Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.09051 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918438357696512 |
|---|---|
| author | Dai, Jiaheng Liu, Huanrong Zhou, Tailai Jia, Tongyu Liu, Qin Ban, Yutong Li, Zeju Gao, Yu Ma, Xin Li, Qingbiao |
| author_facet | Dai, Jiaheng Liu, Huanrong Zhou, Tailai Jia, Tongyu Liu, Qin Ban, Yutong Li, Zeju Gao, Yu Ma, Xin Li, Qingbiao |
| contents | Fine-grained action segmentation during renorrhaphy in robot-assisted partial nephrectomy requires frame-level recognition of visually similar suturing gestures with variable duration and substantial class imbalance. The SIA-RAPN benchmark defines this problem on 50 clinical videos acquired with the da Vinci Xi system and annotated with 12 frame-level labels. The benchmark compares four temporal models built on I3D features: MS-TCN++, AsFormer, TUT, and DiffAct. Evaluation uses balanced accuracy, edit score, segmental F1 at overlap thresholds of 10, 25, and 50, frame-wise accuracy, and frame-wise mean average precision. In addition to the primary evaluation across five released split configurations on SIA-RAPN, the benchmark reports cross-domain results on a separate single-port RAPN dataset. Across the strongest reported values over those five runs on the primary dataset, DiffAct achieves the highest F1, frame-wise accuracy, edit score, and frame mAP, while MS-TCN++ attains the highest balanced accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_09051 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Fine-Grained Action Segmentation for Renorrhaphy in Robot-Assisted Partial Nephrectomy Dai, Jiaheng Liu, Huanrong Zhou, Tailai Jia, Tongyu Liu, Qin Ban, Yutong Li, Zeju Gao, Yu Ma, Xin Li, Qingbiao Computer Vision and Pattern Recognition Robotics Fine-grained action segmentation during renorrhaphy in robot-assisted partial nephrectomy requires frame-level recognition of visually similar suturing gestures with variable duration and substantial class imbalance. The SIA-RAPN benchmark defines this problem on 50 clinical videos acquired with the da Vinci Xi system and annotated with 12 frame-level labels. The benchmark compares four temporal models built on I3D features: MS-TCN++, AsFormer, TUT, and DiffAct. Evaluation uses balanced accuracy, edit score, segmental F1 at overlap thresholds of 10, 25, and 50, frame-wise accuracy, and frame-wise mean average precision. In addition to the primary evaluation across five released split configurations on SIA-RAPN, the benchmark reports cross-domain results on a separate single-port RAPN dataset. Across the strongest reported values over those five runs on the primary dataset, DiffAct achieves the highest F1, frame-wise accuracy, edit score, and frame mAP, while MS-TCN++ attains the highest balanced accuracy. |
| title | Fine-Grained Action Segmentation for Renorrhaphy in Robot-Assisted Partial Nephrectomy |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2604.09051 |