跳到正文
arXiv cs.AI· Mohammad Eslami, Mousa Moradi, Negin Ghamsarian, Nazlee Zebardast, Jennifer L Lindsey, Sophia Y. Wang, Lucia Sobrin, Rishi P Singh, Tobias Elze·· 1 小时前AI 评分38

SurgCBVR:首个面向手术视频内容检索的多域视频到视频基准

SurgCBVR: A Multi-Domain Benchmark for Content-Based Surgical Video-to-Video Retrieval

AI 导读

研究者推出 SurgCBVR,首个基于内容的手术视频到视频检索基准,整合眼科、腹腔镜、机器人辅助和结肠镜四域共八个公开数据集,涵盖 679 例、76,489 个片段(106 小时)。

正文 · 原文

View PDF

Abstract:Hospitals record thousands of hours of surgical video annually, yet these archives remain difficult to search by content. Surgeons cannot readily retrieve similar operations, complications, or workflow events. Existing surgical computer vision primarily produces labels rather than retrieving relevant videos. We introduce SurgCBVR, the first benchmark for content-based video-to-video retrieval in surgery. It integrates eight public datasets across four domains-ophthalmic, laparoscopic, robotic-assisted, and colonoscopy-covering six procedure types, 679 cases, and 76,489 clips (106 hours). SurgCBVR comprises two tiers: Scene, retrieving the same operative state across cases and sites, and Workflow, retrieving and localizing phase transitions and deviations. Scene includes 74,765 clips spanning 40 classes, three temporal granularities, and three playback speeds; Workflow contains 1,724 transition clips. Fixed clip lengths and frame counts, together with phase-classifier oracle and duration-only baselines, help assess label and timing shortcuts. We evaluate six generic and surgical foundation models, two video retrieval methods, and contrastive heads trained on SurgCBVR, using within-dataset, cross-dataset, and pooled-gallery retrieval restricted to the same procedure type. Frozen representations barely outperform a timing-only baseline, transition retrieval approaches chance, and trained heads lose up to half their accuracy across datasets. These findings expose substantial limitations in current video representations and establish SurgCBVR as a benchmark for advancing surgery-aware retrieval.
Subjects: Image and Video Processing (eess.IV); Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.23347 [eess.IV]
  (or arXiv:2611.23347v1 [eess.IV] for this version)
  https://doi.org/10.48550/arXiv.2611.23347

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Mohammad Eslami [view email]
[v1] Tue, 17 Nov 2026 11:00:04 UTC (18,562 KB)

来源:arXiv cs.AI · arxiv.org