LMFT enables state-of-the-art performance in video unsupervised domain adaptation by focusing on motion-rich tokens and reducing computational overhead.
Sefar: Semi-supervised fine- grained action recognition with temporal perturbation and learning stabilization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learnable Motion-Focused Tokenization for Effective and Efficient Video Unsupervised Domain Adaptation
LMFT enables state-of-the-art performance in video unsupervised domain adaptation by focusing on motion-rich tokens and reducing computational overhead.