Action Recognition
Yu Kong⁎; Yun Fu† ⁎B. Thomas Golisano College of Computing and Information Sciences, Rochester Institute of Technology, Rochester, NY, United States†Department of Electrical and Computer Engineering and College of Computer and Information Science (Affiliated), Northeastern University, Boston, MA, United States
Abstract
Appearance and pose of human actions vary significantly in different views, making multiview action recognition a very challenging task. To address this problem, it is crucial to learn view-invariant features from multiview action data that are robust to view variations. In this chapter, we first describe an approach by using deep learning networks to learn view-specific and view-shared ...
Get Deep Learning through Sparse and Low-Rank Modeling now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
