Time-Equivariant Contrastive Video Representation Learning
Simon Jenni Hailin Jin
Adobe Research
{jenni,hljin}@adobe.com
Abstract
We introduce a novel self-supervised contrastive learn-
ing method to learn representations from unlabelled videos.
Existing approaches ignore the specifics of input distor-
tions, e.g., by learning invariance to temporal transforma-
tions. Instead, we argue that video represent ...


雷达卡




京公网安备 11010802022788号







