{"total":51,"rows":[{"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":"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":"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":"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":"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":"2312.07352","title":"CholecTrack20: A Multi-Perspective Tracking Dataset for Surgical Tools","created":"2023-12-12","cited_by_count":17,"area":null},{"id":"2410.21348","title":"Large Language Model Benchmarks in Medical Tasks","created":"2024-10-28","cited_by_count":17,"area":null},{"id":"2401.15753","title":"An objective comparison of methods for augmented reality in laparoscopic liver resection by preoperative-to-intraoperative image fusion","created":"2024-01-28","cited_by_count":16,"area":null},{"id":"2208.02611","title":"Surgical Skill Assessment via Video Semantic Aggregation","created":"2022-08-04","cited_by_count":13,"area":null},{"id":"2501.09209","title":"Surgical Visual Understanding (SurgVU) Dataset","created":"2025-01-16","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":"2506.07603","title":"SurgBench: A Unified Large-Scale Benchmark for Surgical Video Analysis","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2511.06549","title":"Video Dataset for Surgical Phase, Keypoint, and Instrument Recognition in Laparoscopic Surgery (PhaKIR)","created":"2025-11-09","cited_by_count":9,"area":null},{"id":"2312.05968","title":"Jumpstarting Surgical Computer Vision","created":"2023-12-10","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":"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":"2507.16559","title":"Comparative validation of surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation in endoscopy: Results of the PhaKIR 2024 challenge","created":"2025-07-22","cited_by_count":8,"area":null},{"id":"2402.06985","title":"OSSAR: Towards Open-Set Surgical Activity Recognition in Robot-assisted Surgery","created":"2024-02-10","cited_by_count":7,"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":"2212.04448","title":"Objective Surgical Skills Assessment and Tool Localization: Results from the MICCAI 2021 SimSurgSkill Challenge","created":"2022-12-08","cited_by_count":6,"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":"2309.11718","title":"CPR-Coach: Recognizing Composite Error Actions based on Single-class Training","created":"2023-09-21","cited_by_count":4,"area":null},{"id":"2506.21330","title":"Holistic Surgical Phase Recognition with Hierarchical Input Dependent State Space Models","created":"2025-06-26","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":"2206.12320","title":"PoCaP Corpus: A Multimodal Dataset for Smart Operating Room Speech Assistant using Interventional Radiology Workflow Analysis","created":"2022-06-24","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":"2507.00209","title":"SurgiSR4K: A High-Resolution Endoscopic Video Dataset for Robotic-Assisted Minimally Invasive Procedures","created":"2025-06-30","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":"2603.27460","title":"Project Imaging-X: A Survey of 1000+ Open-Access Medical Imaging Datasets for Foundation Model Development","created":"2026-03-29","cited_by_count":2,"area":null},{"id":"2606.25905","title":"SurgAtlas: A Large-Scale Surgical Video-Language Dataset with 2,391 Hours of Open and Minimally Invasive Surgery","created":"2026-06-24","cited_by_count":2,"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":"2506.08258","title":"Surgeons Awareness, Expectations, and Involvement with Artificial Intelligence: a Survey Pre and Post the GPT Era","created":"2025-06-09","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":"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":"2511.05059","title":"SurgiATM: A Physics-Guided Plug-and-Play Model for Deep Learning-Based Smoke Removal in Laparoscopic Surgery","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2512.02188","title":"RobustSurg: Tackling domain generalisation for out-of-distribution surgical scene segmentation","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2603.00108","title":"SurgFusion-Net: Diversified Adaptive Multimodal Fusion Network for Surgical Skill Assessment","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2604.01371","title":"AffordTissue: Dense Affordance Prediction for Tool-Action Specific Tissue Interaction","created":"2026-04-01","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":"2606.13332","title":"OR-Action: Multi-Role Video Understanding with Fine-Grained Actions","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.31007","title":"Dense Structural Priors for Sparse Functional Landmark Localization in Surgical Videos","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2608.04676","title":"SurgNarrator: A Generative Retrieval Framework for Surgical Video Understanding","created":"2026-08-05","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":"2608.20154","title":"Artificial Intelligence for Workflow Analysis in Colorectal Surgery: A Multicentric, Cross-Procedural Development and Generalization Study","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2609.12409","title":"OphBiWSSD: Scaling Temporal Action Localization in Ophthalmic Surgeries with Bidirectional Weight-tied State Space Duality","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.23067","title":"LD-RSVIS: A Large-Scale and Diverse Benchmark for Referring Surgical Video Instrument Segmentation","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.27139","title":"A Hierarchy-Aware Video-Language Model Evaluation and Hyperbolic Baseline for Surgery","created":"2026-09-22","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},{"id":"2610.14512","title":"Spatiotemporal Recognition of Abdominal Wall Layers During Optical Trocar Entry","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}