Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Tzu Ling, Stavness, Ian, Rochan, Mrigank
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2604.09955
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914464845004800
author Liu, Tzu Ling
Stavness, Ian
Rochan, Mrigank
author_facet Liu, Tzu Ling
Stavness, Ian
Rochan, Mrigank
contents Video Unsupervised Domain Adaptation (VUDA) poses a significant challenge in action recognition, requiring the adaptation of a model from a labeled source domain to an unlabeled target domain. Despite recent advances, existing VUDA methods often fall short of fully supervised performance, a key reason being the prevalence of static and uninformative backgrounds that exacerbate domain shifts. Additionally, prior approaches largely overlook computational efficiency, limiting real-world adoption. To address these issues, we propose Learnable Motion-Focused Tokenization (LMFT) for VUDA. LMFT tokenizes video frames into patch tokens and learns to discard low-motion, redundant tokens, primarily corresponding to background regions, while retaining motion-rich, action-relevant tokens for adaptation. Extensive experiments on three standard VUDA benchmarks across 21 domain adaptation settings show that our VUDA framework with LMFT achieves state-of-the-art performance while significantly reducing computational overhead. LMFT thus enables VUDA that is both effective and computationally efficient.
format Preprint
id arxiv_https___arxiv_org_abs_2604_09955
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learnable Motion-Focused Tokenization for Effective and Efficient Video Unsupervised Domain Adaptation
Liu, Tzu Ling
Stavness, Ian
Rochan, Mrigank
Computer Vision and Pattern Recognition
Video Unsupervised Domain Adaptation (VUDA) poses a significant challenge in action recognition, requiring the adaptation of a model from a labeled source domain to an unlabeled target domain. Despite recent advances, existing VUDA methods often fall short of fully supervised performance, a key reason being the prevalence of static and uninformative backgrounds that exacerbate domain shifts. Additionally, prior approaches largely overlook computational efficiency, limiting real-world adoption. To address these issues, we propose Learnable Motion-Focused Tokenization (LMFT) for VUDA. LMFT tokenizes video frames into patch tokens and learns to discard low-motion, redundant tokens, primarily corresponding to background regions, while retaining motion-rich, action-relevant tokens for adaptation. Extensive experiments on three standard VUDA benchmarks across 21 domain adaptation settings show that our VUDA framework with LMFT achieves state-of-the-art performance while significantly reducing computational overhead. LMFT thus enables VUDA that is both effective and computationally efficient.
title Learnable Motion-Focused Tokenization for Effective and Efficient Video Unsupervised Domain Adaptation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.09955