https://github.com/ncsoft/glad
Official implementation of "GLAD: Global-Local View Alignment and Background Debiasing for Unsupervised Video Domain Adaptation with Large Domain Gap" (WACV 2024)
https://github.com/ncsoft/glad
Last synced: 4 months ago
JSON representation
Official implementation of "GLAD: Global-Local View Alignment and Background Debiasing for Unsupervised Video Domain Adaptation with Large Domain Gap" (WACV 2024)
- Host: GitHub
- URL: https://github.com/ncsoft/glad
- Owner: ncsoft
- License: other
- Created: 2024-01-30T04:00:09.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2024-02-06T00:40:55.000Z (over 2 years ago)
- Last Synced: 2025-01-12T20:12:44.015Z (over 1 year ago)
- Homepage:
- Size: 2.93 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE.md
Awesome Lists containing this project
README
# 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.
URL: https://github.com/KHU-VLL/GLAD