- MovieCORE: COgnitive REasoning in Movies (EMNLP 2025)
- HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics (ICCV 2025)
- Bridging Episodes and Semantics: A Novel Framework for Long-Form Video Understanding (ECCVW 2024)
- MovieCORE: COgnitive REasoning in Movies (NeurIPS-W 2024)
- Holistic interaction transformer network for action detection (WACV 2023)
Reviewer for ICLR 2026 and CVPR 2026.
Research Experience
Currently a Software Engineer at Google and a Ph.D. Student in Computer Science at National Taiwan University. Previously, a Senior Computer Vision Engineer at HTC.
Education
Ph.D. in Computer Science from National Taiwan University, advised by Prof. Winston Hsu; Master's Degree in Computer Science from National Tsing Hua University; Bachelor's Degree in Computer Science from National Yang Ming Chiao Tung University.
Background
Research Interests: Teaching AI systems to see and understand human actions in videos. Work: Building AI systems that understand human movements, poses, and interactions.