SurgicalMamba achieves SOTA online accuracy on surgical phase recognition benchmarks by adding dual-path SSD, intensity-modulated stepping, and state regramming to Mamba2 while keeping per-frame cost O(d).
arXiv (2024) 2401.11174 [cs.CV]
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3verdicts
UNVERDICTED 3representative citing papers
Introduces the triplet segmentation task, CholecTriplet-Seg dataset with over 30,000 frames, and TargetFusionNet architecture extending Mask2Former for instance-level grounding of surgical <instrument, verb, target> triplets.
FAROS uses flow-guided propagation from zero-shot masks and optical flow to create dense temporally consistent labels from sparse keyframes, improving joint multi-task learning across temporal and spatial surgical tasks on GraSP, MISAW, and AutoLaparo.
citing papers explorer
-
SurgicalMamba: Dual-Path SSD with State Regramming for Online Surgical Phase Recognition
SurgicalMamba achieves SOTA online accuracy on surgical phase recognition benchmarks by adding dual-path SSD, intensity-modulated stepping, and state regramming to Mamba2 while keeping per-frame cost O(d).
-
Grounding Surgical Action Triplets with Instrument Instance Segmentation: A Dataset and Target-Aware Fusion Approach
Introduces the triplet segmentation task, CholecTriplet-Seg dataset with over 30,000 frames, and TargetFusionNet architecture extending Mask2Former for instance-level grounding of surgical <instrument, verb, target> triplets.
-
Temporally Consistent Label Interpolation for Robust Surgical Multi-Task Learning under Challenging Conditions
FAROS uses flow-guided propagation from zero-shot masks and optical flow to create dense temporally consistent labels from sparse keyframes, improving joint multi-task learning across temporal and spatial surgical tasks on GraSP, MISAW, and AutoLaparo.