Lena Gorelick1, Moshe Blank, Eli Shechtman
1Department of Computer Science and Applied Mathematics, The Weizmann Institute of Science, Israel. lena.gorelick@weizmann.ac.il
You might also read
Articles linked to this work by shared authors, journal, and citation graph.
This study introduces a novel method for analyzing human actions in videos by treating them as 3D space-time shapes. The approach effectively extracts features for robust action recognition, detection, and clustering, even with challenging video conditions.
Area of Science:
Background:
Purpose of the Study:
Main Methods:
Main Results:
Conclusions: