Object-centric Video Representation for Action Prediction

Abstract

Patent application for object-centric video representations used in action prediction.

Type
Publication
US Patent Application 18/539,590
Changcheng Fu
Changcheng Fu
Ph.D. Student in Computer Science at University of Southern California

Hi, I’m Changcheng, a Ph.D. student in Computer Science at the University of Southern California, advised by Prof. Ram Nevatia. My research focuses on computer vision, deep learning, machine learning, and multimodal large language models for visual understanding and long-term action anticipation.