Active Temporal Action Detection in Untrimmed Videos Via Deep Reinforcement Learning

Active Temporal Action Detection in Untrimmed Videos Via Deep Reinforcement Learning

Existing action detection algorithms usually generate action proposals through an extensive search over the video at multiple temporal scales, which brings about huge computational overhead and deviates from the human perception procedure. We argue that the process of detecting actions in the video...

Full description

Bibliographic Details
Main Authors: Nannan Li, Hui-Wen Guo, Yang Zhao, Thomas Li, Ge Li
Format: Article
Language:English
Published: IEEE 2018-01-01
Series:IEEE Access
Subjects:
Video analysis
temporal action detection
deep reinforcement learning
deep learning
self adaptive
Online Access:https://ieeexplore.ieee.org/document/8476583/

Internet

https://ieeexplore.ieee.org/document/8476583/

Similar Items