-
π My research focuses on visual representation learning for video analysis, such as action recognition and action localization.
-
π± Currently, working on semi-supervised and self-supervised multi-modal feature learning for video understanding.
-
π― Iβm looking to collaborate on Data-Driven Representation Learning for multimodal data processing.
endarzboy Goto Github PK
Name: Endarz
Type: User
Company: University of Electronic Science and Technology of China
Bio: Ph.D candidate at UESTC
Location: Chengdu, China