Long Short View Feature Decomposition via Contrastive Video Representation
Learning
Nadine Behrmann1 Mohsen Fayyaz2, Juergen Gall2 Mehdi Noroozi1
1 2
Bosch Center for Artificial Intelligence University of Bonn
{nadine.behrmann, mehdi.noroozi}@de.bosch.com, {fayyaz, gall}@iai.uni-bonn.de
Abstract
Self-supervised video representation methods typically
focus on the representation of temporal ...


雷达卡




京公网安备 11010802022788号







