TDSC jointly learns temporally consistent structured representations and stabilized affinity via coding-rate maximization and momentum averaging for improved human motion segmentation.
Temporal action segmentation: An analysis of modern techniques,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
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.
citing papers explorer
-
Jointly Learning Structured Representations and Stabilized Affinity for Human Motion Segmentation
TDSC jointly learns temporally consistent structured representations and stabilized affinity via coding-rate maximization and momentum averaging for improved human motion segmentation.
-
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.