Salvato in:
Dettagli Bibliografici
Autori principali: Lu, Sicheng, Xiao, Zikai, Wei, Jianhui, Sun, Danyu, Lu, Qi, Hu, Keli, Feng, Yang, Wu, Jian, Yang, Zongxin, Liu, Zuozhu
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2603.29966
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910098059689984
author Lu, Sicheng
Xiao, Zikai
Wei, Jianhui
Sun, Danyu
Lu, Qi
Hu, Keli
Feng, Yang
Wu, Jian
Yang, Zongxin
Liu, Zuozhu
author_facet Lu, Sicheng
Xiao, Zikai
Wei, Jianhui
Sun, Danyu
Lu, Qi
Hu, Keli
Feng, Yang
Wu, Jian
Yang, Zongxin
Liu, Zuozhu
contents Surgical video understanding is essential for computer-assisted interventions, yet existing surgical foundation models remain constrained by limited data scale, procedural diversity, and inconsistent evaluation, often lacking a reproducible training pipeline. We propose SurgRec, a scalable and reproducible pretraining recipe for surgical video understanding, instantiated with two variants: SurgRec-MAE and SurgRec-JEPA. We curate a large multi-source corpus of 10,535 videos and 214.5M frames spanning endoscopy, laparoscopy, cataract, and robotic surgery. Building on this corpus, we develop a unified pretraining pipeline with balanced sampling and standardize a reproducible benchmark across 16 downstream datasets and four clinical domains with consistent data splits. Across extensive comparisons against SSL baselines and vision-language models, SurgRec consistently achieves superior performance across downstream datasets. In contrast, VLMs prove unreliable for fine-grained temporal recognition, exhibiting both performance gaps and sensitivity to prompt phrasing. Our work provides a reproducible, scalable foundation for the community to build more general surgical video models. All code, models, and data will be publicly released.
format Preprint
id arxiv_https___arxiv_org_abs_2603_29966
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Scaling Video Pretraining for Surgical Foundation Models
Lu, Sicheng
Xiao, Zikai
Wei, Jianhui
Sun, Danyu
Lu, Qi
Hu, Keli
Feng, Yang
Wu, Jian
Yang, Zongxin
Liu, Zuozhu
Computer Vision and Pattern Recognition
Surgical video understanding is essential for computer-assisted interventions, yet existing surgical foundation models remain constrained by limited data scale, procedural diversity, and inconsistent evaluation, often lacking a reproducible training pipeline. We propose SurgRec, a scalable and reproducible pretraining recipe for surgical video understanding, instantiated with two variants: SurgRec-MAE and SurgRec-JEPA. We curate a large multi-source corpus of 10,535 videos and 214.5M frames spanning endoscopy, laparoscopy, cataract, and robotic surgery. Building on this corpus, we develop a unified pretraining pipeline with balanced sampling and standardize a reproducible benchmark across 16 downstream datasets and four clinical domains with consistent data splits. Across extensive comparisons against SSL baselines and vision-language models, SurgRec consistently achieves superior performance across downstream datasets. In contrast, VLMs prove unreliable for fine-grained temporal recognition, exhibiting both performance gaps and sensitivity to prompt phrasing. Our work provides a reproducible, scalable foundation for the community to build more general surgical video models. All code, models, and data will be publicly released.
title Scaling Video Pretraining for Surgical Foundation Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.29966