion Transformer for Image-to-Video Generation

Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-Trained Vision-Language Models

Aligned Better, Listen Better for Audio-Visual Large Language Models

Contextual AD Narration with Interleaved Multimodal Sequence

Benchmarking and Analyzing 3D-aware Image Synthesis with a Modularized Codebase

Learning Visual Generative Priors without Text

Neural Dependencies Emerging From Learning Massive Categories

Uncertainty-Aware Hierarchical Refinement for Incremental Implicitly-Refined Classification

Temporal Complementarity-Guided Reinforcement Learning for Image-to-Video Person Re-Identification

Unleashing Potential of Unsupervised Pre-Training With Intra-Identity Regularization for Person Re-Identification

Self-Organizing Pathway Expansion for Non-Exemplar Class-Incremental Learning

CrossMAE: Cross-Modality Masked Autoencoders for Region-Aware Audio-Visual Pre-Training

papers (26)

Group-aware Label Transfer for Domain Adaptive Person Re-identification

Cloth-Changing Person Re-Identification From a Single Image With Gait Prediction and Regularization

Paying More Attention to Images: A Training-Free Method for Alleviating Hallucination in LVLMs

CoDeF: Content Deformation Fields for Temporally Consistent Video Processing

Customizable Image Synthesis with Multiple Subjects

Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videos

Language-Image Pre-training with Long Captions

Animate-X: Universal Character Image Animation with Enhanced Motion Representation

Rank Diminishing in Deep Neural Networks

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

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

Framer: Interactive Frame Interpolation

Mimir: Improving Video Diffusion Models for Precise Text Understanding

Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis

MotionStone: Decoupled Motion Intensity Modulation with Diffusion Transformer for Image-to-Video Generation

Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-Trained Vision-Language Models

Aligned Better, Listen Better for Audio-Visual Large Language Models

Contextual AD Narration with Interleaved Multimodal Sequence

Benchmarking and Analyzing 3D-aware Image Synthesis with a Modularized Codebase

Learning Visual Generative Priors without Text

Neural Dependencies Emerging From Learning Massive Categories

Uncertainty-Aware Hierarchical Refinement for Incremental Implicitly-Refined Classification

Temporal Complementarity-Guided Reinforcement Learning for Image-to-Video Person Re-Identification

Unleashing Potential of Unsupervised Pre-Training With Intra-Identity Regularization for Person Re-Identification

Self-Organizing Pathway Expansion for Non-Exemplar Class-Incremental Learning

CrossMAE: Cross-Modality Masked Autoencoders for Region-Aware Audio-Visual Pre-Training