DBT-Bleed reports 6.53% F1 and 9% MCC gains for bleeding detection on MultiBypass plus 6% F1 zero-shot transfer on a new neurosurgery IAE dataset using dual-branch temporal adapters and entropy-driven frame selection.
arXiv preprint arXiv:2507.15094 (2025)
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
-
DBT-Bleed: Dual-Branch Temporal Modeling with Key-Frame Selection for Surgical Bleeding Detection
DBT-Bleed reports 6.53% F1 and 9% MCC gains for bleeding detection on MultiBypass plus 6% F1 zero-shot transfer on a new neurosurgery IAE dataset using dual-branch temporal adapters and entropy-driven frame selection.