# MoSFormer: Augmenting Temporal Context with Memory of Surgery for Surgical Phase Recognition

arXiv: https://arxiv.org/abs/2503.00695 · HTML: https://mlsanity.com/paper/2503.00695/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 36 references that are in the map.
- First posted on arXiv 2 Mar 2025.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model](https://mlsanity.com/paper/2207.07115/) (2022)
- [Video Object Segmentation using Space-Time Memory Networks](https://mlsanity.com/paper/1904.00607/) (2019)
- [MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation](https://mlsanity.com/paper/1903.01945/) (2019)
- [EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos](https://mlsanity.com/paper/1602.03012/) (2016)
- [Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation](https://mlsanity.com/paper/2106.05210/) (2021)
- [Temporal Convolutional Networks: A Unified Approach to Action Segmentation](https://mlsanity.com/paper/1608.08242/) (2016)
- [Putting the Object Back into Video Object Segmentation](https://mlsanity.com/paper/2310.12982/) (2023)
- [TeCNO: Surgical Phase Recognition with Multi-Stage Temporal Convolutional Networks](https://mlsanity.com/paper/2003.10751/) (2020)
- [Trans-SVNet: Accurate Phase Recognition from Surgical Videos via Hybrid Embedding Aggregation Transformer](https://mlsanity.com/paper/2103.09712/) (2021)
- [AutoLaparo: A New Dataset of Integrated Multi-tasks for Image-guided Surgical Automation in Laparoscopic Hysterectomy](https://mlsanity.com/paper/2208.02049/) (2022)
- [Multi-Task Recurrent Convolutional Network with Correlation Loss for Surgical Video Analysis](https://mlsanity.com/paper/1907.06099/) (2019)
- [Temporal Memory Relation Network for Workflow Recognition from Surgical Video](https://mlsanity.com/paper/2103.16327/) (2021)
- [Real-time Online Video Detection with Temporal Smoothing Transformers](https://mlsanity.com/paper/2209.09236/) (2022)
- [LoViT: Long Video Transformer for Surgical Phase Recognition](https://mlsanity.com/paper/2305.08989/) (2023)
- [Challenges in Multi-centric Generalization: Phase and Step Recognition in Roux-en-Y Gastric Bypass Surgery](https://mlsanity.com/paper/2312.11250/) (2023)
- [Towards Holistic Surgical Scene Understanding](https://mlsanity.com/paper/2212.04582/) (2022)
- [Surgformer: Surgical Transformer with Hierarchical Temporal Attention for Surgical Phase Recognition](https://mlsanity.com/paper/2408.03867/) (2024)
- [Automatic Gesture Recognition in Robot-assisted Surgery with Reinforcement Learning and Tree Search](https://mlsanity.com/paper/2002.08718/) (2020)
- [Metrics Matter in Surgical Phase Recognition](https://mlsanity.com/paper/2305.13961/) (2023)
- [Pelphix: Surgical Phase Recognition from X-ray Images in Percutaneous Pelvic Fixation](https://mlsanity.com/paper/2304.09285/) (2023)
- [M2CAI Workflow Challenge: Convolutional Neural Networks with Time Smoothing and Hidden Markov Model for Video Frames Classification](https://mlsanity.com/paper/1610.05541/) (2016)
- [MoViT: Memorizing Vision Transformers for Medical Image Analysis](https://mlsanity.com/paper/2303.15553/) (2023)
- [Neural Finite-State Machines for Surgical Phase Recognition](https://mlsanity.com/paper/2411.18018/) (2024)

## Built on by (most cited first, 2 of 2)

- [CliPPER: Contextual Video-Language Pretraining on Long-form Intraoperative Surgical Procedures for Event Recognition](https://mlsanity.com/paper/2603.24539/) (2026)
- [Multimodal Shared Latent Representation of Narration, Microscope and iOCT Images for Phase Recognition in Vitreoretinal Surgery](https://mlsanity.com/paper/2608.31065/) (2026)

## Abstract (arXiv)

Surgical phase recognition from video enables various downstream applications. Transformer-based sliding window approaches have set the state-of-the-art by capturing rich spatial-temporal features. However, while transformers can theoretically handle arbitrary-length sequences, in practice they are limited by memory and compute constraints, resulting in fixed context windows that struggle with maintaining temporal consistency across lengthy surgical procedures. This often leads to fragmented predictions and limited procedure-level understanding. To address these challenges, we propose Memory of Surgery (MoS), a framework that enriches temporal modeling by incorporating both semantic interpretable long-term surgical history and short-term impressions. MoSFormer, our enhanced transformer architecture, integrates MoS using a carefully designed encoding and fusion mechanism. We further introduce step filtering to refine history representation and develop a memory caching pipeline to improve training and inference stability, mitigating shortcut learning and overfitting. MoSFormer demonstrates state-of-the-art performance on multiple benchmarks. On the Challenging BernBypass70 benchmark, it attains 88.0 video-level accuracy and phase-level metrics of 70.7 precision, 68.7 recall, and 66.3 F1 score, outperforming its baseline with 2.1 video-level accuracy and phase-level metrics of 4.6 precision, 3.6 recall, and 3.8 F1 score. Further studies confirms the individual and combined benefits of long-term and short-term memory components through ablation and counterfactual inference. Qualitative results shows improved temporal consistency. The augmented temporal context enables procedure-level understanding, paving the way for more comprehensive surgical video analysis.