no code implementations • 30 Nov 2023 • Kyungho Bae, Geo Ahn, Youngrae Kim, Jinwoo Choi
Disentangled action and scene representations could be beneficial for both in-context and out-of-context video understanding.
2 code implementations • 21 Nov 2023 • Hyogun Lee, Kyungho Bae, Seong Jong Ha, Yumin Ko, Gyeong-Moon Park, Jinwoo Choi
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.