Research map / Video / Video segmentation and tracking
Synergistic Bleeding Region and Point Detection in Laparoscopic Surgical Videos
Jialun Pei, Zhangjun Zhou, Diandian Guo, Zhixi Li, Jing Qin, Bo Du, Pheng-Ann Heng
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 edge generator (wavelet Laplacian edge prompts) (ablation) | BlooDet · SurgBlood test set | IoU: 61.20 -> 64.88 | Improved |
| add point memory modeling (ablation) | BlooDet · SurgBlood test set | PCK-5%: 42.83 -> 55.85 | Improved |
| add edge generator on top of point memory modeling for point detection (ablation) | BlooDet · SurgBlood test set | PCK-5%: 51.57 -> 55.85 | Improved |
| add edge generator alone (without point memory modeling) (ablation) | BlooDet · SurgBlood test set | PCK-5%: 45.14 -> 42.83 | Hurt |
| add wavelet Laplacian filter to the edge generator (ablation) | BlooDet · SurgBlood test set | IoU: 62.41 -> 64.88 | Improved |
| add high-resolution features F1 and F2 to the edge generator (ablation) | BlooDet · SurgBlood test set | IoU: 64.74 -> 64.88 | Improved |
| add optical flow for camera offset (background-averaged) (ablation) | BlooDet · SurgBlood test set | PCK-5%: 45.47 -> 55.85 | Improved |
| average optical flow over foreground instead of background (ablation) | BlooDet · SurgBlood test set | PCK-5%: 55.85 -> 41.02 | Hurt |
| average optical flow over whole frame instead of background (ablation) | BlooDet · SurgBlood test set | PCK-5%: 55.85 -> 49.59 | Hurt |
| add point prompt, mask map and mask memory cross-branch guidance (ablation) | BlooDet · SurgBlood test set | IoU, Dice, PCK-5%, PCK-10% | Improved |
| dual-branch joint training versus task-specific models | BlooDet · SurgBlood test set | PCK-10%: 60.13 -> 83.69 vs D-CeLR | Improved |
| add a point head to region-level models for dual-task learning | SAM 2 · SurgBlood test set | IoU: 63.51 -> 50.93 | Hurt |
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.
- SAM 2 — SAM 2: Segment Anything in Images and Videos (ICLR 2025) · better on 7 of 7 shared results
- MemSAM — MemSAM: Taming Segment Anything Model for Echocardiography Video Segmentation (CVPR 2024) · better on 3 of 3 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
- OphNet: A Large-Scale Video Benchmark for Ophthalmic Surgical Workflow Understanding (ECCV 2024 · similarity 0.86)
- Surgical Workflow Recognition and Blocking Effectiveness Detection in Laparoscopic Liver Resection with Pringle Maneuver (AAAI 2025 · similarity 0.84)
- CholecTrack20: A Multi-Perspective Tracking Dataset for Surgical Tools (CVPR 2025 · similarity 0.84)
- Bridging Vision and Language for Robust Context-Aware Surgical Point Tracking: The VL-SurgPT Dataset and Benchmark (AAAI 2026 · similarity 0.84)
- SurgCoT: Advancing Spatiotemporal Reasoning in Surgical Videos through a Chain-of-Thought Benchmark (CVPR 2026 · similarity 0.82)
- Redefining the Laparoscopic Spatial Sense: AI-Based Intra- and Postoperative Measurement from Stereoimages (AAAI 2024 · similarity 0.81)
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.
