AI RESEARCH
Improving Temporal Action Segmentation via Constraint-Aware Decoding
arXiv CS.CV
•
ArXi:2605.10149v1 Announce Type: new Temporal action segmentation (TAS) divides untrimmed videos into labeled action segments. While fully supervised methods have advanced the field, challenges such as action variability, ambiguous boundaries, and high annotation costs remain, especially in new or low-resource domains. Grammar-based approaches improve segmentation with structural priors but rely on complex parsing limiting scalability.