Background-Aware Robust Context Learning for Weakly-Supervised Temporal Action Localization

Background-Aware Robust Context Learning for Weakly-Supervised Temporal Action Localization

Weakly supervised temporal action localization (WTAL) aims to localize temporal intervals of actions in an untrimmed video using only video-level action labels. Although the learning of the background is an important issue in WTAL, most previous studies have not utilized an effective background. In...

Full description

Bibliographic Details
Main Authors: Jinah Kim, Jungchan Cho
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Temporal action localization
entropy maximization
context learning
feature adaptation
Online Access:https://ieeexplore.ieee.org/document/9797701/

Similar Items

Similar Items