Hi, I’m Jinlin Wu (吴锦林)

I am an Assistant Professor at the Institute of Automation, Chinese Academy of Sciences (CASIA) and CAIR, HKISI, CAS. I received my Ph.D. from the University of Chinese Academy of Sciences in 2022, and my B.E. degree from the University of Electronic Science and Technology of China (UESTC) in 2017.

Video Understanding Surgical Video Understanding Scene Understanding Video Multimodal Agents

I am currently the Principal Investigator of a National Natural Science Foundation of China (NSFC) Youth Science Fund project. Specifically, I have presided over one NSFC project and participated as a core member in multiple other NSFC-funded projects.

I serve as a reviewer for top international conferences and journals including CVPR, ECCV, ICCV, NeurIPS, TIP, and TIFS. I am also an organizer of the CREATE Workshop at MICCAI 2023, 2024, and 2025.

60+

Publications

1,100+

Citations

🏆

ECCV 2024 Best Paper Nominee

📰 News

Apr 2026 🏫 We are co-organizing the Medical Augmented Reality Summer School 2026 in Shenzhen, China!

Feb 2026 🎉 3 papers accepted by CVPR 2026!

Jan 2026 🎉 2 papers accepted by AAAI 2026!

Jan 2026 📄 Paper "Procedure-Aware Hierarchical Alignment for Open Surgery Video-Language Pretraining" accepted by IEEE Trans. Image Process. (TIP, CCF-A, IF=13.7)!

Jul 2025 🎉 2 papers accepted by MICCAI 2025!

Oct 2025 🎤 We organized the CREATE Workshop at MICCAI 2025 in Daejeon, South Korea! [News]

Nov 2024 🏆 Our paper "Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and Retention" is nominated for ECCV 2024 Best Paper Award! Congrats to Zuyao Chen!

🎓 Join Us

🔬 Positions Available

I am actively recruiting interns and research assistants (RAs) in the following directions:

🎬 Video-Language Models 🤖 Video Agents 🏥 Medical Video Understanding

📍 Interns can be based in Beijing or Hong Kong.
If you are passionate about cutting-edge video AI research, feel free to drop me an email!