Adding depth-derived geometric priors to a RepVGG backbone improves surgical phase classification on a new nine-phase ESD dataset.
Multimodal graph representation learning for robust surgical workflow recognition with adversarial feature disentanglement,
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
-
Geo-RepNet: Geometry-Aware Representation Learning for Surgical Phase Recognition in Endoscopic Submucosal Dissection
Adding depth-derived geometric priors to a RepVGG backbone improves surgical phase classification on a new nine-phase ESD dataset.