Research map / Video / Video segmentation and tracking
ProstaTD: Bridging Surgical Triplet from Classification to Fully Supervised Detection
Yiliang Chen, Zhixi Li, Cheng Xu, Alex Qinyang Liu, Ruize Cui, Xuemiao Xu, Jeremy Yuen-Chun Teoh, Shengfeng He, Jing Qin
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 |
|---|---|---|---|
| Use fully supervised bounding-box detection instead of weakly supervised class-label training | Tripnet-Det / Faster R-CNN · ProstaTD (5-fold CV) | mAP IVT @0.5: 0.1 -> 25.9 | Improved |
| Use TDnet multi-task self-distillation instead of YOLOv12 | YOLOv12 · ProstaTD (5-fold CV) | mAP IVT @0.5: 34.3 -> 36.1 | Improved |
| Use TDnet instead of YOLOv12 at stricter IoU | YOLOv12 · ProstaTD (5-fold CV) | mAP IVT @0.5:0.95: 31.8 -> 33.1 | Improved |
| Use TDnet instead of YOLOv12 for F1 | YOLOv12 · ProstaTD (5-fold CV) | F1-score IVT: 31.9 -> 32.8 | Improved |
| Use TDnet instead of YOLOv12 for recall | YOLOv12 · ProstaTD (5-fold CV) | Recall IVT: 36.2 -> 39.7 | Improved |
| Use RT-DETR instead of YOLOv12 for speed | RT-DETR · ProstaTD (5-fold CV) | Inference speed (FPS): 66.3 | Hurt |
| Add temporal multi-task branch (TAPIR) instead of single-frame detector YOLOv12 | YOLOv12 · ProstaTD (5-fold CV) | mAP IVT @0.5: 34.3 -> 28.4 | Hurt |
Closest papers by meaning
- CholecTrack20: A Multi-Perspective Tracking Dataset for Surgical Tools (CVPR 2025 · similarity 0.84)
- Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised Data (ICLR 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)
- EndoBench: A Comprehensive Evaluation of Multi-Modal Large Language Models for Endoscopy Analysis (NeurIPS 2025 · similarity 0.83)
- PathView-Bench: Can Multimodal Large Language Models Achieve Fine-grained Multiscale Understanding of Pathology Images? (NeurIPS 2026 · similarity 0.83)
- EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity Understanding (NeurIPS 2025 · similarity 0.82)
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.
