# Large-scale Self-supervised Video Foundation Model for Intelligent Surgery

arXiv: https://arxiv.org/abs/2506.02692 · HTML: https://mlsanity.com/paper/2506.02692/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 69 references that are in the map.
- First posted on arXiv 3 Jun 2025.

## Builds on (most cited first, 30 of 47)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions](https://mlsanity.com/paper/1705.08421/) (2017)
- [InternVideo: General Video Foundation Models via Generative and Discriminative Learning](https://mlsanity.com/paper/2212.03191/) (2022)
- [Masked Autoencoders As Spatiotemporal Learners](https://mlsanity.com/paper/2205.09113/) (2022)
- [EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos](https://mlsanity.com/paper/1602.03012/) (2016)
- [A Short Note about Kinetics-600](https://mlsanity.com/paper/1808.01340/) (2018)
- [A Short Note on the Kinetics-700 Human Action Dataset](https://mlsanity.com/paper/1907.06987/) (2019)
- [Masked Siamese Networks for Label-Efficient Learning](https://mlsanity.com/paper/2204.07141/) (2022)
- [Unmasked Teacher: Towards Training-Efficient Video Foundation Models](https://mlsanity.com/paper/2303.16058/) (2023)
- [EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention](https://mlsanity.com/paper/2305.07027/) (2023)
- [TeCNO: Surgical Phase Recognition with Multi-Stage Temporal Convolutional Networks](https://mlsanity.com/paper/2003.10751/) (2020)
- [Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos](https://mlsanity.com/paper/2109.03223/) (2021)
- [Surgical Data Science: Enabling Next-Generation Surgery](https://mlsanity.com/paper/1701.06482/) (2017)
- [UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer](https://mlsanity.com/paper/2211.09552/) (2022)
- [Surgical Data Science -- from Concepts toward Clinical Translation](https://mlsanity.com/paper/2011.02284/) (2020)
- [Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning](https://mlsanity.com/paper/2212.04500/) (2022)
- [AutoLaparo: A New Dataset of Integrated Multi-tasks for Image-guided Surgical Automation in Laparoscopic Hysterectomy](https://mlsanity.com/paper/2208.02049/) (2022)

## Built on by (most cited first, 10 of 10)

- [Cataract-LMM Large-Scale Multi-Source Multi-Task Benchmark for Deep Learning in Surgical Video Analysis](https://mlsanity.com/paper/2510.16371/) (2025)
- [SurgSigma: A Spectrum of Large-Scale Multimodal Data and Foundation Models for Surgical Intelligence](https://mlsanity.com/paper/2603.16822/) (2026)
- [SurgAtlas: A Large-Scale Surgical Video-Language Dataset with 2,391 Hours of Open and Minimally Invasive Surgery](https://mlsanity.com/paper/2606.25905/) (2026)
- [Scaling Video Pretraining for Surgical Foundation Models](https://mlsanity.com/paper/2603.29966/) (2026)
- [On the Role of Depth in Surgical Vision Foundation Models: An Empirical Study of RGB-D Pre-training](https://mlsanity.com/paper/2601.18929/) (2026)
- [A vision-language model and platform for temporally mapping surgery from video](https://mlsanity.com/paper/2603.22583/) (2026)
- [SurgLQA: Scalable Long-Horizon Surgical Video Question Answering](https://mlsanity.com/paper/2605.17915/) (2026)
- [Attribute Retrieving for Open-Vocabulary Endoscopic Compositional Referring Segmentation](https://mlsanity.com/paper/2607.08397/) (2026)
- [Surgical Video Generation From Diffusion to World Models: A Survey](https://mlsanity.com/paper/2608.26214/) (2026)
- [DART: Depth-as-Target Pretraining for Surgical Vision Foundation Models](https://mlsanity.com/paper/2609.04555/) (2026)

## Abstract (arXiv)

Computer-Assisted Intervention (CAI) has the potential to revolutionize modern surgery, with surgical scene understanding serving as a critical component in supporting decision-making, improving procedural efficacy, and ensuring intraoperative safety. While existing AI-driven approaches alleviate annotation burdens via self-supervised spatial representation learning, their lack of explicit temporal modeling during pre-training fundamentally restricts the capture of dynamic surgical contexts, resulting in incomplete spatiotemporal understanding. In this work, we introduce the first video-level surgical pre-training framework that enables joint spatiotemporal representation learning from large-scale surgical video data. To achieve this, we constructed a large-scale surgical video dataset comprising 3,650 videos and approximately 3.55 million frames, spanning more than 20 surgical procedures and over 10 anatomical structures. Building upon this dataset, we propose SurgVISTA (Surgical Video-level Spatial-Temporal Architecture), a reconstruction-based pre-training method that captures intricate spatial structures and temporal dynamics through joint spatiotemporal modeling. Additionally, SurgVISTA incorporates image-level knowledge distillation guided by a surgery-specific expert to enhance the learning of fine-grained anatomical and semantic features. To validate its effectiveness, we established a comprehensive benchmark comprising 13 video-level datasets spanning six surgical procedures across four tasks. Extensive experiments demonstrate that SurgVISTA consistently outperforms both natural- and surgical-domain pre-trained models, demonstrating strong potential to advance intelligent surgical systems in clinically meaningful scenarios.