Hong Chang

papers

2,116

total citations

papers (18)

Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework

ECCV 2022arXiv

775

citations

BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification

CVPR 2021arXiv

106

citations

Diversity-Measurable Anomaly Detection

CVPR 2023arXiv

104

citations

UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing

CVPR 2025arXiv

citations

Generalized Semi-Supervised Learning via Self-Supervised Feature Adaptation

NEURIPS 2023arXiv

citations

Morph: A Motion-free Physics Optimization Framework for Human Motion Generation

ICCV 2025arXiv

citations

HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding

ICCV 2025arXiv

citations

un$^2$CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP

NEURIPS 2025arXiv

citations

G2PDiffusion: Cross-species Genotype-to-Phenotype Prediction via Evolutionary Diffusion

ICCV 2025arXiv

citations

An Information Theoretical View for Out-Of-Distribution Detection

ECCV 2024

citations

Optimal Positive Generation via Latent Transformation for Contrastive Learning

NEURIPS 2022

citations

Salient-to-Broad Transition for Video Person Re-Identification

CVPR 2022

citations

Understanding Few-Shot Learning: Measuring Task Relatedness and Adaptation Difficulty via Attributes

NEURIPS 2023

citations

TCTS: A Task-Consistent Two-Stage Framework for Person Search

CVPR 2020

citations

Hong Chang

papers (18)

Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework

Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training

Clothes-Changing Person Re-Identification With RGB Modality Only

Appearance-Preserving 3D Convolution for Video-based Person Re-identification

Temporal Complementary Learning for Video Person Re-Identification

BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification

Diversity-Measurable Anomaly Detection

UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing

Generalized Semi-Supervised Learning via Self-Supervised Feature Adaptation

Morph: A Motion-free Physics Optimization Framework for Human Motion Generation

HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding

un$^2$CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP

G2PDiffusion: Cross-species Genotype-to-Phenotype Prediction via Evolutionary Diffusion

An Information Theoretical View for Out-Of-Distribution Detection

Optimal Positive Generation via Latent Transformation for Contrastive Learning

Salient-to-Broad Transition for Video Person Re-Identification

Understanding Few-Shot Learning: Measuring Task Relatedness and Adaptation Difficulty via Attributes

TCTS: A Task-Consistent Two-Stage Framework for Person Search

papers (18)

Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework

Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training

Clothes-Changing Person Re-Identification With RGB Modality Only

Appearance-Preserving 3D Convolution for Video-based Person Re-identification

Temporal Complementary Learning for Video Person Re-Identification

BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification

Diversity-Measurable Anomaly Detection

UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing

Generalized Semi-Supervised Learning via Self-Supervised Feature Adaptation

Morph: A Motion-free Physics Optimization Framework for Human Motion Generation

HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding

un$^2$CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP

G2PDiffusion: Cross-species Genotype-to-Phenotype Prediction via Evolutionary Diffusion

An Information Theoretical View for Out-Of-Distribution Detection

Optimal Positive Generation via Latent Transformation for Contrastive Learning

Salient-to-Broad Transition for Video Person Re-Identification

Understanding Few-Shot Learning: Measuring Task Relatedness and Adaptation Difficulty via Attributes

TCTS: A Task-Consistent Two-Stage Framework for Person Search