GLAD: Global-Local View Alignment and Background Debiasing for Unsupervised Video Domain Adaptation with Large Domain Gap [WACV 2024]
In this work, we tackle the challenging problem of unsupervised video domain adaptation (UVDA) for action recognition. We specifically focus on scenarios with a substantial domain gap, in contrast to existing works primarily deal with small domain gaps between labeled source domains and unlabeled target domains.
This opensource is a collaboration between NCSOFT and Kyung Hee University. Additional information about the dataset can be found at the URL below.