{"total":66,"rows":[{"id":"2109.03223","title":"Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos","created":"2021-09-07","cited_by_count":141,"area":null},{"id":"2401.11174","title":"Pixel-Wise Recognition for Holistic Surgical Scene Understanding","created":"2024-01-20","cited_by_count":49,"area":null},{"id":"2204.04746","title":"CholecTriplet2021: A benchmark challenge for surgical action triplet recognition","created":"2022-04-10","cited_by_count":44,"area":null},{"id":"2312.11250","title":"Challenges in Multi-centric Generalization: Phase and Step Recognition in Roux-en-Y Gastric Bypass Surgery","created":"2023-12-18","cited_by_count":40,"area":null},{"id":"2212.04582","title":"Towards Holistic Surgical Scene Understanding","created":"2022-12-08","cited_by_count":33,"area":null},{"id":"2406.07471","title":"OphNet: A Large-Scale Video Benchmark for Ophthalmic Surgical Workflow Understanding","created":"2024-06-11","cited_by_count":32,"area":null},{"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":"2211.16963","title":"Rendezvous in Time: An Attention-based Temporal Fusion approach for Surgical Triplet Recognition","created":"2022-11-30","cited_by_count":27,"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":"2204.05235","title":"Data Splits and Metrics for Method Benchmarking on Surgical Action Triplet Datasets","created":"2022-04-11","cited_by_count":23,"area":null},{"id":"2302.06294","title":"CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection","created":"2023-02-13","cited_by_count":23,"area":null},{"id":"2307.09548","title":"Surgical Action Triplet Detection by Mixed Supervised Learning of Instrument-Tissue Interactions","created":"2023-07-18","cited_by_count":23,"area":null},{"id":"2303.13293","title":"LABRAD-OR: Lightweight Memory Scene Graphs for Accurate Bimodal Reasoning in Dynamic Operating Rooms","created":"2023-03-23","cited_by_count":21,"area":null},{"id":"2202.08141","title":"FUN-SIS: a Fully UNsupervised approach for Surgical Instrument Segmentation","created":"2022-02-16","cited_by_count":20,"area":null},{"id":"2312.07352","title":"CholecTrack20: A Multi-Perspective Tracking Dataset for Surgical Tools","created":"2023-12-12","cited_by_count":17,"area":null},{"id":"2202.13402","title":"Concept Graph Neural Networks for Surgical Video Understanding","created":"2022-02-27","cited_by_count":13,"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":"2505.24287","title":"EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity Understanding","created":"2025-05-30","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":"2303.12915","title":"Self-distillation for surgical action recognition","created":"2023-03-22","cited_by_count":9,"area":"distill"},{"id":"2301.07053","title":"Preserving Privacy in Surgical Video Analysis Using Artificial Intelligence: A Deep Learning Classifier to Identify Out-of-Body Scenes in Endoscopic Videos","created":"2023-01-17","cited_by_count":8,"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":"2404.00322","title":"Instrument-tissue Interaction Detection Framework for Surgical Video Understanding","created":"2024-03-30","cited_by_count":8,"area":null},{"id":"2411.01647","title":"Optical Flow Representation Alignment Mamba Diffusion Model for Medical Video Generation","created":"2024-11-03","cited_by_count":8,"area":"diffusion"},{"id":"2502.14886","title":"Surgical Scene Understanding in the Era of Foundation AI Models: A Comprehensive Review","created":"2025-02-16","cited_by_count":8,"area":null},{"id":"2105.04642","title":"SUPR-GAN: SUrgical PRediction GAN for Event Anticipation in Laparoscopic and Robotic Surgery","created":"2021-05-10","cited_by_count":7,"area":null},{"id":"2112.13815","title":"Temporally Constrained Neural Networks (TCNN): A framework for semi-supervised video semantic segmentation","created":"2021-12-27","cited_by_count":6,"area":null},{"id":"2407.09230","title":"Surgical Text-to-Image Generation","created":"2024-07-12","cited_by_count":6,"area":null},{"id":"2302.10834","title":"Weakly Supervised Temporal Convolutional Networks for Fine-grained Surgical Activity Recognition","created":"2023-02-21","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":"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":"2209.08647","title":"Why Deep Surgical Models Fail?: Revisiting Surgical Action Triplet Recognition through the Lens of Robustness","created":"2022-09-18","cited_by_count":4,"area":null},{"id":"2211.15327","title":"Task-Aware Asynchronous Multi-Task Model with Class Incremental Contrastive Learning for Surgical Scene Understanding","created":"2022-11-28","cited_by_count":4,"area":null},{"id":"2406.13210","title":"Surgical Triplet Recognition via Diffusion Model","created":"2024-06-19","cited_by_count":4,"area":"diffusion"},{"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":"2509.12893","title":"MEJO: MLLM-Engaged Surgical Triplet Recognition via Inter- and Intra-Task Joint Optimization","created":"2025-09-16","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":"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":"2203.04301","title":"Live Laparoscopic Video Retrieval with Compressed Uncertainty","created":"2022-03-08","cited_by_count":2,"area":null},{"id":"2308.12789","title":"Robotic Scene Segmentation with Memory Network for Runtime Surgical Context Inference","created":"2023-08-24","cited_by_count":2,"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":"2411.07619","title":"Artificial Intelligence for Biomedical Video Generation","created":"2024-11-12","cited_by_count":2,"area":null},{"id":"2501.15326","title":"Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised Data","created":"2025-01-25","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":"2603.16822","title":"Surg$\\Sigma$: A Spectrum of Large-Scale Multimodal Data and Foundation Models for Surgical Intelligence","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2507.05011","title":"DARIL: When Imitation Learning outperforms Reinforcement Learning in Surgical Action Planning","created":"2025-07-07","cited_by_count":1,"area":"wm"},{"id":"2509.18802","title":"Surgical Video Understanding with Label Interpolation","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2511.00643","title":"Grounding Surgical Action Triplets with Instrument Instance Segmentation: A Dataset and Target-Aware Fusion Approach","created":"2025-11-01","cited_by_count":1,"area":null},{"id":"2603.29966","title":"Scaling Video Pretraining for Surgical Foundation Models","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2608.16469","title":"Sterilizable Scene Graph Generation for Operating Rooms","created":"2026-08-17","cited_by_count":1,"area":null},{"id":"2506.01980","title":"Surgical Foundation Model Leveraging Compression and Entropy Maximization for Image-Guided Surgical Assistance","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2507.19592","title":"SurgPIS: Surgical-instrument-level Instances and Part-level Semantics for Weakly-supervised Part-aware Instance Segmentation","created":"2025-07-25","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":"2510.24332","title":"Sound Source Localization for Spatial Mapping of Surgical Actions in Dynamic Scenes","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2511.15159","title":"Generating Natural-Language Surgical Feedback: From Structured Representation to Domain-Grounded Evaluation","created":"2025-11-19","cited_by_count":0,"area":null},{"id":"2601.12312","title":"CurConMix+: A Unified Spatio-Temporal Framework for Hierarchical Surgical Workflow Understanding","created":"2026-01-18","cited_by_count":0,"area":null},{"id":"2604.07577","title":"Event-Level Detection of Surgical Instrument Handovers in Videos with Interpretable Vision Models","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2606.26634","title":"Temporally Consistent Label Interpolation for Robust Surgical Multi-Task Learning under Challenging Conditions","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.19889","title":"Latent-Action-Guided Video-Language Feature Learning for Surgical Instrument-Tissue Interaction Recognition","created":"2026-07-22","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":"2608.17935","title":"Beyond Instrument Motion: Recognizing Tissue Tension Toward Surgical Skill Assessment","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.22972","title":"Optimize Surgical Triplet Recognition: A Knowledge-Driven Mixture-of-Experts Solution","created":"2026-08-24","cited_by_count":0,"area":"moe"},{"id":"2608.23344","title":"Towards Actionable Surgical Team Dynamics: from Teamwork to Counterfactual Annotations","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.08543","title":"STSG-VQA: Evidence-Grounded Temporal Question Answering from Surgical Spatio-Temporal Scene Graphs","created":"2026-09-08","cited_by_count":0,"area":"lr"}],"next_cursor":null}