Showing cs.CVShow all
3 papers · 1 filter
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
Test-Time Adaptation for Video Highlight Detection Using Meta-Auxiliary Learning and Cross-Modality Hallucinations
Zahidul Islam, Sujoy Paul, Mrigank Rochan
Existing video highlight detection methods, although advanced, struggle to generalize well to all test videos. These methods typically employ a generic highlight detection model fo…
cs.CV2025
Unsupervised Video Highlight Detection by Learning from Audio and Visual Recurrence
Zahidul Islam, Sujoy Paul, Mrigank Rochan
With the exponential growth of video content, the need for automated video highlight detection to extract key moments or highlights from lengthy videos has become increasingly pres…