Research map / Video / Video segmentation and tracking
Where It Moves, It Matters: Referring Surgical Instrument Segmentation via Motion
Meng Wei, Kun Yuan, Shi Li, Yue Zhou, Long Bai, Nassir Navab, Hongliang Ren, Hong Joo Lee, Tom Vercauteren, Nicolas Padoy
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add key-frame selection module | SurgRef · EV-IM17 | J&F: 87.70 -> 89.42 | Improved |
| add key-frame selection module | SurgRef · EV-IM18 | J&F: 80.27 -> 84.48 | Improved |
| add key-frame selection module | SurgRef · CholecSeg8k-IM zero-shot | J&F: 67.91 -> 70.62 | Improved |
| train with motion-based expressions (ablation) | SurgRef · EV-IM17 motion test expressions | J&F: 79.03 -> 89.42 | Improved |
| train with motion-based expressions (ablation) | SurgRef · EV-IM17 appearance test expressions | J&F: 74.25 -> 85.17 | Improved |
| keep spatial location cues in expressions (ablation) | SurgRef · EV-IM17 expression style | J&F: 64.13 -> 87.70 | Improved |
| keep instrument names in expressions (ablation) | SurgRef · EV-IM17 expression style | J&F: 79.02 -> 87.70 | Improved |
| replace uniform frame sampling with learned key-frame selection at T'=8 (ablation) | SurgRef · EV-IM17 | J&F: 82.16 -> 89.42 | Improved |
| replace cosine-similarity selection with learned key-frame selection at T'=8 (ablation) | SurgRef · EV-IM17 | J&F: 85.71 -> 89.42 | Improved |
| increase number of selected frames T' beyond 16 (ablation) | SurgRef · EV-IM17 | J&F: 89.56 -> 88.35 (T'=16 -> 32) | No clear effect |
| add key-frame selection module vs MPG-SAM 2 baseline | SurgRef · EV-IM17 | Dice: 84.37 -> 87.94 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- MPG-SAM 2 — MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation (ICCV 2025) · better on 3 of 3 shared results
- VISA — VISA: Reasoning Video Object Segmentation via Large Language Model (ECCV 2024) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Bridging Vision and Language for Robust Context-Aware Surgical Point Tracking: The VL-SurgPT Dataset and Benchmark (AAAI 2026 · similarity 0.88)
- CholecTrack20: A Multi-Perspective Tracking Dataset for Surgical Tools (CVPR 2025 · similarity 0.87)
- SurgCoT: Advancing Spatiotemporal Reasoning in Surgical Videos through a Chain-of-Thought Benchmark (CVPR 2026 · similarity 0.87)
- SurgicalSAM: Efficient Class Promptable Surgical Instrument Segmentation (AAAI 2024 · similarity 0.87)
- Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation (NeurIPS 2024 · similarity 0.86)
- MM-OR: A Large Multimodal Operating Room Dataset for Semantic Understanding of High-Intensity Surgical Environments (CVPR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
