TCLR: Temporal contrastive learning for video representation

• Published in: Computer vision and image understanding Vol. 219; p. 103406
• Main Authors: Dave, Ishan, Gupta, Rohit, Rizve, Mamshad Nayeem, Shah, Mubarak
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.06.2022
• Subjects: Action Recognition; Self-Supervised Learning; Video Representation; 68T45; 68T07; Action Recognition; 68T30; Self-Supervised Learning; 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...