Picture for Chang Wen Chen

Chang Wen Chen

VideoMind: A Chain-of-LoRA Agent for Long Video Reasoning

Add code
Mar 17, 2025
Viaarxiv icon

FedPCA: Noise-Robust Fair Federated Learning via Performance-Capacity Analysis

Add code
Mar 13, 2025
Viaarxiv icon

What Makes a Scene ? Scene Graph-based Evaluation and Feedback for Controllable Generation

Add code
Nov 23, 2024
Figure 1 for What Makes a Scene ? Scene Graph-based Evaluation and Feedback for Controllable Generation
Figure 2 for What Makes a Scene ? Scene Graph-based Evaluation and Feedback for Controllable Generation
Figure 3 for What Makes a Scene ? Scene Graph-based Evaluation and Feedback for Controllable Generation
Figure 4 for What Makes a Scene ? Scene Graph-based Evaluation and Feedback for Controllable Generation
Viaarxiv icon

E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding

Add code
Sep 26, 2024
Figure 1 for E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding
Figure 2 for E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding
Figure 3 for E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding
Figure 4 for E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding
Viaarxiv icon

Exploring Rich Subjective Quality Information for Image Quality Assessment in the Wild

Add code
Sep 09, 2024
Figure 1 for Exploring Rich Subjective Quality Information for Image Quality Assessment in the Wild
Figure 2 for Exploring Rich Subjective Quality Information for Image Quality Assessment in the Wild
Figure 3 for Exploring Rich Subjective Quality Information for Image Quality Assessment in the Wild
Figure 4 for Exploring Rich Subjective Quality Information for Image Quality Assessment in the Wild
Viaarxiv icon

Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval

Add code
Jul 23, 2024
Figure 1 for Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval
Figure 2 for Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval
Figure 3 for Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval
Figure 4 for Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval
Viaarxiv icon

PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLM

Add code
Jun 05, 2024
Viaarxiv icon

$R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding

Add code
Mar 31, 2024
Viaarxiv icon

SubjectDrive: Scaling Generative Data in Autonomous Driving via Subject Control

Add code
Mar 28, 2024
Figure 1 for SubjectDrive: Scaling Generative Data in Autonomous Driving via Subject Control
Figure 2 for SubjectDrive: Scaling Generative Data in Autonomous Driving via Subject Control
Figure 3 for SubjectDrive: Scaling Generative Data in Autonomous Driving via Subject Control
Figure 4 for SubjectDrive: Scaling Generative Data in Autonomous Driving via Subject Control
Viaarxiv icon

SD-DiT: Unleashing the Power of Self-supervised Discrimination in Diffusion Transformer

Add code
Mar 25, 2024
Viaarxiv icon