{"total":105,"rows":[{"id":"2208.02049","title":"AutoLaparo: A New Dataset of Integrated Multi-tasks for Image-guided Surgical Automation in Laparoscopic Hysterectomy","created":"2022-08-03","cited_by_count":85,"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":"2109.14956","title":"Comparative Validation of Machine Learning Algorithms for Surgical Workflow and Skill Analysis with the HeiChole Benchmark","created":"2021-09-30","cited_by_count":60,"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":"2408.07931","title":"Surgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame Pruning","created":"2024-08-15","cited_by_count":47,"area":null},{"id":"2312.10251","title":"Advancing Surgical VQA with Scene Graph Knowledge","created":"2023-12-15","cited_by_count":41,"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":"2410.00263","title":"Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation","created":"2024-09-30","cited_by_count":39,"area":null},{"id":"2310.11475","title":"Tracking and Mapping in Medical Computer Vision: A Review","created":"2023-10-17","cited_by_count":36,"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":"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":"2207.09899","title":"Labeling instructions matter in biomedical image analysis","created":"2022-07-20","cited_by_count":20,"area":null},{"id":"2503.19740","title":"LEMON: A Large Endoscopic MONocular Dataset and Foundation Model for Perception in Surgical Settings","created":"2025-03-25","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":"2307.11261","title":"SimCol3D -- 3D Reconstruction during Colonoscopy Challenge","created":"2023-07-20","cited_by_count":19,"area":null},{"id":"2203.07345","title":"Federated Cycling (FedCy): Semi-supervised Federated Learning of Surgical Phases","created":"2022-03-14","cited_by_count":18,"area":null},{"id":"2304.13014","title":"Methods and datasets for segmentation of minimally invasive surgical instruments in endoscopic images and videos: A review of the state of the art","created":"2023-04-25","cited_by_count":18,"area":null},{"id":"2301.00452","title":"Human-in-the-loop Embodied Intelligence with Interactive Simulation Environment for Surgical Robot Learning","created":"2023-01-01","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":"2409.01184","title":"PitVis-2023 Challenge: Workflow Recognition in videos of Endoscopic Pituitary Surgery","created":"2024-09-02","cited_by_count":10,"area":null},{"id":"2409.06037","title":"Online 3D reconstruction and dense tracking in endoscopic videos","created":"2024-09-09","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":"2303.12915","title":"Self-distillation for surgical action recognition","created":"2023-03-22","cited_by_count":9,"area":"distill"},{"id":"2309.03048","title":"Exploring Semantic Consistency in Unpaired Image Translation to Generate Data for Surgical Applications","created":"2023-09-06","cited_by_count":9,"area":null},{"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":"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":"2407.11906","title":"SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challenge","created":"2024-07-16","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":"2410.07753","title":"Data Augmentation for Surgical Scene Segmentation with Anatomy-Aware Diffusion Models","created":"2024-10-10","cited_by_count":8,"area":"diffusion"},{"id":"2210.11826","title":"3D Human Pose Estimation in Multi-View Operating Room Videos Using Differentiable Camera Projections","created":"2022-10-21","cited_by_count":7,"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":"2405.08272","title":"VS-Assistant: Versatile Surgery Assistant on the Demand of Surgeons","created":"2024-05-14","cited_by_count":7,"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":"2203.08674","title":"Know your sensORs -- A Modality Study For Surgical Action Classification","created":"2022-03-16","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":"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":"2407.08333","title":"SR-Mamba: Effective Surgical Phase Recognition with State Space Model","created":"2024-07-11","cited_by_count":6,"area":"ssm"},{"id":"2503.13028","title":"Beyond Role-Based Surgical Domain Modeling: Generalizable Re-Identification in the Operating Room","created":"2025-03-17","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":"2209.14647","title":"Bounded Future MS-TCN++ for surgical gesture recognition","created":"2022-09-29","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":"2303.10173","title":"VideoSum: A Python Library for Surgical Video Summarization","created":"2023-02-15","cited_by_count":4,"area":null},{"id":"2306.08720","title":"A Client-server Deep Federated Learning for Cross-domain Surgical Image Segmentation","created":"2023-06-14","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":"2406.19217","title":"Think Step by Step: Chain-of-Gesture Prompting for Error Detection in Robotic Surgical Videos","created":"2024-06-27","cited_by_count":4,"area":"lr"},{"id":"2408.09822","title":"SurgicaL-CD: Generating Surgical Images via Unpaired Image Translation with Latent Consistency Diffusion Models","created":"2024-08-19","cited_by_count":4,"area":"diffusion"},{"id":"2209.01435","title":"A comprehensive survey on recent deep learning-based methods applied to surgical data","created":"2022-09-03","cited_by_count":3,"area":null},{"id":"2212.12719","title":"MURPHY: Relations Matter in Surgical Workflow Analysis","created":"2022-12-24","cited_by_count":3,"area":null},{"id":"2310.01735","title":"Learning Expected Appearances for Intraoperative Registration during Neurosurgery","created":"2023-10-03","cited_by_count":3,"area":null},{"id":"2402.19340","title":"One model to use them all: Training a segmentation model with complementary datasets","created":"2024-02-29","cited_by_count":3,"area":null},{"id":"2411.03695","title":"AMNCutter: Affinity-Attention-Guided Multi-View Normalized Cutter for Unsupervised Surgical Instrument Segmentation","created":"2024-11-06","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":"2504.16612","title":"Federated EndoViT: Pretraining Vision Transformers via Federated Learning on Endoscopic Image Collections","created":"2025-04-23","cited_by_count":3,"area":null},{"id":"2603.24539","title":"CliPPER: Contextual Video-Language Pretraining on Long-form Intraoperative Surgical Procedures for Event Recognition","created":"2026-03-25","cited_by_count":3,"area":null},{"id":"2304.00007","title":"Can We Revitalize Interventional Healthcare with AI-XR Surgical Metaverses?","created":"2023-03-25","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":"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":"2409.19934","title":"Leveraging Pre-trained Models for Robust Federated Learning for Kidney Stone Type Recognition","created":"2024-09-30","cited_by_count":2,"area":null},{"id":"2412.04039","title":"Benchmarking and Enhancing Surgical Phase Recognition Models for Robotic-Assisted Esophagectomy","created":"2024-12-05","cited_by_count":2,"area":null},{"id":"2506.01471","title":"SemiVT-Surge: Semi-Supervised Video Transformer for Surgical Phase Recognition","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2506.04716","title":"Learning dissection trajectories from expert surgical videos via imitation learning with equivariant diffusion","created":"2025-06-05","cited_by_count":2,"area":"diffusion"},{"id":"2508.07968","title":"TrackOR: Towards Personalized Intelligent Operating Rooms Through Robust Tracking","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2509.09327","title":"Exploring Pre-training Across Domains for Few-Shot Surgical Skill Assessment","created":"2025-09-11","cited_by_count":2,"area":null},{"id":"2603.12430","title":"Surg-R1: A Hierarchical Reasoning Foundation Model for Scalable and Interpretable Surgical Decision Support with Multi-Center Clinical Validation","created":"2026-03-12","cited_by_count":2,"area":"lr"},{"id":"2207.13185","title":"Learning-Based Keypoint Registration for Fetoscopic Mosaicking","created":"2022-07-26","cited_by_count":1,"area":null},{"id":"2403.14863","title":"Distribution-informed and wavelength-flexible data-driven photoacoustic oximetry","created":"2024-03-21","cited_by_count":1,"area":null},{"id":"2410.20026","title":"Towards Robust Algorithms for Surgical Phase Recognition via Digital Twin Representation","created":"2024-10-26","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":"2505.09858","title":"Mission Balance: Generating Under-represented Class Samples using Video Diffusion Models","created":"2025-05-14","cited_by_count":1,"area":"diffusion"},{"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":"2507.20881","title":"Endoscopic Depth Estimation Based on Deep Learning: A Survey","created":"2025-07-28","cited_by_count":1,"area":null},{"id":"2510.04772","title":"Federated Learning for Surgical Vision in Appendicitis Classification: Results of the FedSurg EndoVis 2024 Challenge","created":"2025-10-06","cited_by_count":1,"area":null},{"id":"2511.11899","title":"End to End AI System for Surgical Gesture Sequence Recognition and Clinical Outcome Prediction","created":"2025-11-14","cited_by_count":1,"area":null},{"id":"2511.16618","title":"SurgSLOT: Segment Anything in Surgical Videos via Semantic Long-term Tracking","created":"2025-11-20","cited_by_count":1,"area":null},{"id":"2606.22124","title":"Surgical Anatomy Recognition with Context Learning using Foundation Representations","created":"2026-06-20","cited_by_count":1,"area":null},{"id":"2606.31245","title":"HyperVLP: Enhancing Hierarchical Surgical Video-Language Pre-training in Hyperbolic Space","created":"2026-06-30","cited_by_count":1,"area":"mllm"},{"id":"2111.05408","title":"Robust deep learning-based semantic organ segmentation in hyperspectral images","created":"2021-11-09","cited_by_count":0,"area":null},{"id":"2206.05935","title":"Fluorescence angiography classification in colorectal surgery -- A preliminary report","created":"2022-06-13","cited_by_count":0,"area":null},{"id":"2212.06809","title":"Real-Time Artificial Intelligence Assistance for Safe Laparoscopic Cholecystectomy: Early-Stage Clinical Evaluation","created":"2022-12-13","cited_by_count":0,"area":null},{"id":"2306.14780","title":"INDEXITY: a web-based collaborative tool for medical video annotation","created":"2023-06-26","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":"2309.13404","title":"Weakly Supervised YOLO Network for Surgical Instrument Localization in Endoscopic Videos","created":"2023-09-23","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":"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":"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":"2507.06643","title":"Learning from Sparse Point Labels for Dense Carcinosis Localization in Advanced Ovarian Cancer Assessment","created":"2025-07-09","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":"2512.21284","title":"Toward Real-Time Surgical Scene Segmentation via a Spike-Driven Video Transformer with Spike-Informed Pretraining","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2602.02850","title":"Self-Supervised Uncalibrated Multi-View Video Anonymization in the Operating Room","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.17310","title":"Attachment Anchors: A Novel Framework for Laparoscopic Grasping Point Prediction in Colorectal Surgery","created":"2026-02-19","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":"2604.20319","title":"SurgCoT: Advancing Spatiotemporal Reasoning in Surgical Videos through a Chain-of-Thought Benchmark","created":"2026-04-22","cited_by_count":0,"area":"lr"},{"id":"2605.12026","title":"Spectral Vision Transformer for Efficient Tokenization with Limited Data","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.30657","title":"AI for Quality Assurance in the Operating Room","created":"2026-06-16","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},{"id":"2608.09302","title":"Bootstrapping Vision-Language Model for Hysteroscopic Surgical Scene Segmentation","created":"2026-08-10","cited_by_count":0,"area":"mllm"}],"next_cursor":"100"}