👋About me.

Curriculum Vitae • Zhihu • Gmail • Email@edu

😄 I’m a First-Year Ph.D at KDD Lab at Arizona State University, supervised by professor Yanjie Fu. I got my Master’s Degree from ShanghaiTech University, where I worked in SVIP-Lab supervised by professor Shenghua Gao. Before these, I received my Bachelor’s degree in 2020 from Dalian University of Technology. My research interests lie in video understanding and weakly supervised learning, including human activity recognition and video representation learning. I am also focusing on multi-modal learning. More detail please refer to my CV.

🎉 News:

• 2024-02-17: A paper about multimodal large language model for tool agent. Code and dataset has been released.
• 2023-02-28: A paper about weakly supervised video representation learning was accepted as CVPR 2023.
• 2022-03-28: A paper about repetition action counting was accepted as CVPR 2022 Oral.

📄 Selected Publications:

• (CVPR2023) Weakly Supervised Video Representation Learning with Unaligned Text for Sequential Videos. [paper][code]

• (CVPR2022 Oral) TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Counting [paper] [code][dataset][Youtube][Bilibili]

👯 I’m looking to inject some fun and creativity into my work week, and I’m guessing you are too. If you’re keen to join forces and make something awesome happen, shoot me a message and let’s make it a reality!

📧 Reach me: ironieser@gmail.com, sdong46@asu.edu