Improving Weakly Supervised Temporal Action Localization by Exploiting Multi-Resolution Information in Temporal Domain

Weakly supervised temporal action localization is a challenging task as only the video-level annotation is available during the training process. To address this problem, we propose a two-stage approach to generate high-quality frame-level pseudo labels by fully exploiting multi-resolution informati...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 30(2021) vom: 24., Seite 6659-6672
1. Verfasser: Su, Rui (VerfasserIn)
Weitere Verfasser: Xu, Dong, Zhou, Luping, Ouyang, Wanli
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2021
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article