News


24 Nov 2022
One paper is accepted by IEEE TRANSACTIONS ON IMAGE PROCESSING (TIP 2022) on video action recognition.

3 July 2022
One paper is accepted by ACM Multimedia 2022 on video action recognition.

5 July 2021
One paper is accepted by ACM Multimedia 2021 on classifying actions in videos.

YI TAN 

PhD student

School of Information Science and Techonology
University of Science and Technology of China

Email: ty133@mail.ustc.edu.cn

I am a 3rd year PhD student at the USTC, Lab for Data Science , supervised by Prof. Xiangnan He. My research interest lies in video understanding and representation. I have multiple publications that appear in top-tier conferences and journals including ACM MM and IEEE TIP. Moreover, I have served as the reviewer for ACM MM.

Publication


In the Year of 2023:


pdf
Selective Volume Mixup for Video Action Recognition
Yi Tan, Zhaofan Qiu, Yanbin Hao, Ting Yao, Xiangnan He & Tao Mei
In the Year of 2022:


pdf
Spatio-Temporal Collaborative Module for Efficient Action Recognition
Yanbin Hao, Shuo Wang, Yi Tan, Xiangnan He, Zhenguang Liu & Meng Wang
IEEE TRANSACTIONS ON IMAGE PROCESSING (TIP 2022)   

pdf
Hierarchical Hourglass Convolutional Network for Efficient Video Classification
Yi Tan, Yanbin Hao*, Hao Zhang, Shuo Wang & Xiangnan He*
ACM MM 2022 (Full, Accept Rate: 27.9%)    Codes
In the Year of 2021:


pdf
Selective Dependency Aggregation for Action Classification
Yi Tan, Yanbin Hao*, Xiangnan He, Yinwei Wei & Xun Yang
ACM MM 2021 (Full Accept Rate: 28%)    Codes

Experiences

Research interm @JD, supervised by Zhaofan Qiu, Ting Yao & Tao Mei, Dec 2022 - Apr 2023

Education

University of Science and Techonology of China (USTC)
PhD student in Computer Science                   Sep 2020 - Now, Hefei
Advisor: Prof. Xiangnan He
University of Science and Techonology of China (USTC)
Master in Automation      Sep 2018 - June 2020, Hefei
University of Science and Techonology of China (USTC)
Bachelor in Automation      Sep 2014 - June 2018, Hefei

Last update: 3 Jan, 2023. Webpage template borrows from Prof. Xiangnan He.