Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
FIS-OT: Feature-Induced Optimal Transport for Unsupervised Action Segmentation
Linxiang Peng, Xinyao Qin, Jinhan Li +2
Unsupervised action segmentation is a challenging task. It involves finding action categories and boundaries in videos without labels. Existing Optimal Transport (OT) methods use g…
cs.CV2026
MASQ: Mask-Aware Spatiotemporal Quantization for Unsupervised Skeleton Action Segmentation
Xinyao Qin, Linxiang Peng, Youbao Ye +2
Unsupervised skeleton-based temporal action segmentation is a crucial task for understanding human behavior in long untrimmed sequences. Recent approaches often rely on discrete qu…