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...

Celý popis

Podrobná bibliografie

Vydáno v:	Computer vision and image understanding Ročník 219; s. 103406
Hlavní autoři:	Dave, Ishan, Gupta, Rohit, Rizve, Mamshad Nayeem, Shah, Mubarak
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier Inc 01.06.2022
Témata:	Action Recognition Self-Supervised Learning Video Representation 68T45 68T07 Action Recognition 68T30 Self-Supervised Learning Video Representation
ISSN:	1077-3142, 1090-235X
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!