StepAL is an active learning method that selects whole surgical videos that are both uncertain and step-diverse, improving step recognition accuracy with fewer annotations.
In: MICCAI 2020
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
StepAL: Step-aware Active Learning for Cataract Surgical Videos
StepAL is an active learning method that selects whole surgical videos that are both uncertain and step-diverse, improving step recognition accuracy with fewer annotations.