Yujun Cai

papers

509

total citations

papers (17)

Learning Progressive Joint Propagation for Human Motion Prediction

ECCV 2020

187

citations

Direct Multi-view Multi-person 3D Pose Estimation

NEURIPS 2021arXiv

124

citations

Geometry-Guided Progressive NeRF for Generalizable and Efficient Neural Human Rendering

ECCV 2022arXiv

citations

LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognition

NEURIPS 2023arXiv

citations

Learning Few-Step Diffusion Models by Trajectory Distribution Matching

ICCV 2025arXiv

citations

Texture or Semantics? Vision-Language Models Get Lost in Font Recognition

COLM 2025arXiv

citations

Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models

CVPR 2025arXiv

citations

LatentHOI: On the Generalizable Hand Object Motion Generation with Latent Hand Diffusion.

CVPR 2025

citations

Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models

COLM 2025arXiv

citations

Adaptive Data Augmentation on Temporal Graphs

NEURIPS 2021

citations

A Unified 3D Human Motion Synthesis Model via Conditional Variational Auto-Encoder

ICCV 2021

citations

DeepEMD: Few-Shot Image Classification With Differentiable Earth Mover's Distance and Structured Classifiers

CVPR 2020

citations

A Characteristic Function-Based Method for Bottom-Up Human Pose Estimation

CVPR 2023

citations

Social Diffusion: Long-term Multiple Human Motion Anticipation

ICCV 2023

citations

Yujun Cai

papers (17)

Learning Progressive Joint Propagation for Human Motion Prediction

Direct Multi-view Multi-person 3D Pose Estimation

Geometry-Guided Progressive NeRF for Generalizable and Efficient Neural Human Rendering

LLMs are Good Action Recognizers

6D-Diff: A Keypoint Diffusion Framework for 6D Object Pose Estimation

Heatmap Distribution Matching for Human Pose Estimation

LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognition

Learning Few-Step Diffusion Models by Trajectory Distribution Matching

Texture or Semantics? Vision-Language Models Get Lost in Font Recognition

Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models

LatentHOI: On the Generalizable Hand Object Motion Generation with Latent Hand Diffusion.

Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models

Adaptive Data Augmentation on Temporal Graphs

A Unified 3D Human Motion Synthesis Model via Conditional Variational Auto-Encoder

DeepEMD: Few-Shot Image Classification With Differentiable Earth Mover's Distance and Structured Classifiers

A Characteristic Function-Based Method for Bottom-Up Human Pose Estimation

Social Diffusion: Long-term Multiple Human Motion Anticipation

papers (17)

Learning Progressive Joint Propagation for Human Motion Prediction

Direct Multi-view Multi-person 3D Pose Estimation

Geometry-Guided Progressive NeRF for Generalizable and Efficient Neural Human Rendering

LLMs are Good Action Recognizers

6D-Diff: A Keypoint Diffusion Framework for 6D Object Pose Estimation

Heatmap Distribution Matching for Human Pose Estimation

LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognition

Learning Few-Step Diffusion Models by Trajectory Distribution Matching

Texture or Semantics? Vision-Language Models Get Lost in Font Recognition

Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models

LatentHOI: On the Generalizable Hand Object Motion Generation with Latent Hand Diffusion.

Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models

Adaptive Data Augmentation on Temporal Graphs

A Unified 3D Human Motion Synthesis Model via Conditional Variational Auto-Encoder

DeepEMD: Few-Shot Image Classification With Differentiable Earth Mover's Distance and Structured Classifiers

A Characteristic Function-Based Method for Bottom-Up Human Pose Estimation

Social Diffusion: Long-term Multiple Human Motion Anticipation