{"total":60,"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":"2307.15220","title":"Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures","created":"2023-07-27","cited_by_count":68,"area":null},{"id":"2301.03505","title":"Advances in Medical Image Analysis with Vision Transformers: A Comprehensive Review","created":"2023-01-09","cited_by_count":62,"area":null},{"id":"2305.08989","title":"LoViT: Long Video Transformer for Surgical Phase Recognition","created":"2023-05-15","cited_by_count":56,"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":"2207.00449","title":"Dissecting Self-Supervised Learning Methods for Surgical Computer Vision","created":"2022-07-01","cited_by_count":48,"area":null},{"id":"2202.12165","title":"Transformers in Medical Image Analysis: A Review","created":"2022-02-24","cited_by_count":41,"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":"2203.15251","title":"Exploring Intra- and Inter-Video Relation for Surgical Semantic Scene Segmentation","created":"2022-03-29","cited_by_count":27,"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":"2309.14538","title":"Dynamic Scene Graph Representation for Surgical Video","created":"2023-09-25","cited_by_count":21,"area":null},{"id":"2107.04810","title":"Not End-to-End: Explore Multi-Stage Architecture for Online Surgical Phase Recognition","created":"2021-07-10","cited_by_count":20,"area":null},{"id":"2203.07976","title":"On the Pitfalls of Batch Normalization for End-to-End Video Learning: A Study on Surgical Workflow Analysis","created":"2022-03-15","cited_by_count":19,"area":null},{"id":"2305.13961","title":"Metrics Matter in Surgical Phase Recognition","created":"2023-05-23","cited_by_count":14,"area":null},{"id":"2202.08199","title":"Less is More: Surgical Phase Recognition from Timestamp Supervision","created":"2022-02-16","cited_by_count":13,"area":null},{"id":"2408.10538","title":"Surgical Workflow Recognition and Blocking Effectiveness Detection in Laparoscopic Liver Resections with Pringle Maneuver","created":"2024-08-20","cited_by_count":12,"area":null},{"id":"2409.04732","title":"VidLPRO: A $\\underline{Vid}$eo-$\\underline{L}$anguage $\\underline{P}$re-training Framework for $\\underline{Ro}$botic and Laparoscopic Surgery","created":"2024-09-07","cited_by_count":12,"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":"2303.12915","title":"Self-distillation for surgical action recognition","created":"2023-03-22","cited_by_count":9,"area":"distill"},{"id":"2403.16736","title":"Creating a Digital Twin of Spinal Surgery: A Proof of Concept","created":"2024-03-25","cited_by_count":9,"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":"2407.17361","title":"MuST: Multi-Scale Transformers for Surgical Phase Recognition","created":"2024-07-24","cited_by_count":8,"area":null},{"id":"2208.00902","title":"Retrieval of surgical phase transitions using reinforcement learning","created":"2022-08-01","cited_by_count":7,"area":null},{"id":"2203.08674","title":"Know your sensORs -- A Modality Study For Surgical Action Classification","created":"2022-03-16","cited_by_count":6,"area":null},{"id":"2203.09230","title":"Surgical Workflow Recognition: from Analysis of Challenges to Architectural Study","created":"2022-03-17","cited_by_count":6,"area":null},{"id":"2209.01148","title":"ARST: Auto-Regressive Surgical Transformer for Phase Recognition from Laparoscopic Videos","created":"2022-09-02","cited_by_count":6,"area":null},{"id":"2307.09997","title":"TUNeS: A Temporal U-Net with Self-Attention for Video-based Surgical Phase Recognition","created":"2023-07-19","cited_by_count":6,"area":null},{"id":"2311.12603","title":"Surgical Temporal Action-aware Network with Sequence Regularization for Phase Recognition","created":"2023-11-21","cited_by_count":6,"area":null},{"id":"2407.08333","title":"SR-Mamba: Effective Surgical Phase Recognition with State Space Model","created":"2024-07-11","cited_by_count":6,"area":"ssm"},{"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":"2212.12719","title":"MURPHY: Relations Matter in Surgical Workflow Analysis","created":"2022-12-24","cited_by_count":3,"area":null},{"id":"2409.06217","title":"DACAT: Dual-stream Adaptive Clip-aware Time Modeling for Robust Online Surgical Phase Recognition","created":"2024-09-10","cited_by_count":3,"area":null},{"id":"2409.12108","title":"SPRMamba: Surgical Phase Recognition for Endoscopic Submucosal Dissection with Mamba","created":"2024-09-18","cited_by_count":3,"area":"ssm"},{"id":"2401.11644","title":"Friends Across Time: Multi-Scale Action Segmentation Transformer for Surgical Phase Recognition","created":"2024-01-22","cited_by_count":2,"area":null},{"id":"2403.06200","title":"SuPRA: Surgical Phase Recognition and Anticipation for Intra-Operative Planning","created":"2024-03-10","cited_by_count":2,"area":null},{"id":"2405.02571","title":"ViTALS: Vision Transformer for Action Localization in Surgical Nephrectomy","created":"2024-05-04","cited_by_count":2,"area":null},{"id":"2409.12467","title":"SurgPLAN++: Universal Surgical Phase Localization Network for Online and Offline Inference","created":"2024-09-19","cited_by_count":2,"area":null},{"id":"2502.07431","title":"ArthroPhase: A Novel Dataset and Method for Phase Recognition in Arthroscopic Video","created":"2025-02-11","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":"2504.18954","title":"Surgeons vs. Computer Vision: A comparative analysis on surgical phase recognition capabilities","created":"2025-04-26","cited_by_count":2,"area":null},{"id":"2205.03028","title":"Quantification of Robotic Surgeries with Vision-Based Deep Learning","created":"2022-05-06","cited_by_count":1,"area":null},{"id":"2306.16879","title":"Surgical Phase and Instrument Recognition: How to identify appropriate Dataset Splits","created":"2023-06-29","cited_by_count":1,"area":null},{"id":"2402.17903","title":"Surgment: Segmentation-enabled Semantic Search and Creation of Visual Question and Feedback to Support Video-Based Surgery Learning","created":"2024-02-27","cited_by_count":1,"area":null},{"id":"2502.03430","title":"A Temporal Convolutional Network-Based Approach and a Benchmark Dataset for Colonoscopy Video Temporal Segmentation","created":"2025-02-05","cited_by_count":1,"area":null},{"id":"2206.07198","title":"Surgical Phase Recognition in Laparoscopic Cholecystectomy","created":"2022-06-14","cited_by_count":0,"area":null},{"id":"2303.09648","title":"Shifted-Windows Transformers for the Detection of Cerebral Aneurysms in Microsurgery","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2308.02529","title":"Hierarchical Semi-Supervised Learning Framework for Surgical Gesture Segmentation and Recognition Based on Multi-Modality Data","created":"2023-07-31","cited_by_count":0,"area":null},{"id":"2309.05209","title":"Phase-Specific Augmented Reality Guidance for Microscopic Cataract Surgery Using Long-Short Spatiotemporal Aggregation Transformer","created":"2023-09-11","cited_by_count":0,"area":null},{"id":"2310.17209","title":"Weakly-Supervised Surgical Phase Recognition","created":"2023-10-26","cited_by_count":0,"area":null},{"id":"2406.18481","title":"Robust Surgical Phase Recognition From Annotation Efficient Supervision","created":"2024-06-26","cited_by_count":0,"area":null},{"id":"2503.10216","title":"CoStoDet-DDPM: Collaborative Training of Stochastic and Deterministic Models Improves Surgical Workflow Anticipation and Recognition","created":"2025-03-13","cited_by_count":0,"area":"diffusion"},{"id":"2505.13746","title":"ReSW-VL: Representation Learning for Surgical Workflow Analysis Using Vision-Language Model","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2507.03295","title":"CPKD: Clinical Prior Knowledge-Constrained Diffusion Models for Surgical Phase Recognition in Endoscopic Submucosal Dissection","created":"2025-07-04","cited_by_count":0,"area":"diffusion"},{"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":"2603.24897","title":"SurgPhase: Time efficient pituitary tumor surgery phase recognition via an interactive web platform","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2605.14889","title":"SurgicalMamba: Dual-Path SSD with State Regramming for Online Surgical Phase Recognition","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.26483","title":"Clinically-Grounded Counterfactual Reasoning for Medical Video Diagnosis","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2608.01058","title":"Extended KAFR: A kinematic-adaptive paradigm for the efficient analysis of surgical video","created":"2026-08-02","cited_by_count":0,"area":null}],"next_cursor":null}