arXiv Computer Vision

Latent-Action-Guided Vision-Language Contrastive Learning for Surgical Interaction Recognition

arXiv Computer Vision
Oct 7

Latent-Action-Guided Video-Language Feature Learning for Surgical Instrument-Tissue Interaction Recognition

The paper introduces Latent-Action-Guided Video-Language Feature Learning (LAG-VLFL) for recognizing surgical instrument–tissue interactions. By compressing frame-to-frame feature changes into latent actions and predicting next‑frame features, the method aligns video and textual action descriptions without requiring extra spatial or motion annotations. Experiments show that LAG-VLFL improves interaction grounding, temporal‑direction sensitivity, and achieves competitive recognition with faster inference and lower INT4 accuracy loss compared to V‑JEPA2/2.1.

By Jiajun Cheng, Sainan Liu, Subarna Tripathi, Xiaofan Yu, Shan Lin
arXiv Computer Vision
Sep 22

SurgMotion: A Video-Native Foundation Model for Universal Understanding of Surgical Videos

SurgMotion is a video-native foundation model that replaces pixel-level reconstruction with latent motion prediction for surgical video analysis. It introduces motion-guided masked prediction, spatiotemporal affinity self-distillation, and spatiotemporal feature diversity regularization to focus on semantically meaningful regions and avoid representation collapse. Trained on SurgMotion-15M, the largest surgical video dataset, it outperforms state-of-the-art methods across 17 benchmarks, improving workflow recognition, action triplet recognition, skill assessment, polyp segmentation, and depth estimation.

By Jinlin Wu, Felix Holm, Chuxi Chen, An Wang, Yaxin Hu, Xiaofan Ye, Zelin Zang, Miao Xu, Lihua Zhou, Huai Liao, Danny T. M. Chan, Ming Feng, Wai S. Poon, Hongliang Ren, Dong Yi, Nassir Navab, Gaofeng Meng, Jiebo Luo, Hongbin Liu, Zhen Lei
arXiv Computation and Language
Oct 27

MIS-VQA: An Annotation-Driven Surgical Vision-Language Dataset for Complex Surgical Understanding

arXiv:2610.34210v1 Announce Type: cross Abstract: Modern surgical AI increasingly requires multimodal understanding rather than isolated perception, yet existing datasets remain largely limited to si...

By Mohamed Hamdy, Iheb Zouari, Fatmaelzahraa Ahmed, Muraam Abdel-Ghani, Muhammed Arsalan, Ponnuthurai Suganthan, Khalid Al-Jalham, Abdulaziz Al-Ali, Shidin Balakrishnan
arXiv AI
Nov 6

InnerLogic-Surg: An Open Surgical Foundation Model via Continual Pretraining

InnerLogic‑Surg is an open family of transformer‑based surgical vision encoders ranging from 21 M to 300 M parameters, trained by continually pretraining on millions of surgical images from 11,965 internet‑sourced videos covering ~2,900 hours and more than fifteen procedure types. The training pipeline builds on DINOv3 to preserve general representation ability while adding a learned feature‑upsampling module for high‑resolution dense prediction at low token cost. In a benchmark covering workflow, instrument and anatomy recognition, segmentation, detection, and monocular depth, the largest InnerLogic‑Surg model achieves the best linear‑probe performance across all 20 surgical tasks, demonstrating transferable representations that generalize across procedures, anatomical regions, and task types.

By Kun Yuan, Hao Ding, Yiqing Shen, Gasper Podobnik, Benjamin Killeen, Tito Porras, Axel Krieger, Mathias Unberath
arXiv AI
Jun 2

From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data

arXiv:2606. 00054v1 Announce Type: cross Abstract: Recent progress in generalizable embodied control has been driven by large-scale pretraining of Vision-Language-Action (VLA) models.

By Zhiyuan Feng, Qixiu Li, Huizhi Liang, Rushuai Yang, Yichao Shen, Zhiying Du, Zhaowei Zhang, Yu Deng, Li Zhao, Hao Zhao, Zongqing Lu, Oier Mees, Marc Pollefeys, Jiaolong Yang, Baining Guo
Hugging Face Trending Papers
Nov 5

InnerLogic-Surg: An Open Surgical Foundation Model via Continual Pretraining

InnerLogic‑Surg is an open family of transformer‑based surgical vision encoders, ranging from 21 M to 300 M parameters, that are continually pretrained on millions of surgical images drawn from 11,965 internet‑sourced videos covering roughly 2,900 hours and more than fifteen procedure types. The training pipeline builds on DINOv3 to maintain general representation quality while adding a learned feature‑upsampling module for efficient high‑resolution dense prediction. On a benchmark of 20 surgical tasks—including workflow, instrument and anatomy recognition, segmentation, detection, and monocular depth—the largest InnerLogic‑Surg model achieves the best linear‑probe performance across all tasks, demonstrating that surgical continual pretraining yields transferable representations that generalize across procedures, anatomical regions, and task types.

Hugging Face Trending Papers
Jun 25

Temporally Consistent Label Interpolation for Robust Surgical Multi-Task Learning under Challenging Conditions

Effective multi-task learning for surgical scene understanding is fundamentally hindered by annotation granularity mismatch; temporal workflow tasks such as phase recognition, step recognition and anticipation benefit from dense frame-level supervision, whereas pixel-level spatial tasks including instrument segmentation and action recognition are only sparsely annotated on selected keyframes due to prohibitive labeling costs. This supervision imbalance undermines shared representation learning and limits joint optimization across heterogeneous surgical tasks.

arXiv AI
Nov 5

SurgTransfer: Multi-Step Latent Action Modeling for Action Transfer in Surgical World Model

SurgTransfer introduces a multi-step latent action modeling framework for surgical world models, enabling the learning of context-invariant latent actions from unlabeled videos. Unlike prior work that relies on ground-truth kinematics or expert annotations, SurgTransfer captures the hierarchical, goal-directed structure of surgical procedures. Experiments on SurgToolLoc-2022 and PitVis-2023 datasets demonstrate improved quantitative metrics and qualitative expert evaluation, with code publicly available on GitHub.

By Saurabh Koju, Love Panta, Deepak Thapa, Rudra P. K. Poudel, Prajwal Ghimire, Angus Watson, Yash Raj Shrestha, Prashnna Kumar Gyawali, Binod Bhattarai
arXiv Computer Vision
Aug 25

Dense Structural Priors for Sparse Functional Landmark Localization in Surgical Videos

The paper presents a method for localizing functional surgical landmarks—specifically instrument tips and anchors—in surgical videos without requiring manual pixel-level mask annotations. It leverages vision foundation models, such as SAM 3, to generate dense structural priors through zero‑shot, point‑prompted masks, and refines landmark predictions with a lightweight, coarse‑to‑fine multi‑frame network. Experiments on 7,867 clips from 60 videos show that the approach achieves F1 scores of 72.4% for tip and 58.0% for anchor localization, with ablations confirming the benefits of structural priors and refinement stages.

By Chenyan Jing, Hao Ding, Lalithkumar Seenivasan, Jacob M. Delgado L\'opez, Mathias Unberath