Guangyi Chen

papers

2,182

total citations

papers (23)

DenseCLIP: Language-Guided Dense Prediction With Context-Aware Prompting

CVPR 2022arXiv

736

citations

Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion

CVPR 2022arXiv

323

citations

Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-Identification

ICCV 2021arXiv

312

citations

FineDiving: A Fine-Grained Dataset for Procedure-Aware Action Quality Assessment

CVPR 2022arXiv

146

citations

PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery

CVPR 2023arXiv

106

citations

Human Trajectory Prediction via Counterfactual Analysis

ICCV 2021arXiv

citations

Temporal Coherence or Temporal Motion: Which is More Critical for Video-based Person Re-identification?

ECCV 2020

citations

CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process

ICML 2024arXiv

citations

SmartCLIP: Modular Vision-language Alignment with Identification Guarantees

CVPR 2025arXiv

citations

Learning Causal Domain-Invariant Temporal Dynamics for Few-Shot Action Recognition

ICML 2024arXiv

citations

Identification of Intermittent Temporal Latent Process

ICLR 2025

citations

BCDiff: Bidirectional Consistent Diffusion for Instantaneous Trajectory Prediction

NEURIPS 2023

citations

S3A: Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment

AAAI 2024

citations

Deep Credible Metric Learning for Unsupervised Domain Adaptation Person Re-identification

ECCV 2020

citations

Guangyi Chen

papers (23)

DenseCLIP: Language-Guided Dense Prediction With Context-Aware Prompting

Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion

Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-Identification

FineDiving: A Fine-Grained Dataset for Procedure-Aware Action Quality Assessment

PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery

Human Trajectory Prediction via Counterfactual Analysis

Temporal Coherence or Temporal Motion: Which is More Critical for Video-based Person Re-identification?

Temporally Disentangled Representation Learning

Personalized Trajectory Prediction via Distribution Discrimination

Subspace Identification for Multi-Source Domain Adaptation

Understanding Masked Autoencoders via Hierarchical Latent Variable Models

Unsupervised Sampling Promoting for Stochastic Human Trajectory Prediction

Tem-Adapter: Adapting Image-Text Pretraining for Video Question Answer

Efficient Inference of Vision Instruction-Following Models with Elastic Cache

Temporally Disentangled Representation Learning under Unknown Nonstationarity

Narrative Action Evaluation with Prompt-Guided Multimodal Interaction

CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process

SmartCLIP: Modular Vision-language Alignment with Identification Guarantees

Learning Causal Domain-Invariant Temporal Dynamics for Few-Shot Action Recognition

Identification of Intermittent Temporal Latent Process

BCDiff: Bidirectional Consistent Diffusion for Instantaneous Trajectory Prediction

S3A: Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment

Deep Credible Metric Learning for Unsupervised Domain Adaptation Person Re-identification

papers (23)

DenseCLIP: Language-Guided Dense Prediction With Context-Aware Prompting

Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion

Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-Identification

FineDiving: A Fine-Grained Dataset for Procedure-Aware Action Quality Assessment

PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery

Human Trajectory Prediction via Counterfactual Analysis

Temporal Coherence or Temporal Motion: Which is More Critical for Video-based Person Re-identification?

Temporally Disentangled Representation Learning

Personalized Trajectory Prediction via Distribution Discrimination

Subspace Identification for Multi-Source Domain Adaptation

Understanding Masked Autoencoders via Hierarchical Latent Variable Models

Unsupervised Sampling Promoting for Stochastic Human Trajectory Prediction

Tem-Adapter: Adapting Image-Text Pretraining for Video Question Answer

Efficient Inference of Vision Instruction-Following Models with Elastic Cache

Temporally Disentangled Representation Learning under Unknown Nonstationarity

Narrative Action Evaluation with Prompt-Guided Multimodal Interaction

CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process

SmartCLIP: Modular Vision-language Alignment with Identification Guarantees

Learning Causal Domain-Invariant Temporal Dynamics for Few-Shot Action Recognition

Identification of Intermittent Temporal Latent Process

BCDiff: Bidirectional Consistent Diffusion for Instantaneous Trajectory Prediction

S3A: Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment

Deep Credible Metric Learning for Unsupervised Domain Adaptation Person Re-identification