2 papers
cs.CV2026
Learnable Motion-Focused Tokenization for Effective and Efficient Video Unsupervised Domain Adaptation
Tzu Ling Liu, Ian Stavness, Mrigank Rochan
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 ta…
cs.CV2025
Selective Masking based Self-Supervised Learning for Image Semantic Segmentation
Yuemin Wang, Ian Stavness
This paper proposes a novel self-supervised learning method for semantic segmentation using selective masking image reconstruction as the pretraining task. Our proposed method repl…