AI RESEARCH
Boundary-Centric Active Learning for Temporal Action Segmentation
arXiv CS.CV
•
ArXi:2604.15173v1 Announce Type: new Temporal action segmentation (TAS) demands dense temporal supervision, yet most of the annotation cost in untrimmed videos is spent identifying and refining action transitions, where segmentation errors concentrate and small temporal shifts disproportionately degrade segmental metrics. We