Introduces SIA-RAPN benchmark of 50 clinical videos with 12 fine-grained renorrhaphy action labels and evaluates four temporal segmentation models, with DiffAct leading on most metrics.
Asformer: Transformer for action segmentation
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.CV 4years
2026 4verdicts
UNVERDICTED 4representative 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.
IMPACT-Scribe is a correction-driven interactive system that combines uncertainty-aware boundary scribbles, local proposal modeling, cost-aware query planning, structured propagation, and correction-driven adaptation to improve labeling quality per effort and boundary accuracy in temporal action seg
AdaAct employs a HOI encoder and two-branch hypernetwork to adaptively adjust temporal encoding parameters based on video-level human-object interactions for improved weakly-supervised action segmentation.
citing papers explorer
-
Fine-Grained Action Segmentation for Renorrhaphy in Robot-Assisted Partial Nephrectomy
Introduces SIA-RAPN benchmark of 50 clinical videos with 12 fine-grained renorrhaphy action labels and evaluates four temporal segmentation models, with DiffAct leading on most metrics.
-
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.
-
IMPACT-Scribe: Interactive Temporal Action Segmentation with Boundary Scribbles and Query Planning
IMPACT-Scribe is a correction-driven interactive system that combines uncertainty-aware boundary scribbles, local proposal modeling, cost-aware query planning, structured propagation, and correction-driven adaptation to improve labeling quality per effort and boundary accuracy in temporal action seg
-
HOI-aware Adaptive Network for Weakly-supervised Action Segmentation
AdaAct employs a HOI encoder and two-branch hypernetwork to adaptively adjust temporal encoding parameters based on video-level human-object interactions for improved weakly-supervised action segmentation.