Bridging Distributional Discrepancy with Temporal Dynamics for Video Understanding

Abstract

Video has become one of the major media in our society, bringing considerable interests in the development of video analysis techniques for various applications. Temporal Dynamic, which represents how information changes along time, is the key component for videos. However, it is still not clear how temporal dynamics benefit video tasks, especially for the cross-domain case, which is close to real-world scenarios. In this talk, I will share my Ph.D. work which effectively exploits temporal dynamics from videos to tackle distributional discrepancy problems for video understanding.

Date
May 3, 2021 2:00 PM — 4:00 PM
Event
Invited talk by Dr. Jun-Cheng Chen at Academia Sinica
Location
Auditorium 122 at CITI
Taipei City, Taiwan

Feel free to click the upper button Slides to check the full talk slides.
Note: This talk was invited by Dr. Jun-Cheng Chen.

Min-Hung Chen
Min-Hung Chen
Senior Research Scientist

My research interest is Learning without Fully Supervision.

Related