B-ACT improves label efficiency in temporal action segmentation by selecting only boundary frames for annotation via a two-stage uncertainty-driven process that fuses neighborhood uncertainty, class ambiguity, and temporal dynamics.
Steps: Self- supervised key step extraction and localization from unlabeled procedu- ral videos,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Boundary-Centric Active Learning for Temporal Action Segmentation
B-ACT improves label efficiency in temporal action segmentation by selecting only boundary frames for annotation via a two-stage uncertainty-driven process that fuses neighborhood uncertainty, class ambiguity, and temporal dynamics.