{"total":30,"rows":[{"id":"2304.09974","title":"SurgicalGPT: End-to-End Language-Vision GPT for Visual Question Answering in Surgery","created":"2023-04-19","cited_by_count":48,"area":null},{"id":"2303.09514","title":"MATIS: Masked-Attention Transformers for Surgical Instrument Segmentation","created":"2023-03-16","cited_by_count":36,"area":null},{"id":"2501.09436","title":"Scaling up self-supervised learning for improved surgical foundation models","created":"2025-01-16","cited_by_count":25,"area":null},{"id":"2401.00678","title":"General-purpose foundation models for increased autonomy in robot-assisted surgery","created":"2024-01-01","cited_by_count":15,"area":null},{"id":"2410.09750","title":"Surgical-LLaVA: Toward Surgical Scenario Understanding via Large Language and Vision Models","created":"2024-10-13","cited_by_count":13,"area":null},{"id":"2501.07468","title":"From Screens to Scenes: A Survey of Embodied AI in Healthcare","created":"2025-01-13","cited_by_count":10,"area":null},{"id":"2506.02692","title":"Large-scale Self-supervised Video Foundation Model for Intelligent Surgery","created":"2025-06-03","cited_by_count":10,"area":null},{"id":"2303.17636","title":"Whether and When does Endoscopy Domain Pretraining Make Sense?","created":"2023-03-30","cited_by_count":8,"area":null},{"id":"2304.09285","title":"Pelphix: Surgical Phase Recognition from X-ray Images in Percutaneous Pelvic Fixation","created":"2023-04-18","cited_by_count":8,"area":null},{"id":"2404.00322","title":"Instrument-tissue Interaction Detection Framework for Surgical Video Understanding","created":"2024-03-30","cited_by_count":8,"area":null},{"id":"2407.17361","title":"MuST: Multi-Scale Transformers for Surgical Phase Recognition","created":"2024-07-24","cited_by_count":8,"area":null},{"id":"2407.17904","title":"Exploring the Effect of Dataset Diversity in Self-Supervised Learning for Surgical Computer Vision","created":"2024-07-25","cited_by_count":7,"area":null},{"id":"2306.08859","title":"SF-TMN: SlowFast Temporal Modeling Network for Surgical Phase Recognition","created":"2023-06-15","cited_by_count":5,"area":null},{"id":"2309.09563","title":"RIDE: Self-Supervised Learning of Rotation-Equivariant Keypoint Detection and Invariant Description for Endoscopy","created":"2023-09-18","cited_by_count":5,"area":null},{"id":"2401.08256","title":"Multitask Learning in Minimally Invasive Surgical Vision: A Review","created":"2024-01-16","cited_by_count":5,"area":null},{"id":"2411.18018","title":"Neural Finite-State Machines for Surgical Phase Recognition","created":"2024-11-27","cited_by_count":5,"area":null},{"id":"2506.01130","title":"ProstaTD: Bridging Surgical Triplet from Classification to Fully Supervised Detection","created":"2025-06-01","cited_by_count":4,"area":null},{"id":"2602.05638","title":"SurgMotion: A Video-Native Foundation Model for Universal Understanding of Surgical Videos","created":"2026-02-05","cited_by_count":4,"area":null},{"id":"2605.08712","title":"From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation","created":"2026-05-09","cited_by_count":4,"area":null},{"id":"2212.12719","title":"MURPHY: Relations Matter in Surgical Workflow Analysis","created":"2022-12-24","cited_by_count":3,"area":null},{"id":"2403.17192","title":"Strategies to Improve Real-World Applicability of Laparoscopic Anatomy Segmentation Models","created":"2024-03-25","cited_by_count":2,"area":null},{"id":"2502.06708","title":"TEMSET-24K: Densely Annotated Dataset for Indexing Multipart Endoscopic Videos using Surgical Timeline Segmentation","created":"2025-02-10","cited_by_count":2,"area":null},{"id":"2502.15184","title":"Hierarchical Context Transformer for Multi-level Semantic Scene Understanding","created":"2025-02-21","cited_by_count":2,"area":null},{"id":"2503.00695","title":"MoSFormer: Augmenting Temporal Context with Memory of Surgery for Surgical Phase Recognition","created":"2025-03-02","cited_by_count":2,"area":null},{"id":"2507.15541","title":"Towards Holistic Surgical Scene Graph","created":"2025-07-21","cited_by_count":2,"area":null},{"id":"2409.07801","title":"SURGIVID: Annotation-Efficient Surgical Video Object Discovery","created":"2024-09-12","cited_by_count":1,"area":null},{"id":"2509.18802","title":"Surgical Video Understanding with Label Interpolation","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2308.13073","title":"SurGNN: Explainable visual scene understanding and assessment of surgical skill using graph neural networks","created":"2023-08-24","cited_by_count":0,"area":null},{"id":"2510.12904","title":"State-Change Learning for Prediction of Future Events in Endoscopic Videos","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2602.20500","title":"Strategy-Supervised Autonomous Laparoscopic Camera Control via Event-Driven Graph Mining","created":"2026-02-24","cited_by_count":0,"area":null}],"next_cursor":null}