{"total":33,"rows":[{"id":"2503.02579","title":"MM-OR: A Large Multimodal Operating Room Dataset for Semantic Understanding of High-Intensity Surgical Environments","created":"2025-03-04","cited_by_count":28,"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":"2312.12429","title":"The Endoscapes Dataset for Surgical Scene Segmentation, Object Detection, and Critical View of Safety Assessment: Official Splits and Benchmark","created":"2023-12-19","cited_by_count":21,"area":null},{"id":"2312.06829","title":"Encoding Surgical Videos as Latent Spatiotemporal Graphs for Object and Anatomy-Driven Reasoning","created":"2023-12-11","cited_by_count":14,"area":null},{"id":"2407.20214","title":"SANGRIA: Surgical Video Scene Graph Optimization for Surgical Workflow Prediction","created":"2024-07-29","cited_by_count":12,"area":null},{"id":"2410.17751","title":"VISAGE: Video Synthesis using Action Graphs for Surgery","created":"2024-10-23","cited_by_count":11,"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":"2312.05968","title":"Jumpstarting Surgical Computer Vision","created":"2023-12-10","cited_by_count":8,"area":null},{"id":"2312.12250","title":"ST(OR)2: Spatio-Temporal Object Level Reasoning for Activity Recognition in the Operating Room","created":"2023-12-19","cited_by_count":6,"area":null},{"id":"2509.17100","title":"The SAGES Critical View of Safety Challenge: A Global Benchmark for AI-Assisted Surgical Quality Assessment","created":"2025-09-21","cited_by_count":6,"area":null},{"id":"2402.01974","title":"Hypergraph-Transformer (HGT) for Interactive Event Prediction in Laparoscopic and Robotic Surgery","created":"2024-02-03","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":"2506.03082","title":"SG2VID: Scene Graphs Enable Fine-Grained Control for Video Synthesis","created":"2025-06-03","cited_by_count":4,"area":null},{"id":"2506.20254","title":"Recognizing Surgical Phases Anywhere: Few-Shot Test-time Adaptation and Task-graph Guided Refinement","created":"2025-06-25","cited_by_count":4,"area":null},{"id":"2309.07330","title":"Automated Assessment of Critical View of Safety in Laparoscopic Cholecystectomy","created":"2023-09-13","cited_by_count":3,"area":null},{"id":"2407.06795","title":"CycleSAM: Few-Shot Surgical Scene Segmentation with Cycle- and Scene-Consistent Feature Matching","created":"2024-07-09","cited_by_count":3,"area":null},{"id":"2501.09555","title":"Text-driven Adaptation of Foundation Models for Few-shot Surgical Workflow Analysis","created":"2025-01-16","cited_by_count":3,"area":null},{"id":"2502.16459","title":"Deep learning approaches to surgical video segmentation and object detection: A Scoping Review","created":"2025-02-23","cited_by_count":3,"area":null},{"id":"2509.20941","title":"Decoding the Surgical Scene: A Scoping Review of Scene Graphs in Surgery","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2603.12787","title":"Generalized Recognition of Basic Surgical Actions Enables Skill Assessment and Vision-Language-Model-based Surgical Planning","created":"2026-03-13","cited_by_count":3,"area":null},{"id":"2503.03942","title":"SurgiSAM2: Fine-tuning a foundational model for surgical video anatomy segmentation and detection","created":"2025-03-05","cited_by_count":2,"area":null},{"id":"2507.05007","title":"Multi-modal Representations for Fine-grained Multi-label Critical View of Safety Recognition","created":"2025-07-07","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":"2403.06953","title":"Optimizing Latent Graph Representations of Surgical Scenes for Zero-Shot Domain Transfer","created":"2024-03-11","cited_by_count":1,"area":null},{"id":"2502.07008","title":"Early Operative Difficulty Assessment in Laparoscopic Cholecystectomy via Snapshot-Centric Video Analysis","created":"2025-02-10","cited_by_count":1,"area":null},{"id":"2601.13954","title":"DExTeR: Weakly Semi-Supervised Object Detection with Class and Instance Experts for Medical Imaging","created":"2026-01-20","cited_by_count":1,"area":null},{"id":"2603.29962","title":"SurgTEMP: Temporal-Aware Surgical Video Question Answering with Text-guided Visual Memory for Laparoscopic Cholecystectomy","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2502.13883","title":"Multi-view Video-Pose Pretraining for Operating Room Surgical Activity Recognition","created":"2025-02-19","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":"2608.02188","title":"SPIRIT: Spatio-temporal Pairwise Relational Modeling of Instrument-Tissue Interactions for Surgical Action Triplet Recognition","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.15336","title":"SAGE-OR: Semi-supervised Adaptive Scene Graph Generation for Operating Rooms","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2609.27681","title":"CasCVS-Net: A Staged Multi-Task Cascade for Critical View of Safety Assessment","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.31821","title":"A Surgical Foundation Model Reveals Task-Dependent Label Efficiency","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}