TCLR: Temporal contrastive learning for video representation

Contrastive learning has nearly closed the gap between supervised and self-supervised learning of image representations, and has also been explored for videos. However, prior work on contrastive learning for video data has not explored the effect of explicitly encouraging the features to be distinct...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Computer vision and image understanding Jg. 219; S. 103406
Hauptverfasser:	Dave, Ishan, Gupta, Rohit, Rizve, Mamshad Nayeem, Shah, Mubarak
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier Inc 01.06.2022
Schlagworte:	Action Recognition Self-Supervised Learning Video Representation 68T45 68T07 Action Recognition 68T30 Self-Supervised Learning Video Representation
ISSN:	1077-3142, 1090-235X
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!