Date of Award

8-1-2021

Language

English

Document Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

College/School/Department

Department of Computer Science

Content Description

1 online resource (xi, 92 pages) : color illustrations.

Dissertation/Thesis Chair

Ming-Ching Chang

Committee Members

Siwei Lyu, Yiming Ying, Shaghayegh Sahebi

Keywords

Activity recognition, Concurrent activity detection, Group activity recognition, Video understanding, Neural networks (Computer science), Computer vision, Image processing, Optical pattern recognition, Pattern recognition systems

Subject Categories

Computer Sciences

Abstract

Human activity understanding, as one of the most important task in video analysis, has been studied for decades. Great efforts have been made to push the activity recognition models towards effective and efficient representation learning. However, it is difficult to define an explicit semantic organization of activities, even for human. Current activity recognition benchmarks only organize the activity labels with shallow hierarchies, which hinders the development of activity recognition system.

Share

COinS