{"total":126,"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":"2103.09712","title":"Trans-SVNet: Accurate Phase Recognition from Surgical Videos via Hybrid Embedding Aggregation Transformer","created":"2021-03-17","cited_by_count":94,"area":null},{"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":"2103.16327","title":"Temporal Memory Relation Network for Workflow Recognition from Surgical Video","created":"2021-03-30","cited_by_count":66,"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":"2203.11937","title":"4D-OR: Semantic Scene Graphs for OR Domain Modeling","created":"2022-03-22","cited_by_count":49,"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":"2204.04746","title":"CholecTriplet2021: A benchmark challenge for surgical action triplet recognition","created":"2022-04-10","cited_by_count":44,"area":null},{"id":"2102.12218","title":"Multi-Task Temporal Convolutional Networks for Joint Recognition of Surgical Phases and Steps in Gastric Bypass Procedures","created":"2021-02-24","cited_by_count":42,"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":"2212.04155","title":"Latent Graph Representations for Critical View of Safety Assessment","created":"2022-12-08","cited_by_count":37,"area":null},{"id":"2208.03392","title":"Federated Learning for Medical Applications: A Taxonomy, Current Trends, Challenges, and Future Research Directions","created":"2022-08-05","cited_by_count":35,"area":null},{"id":"2212.04582","title":"Towards Holistic Surgical Scene Understanding","created":"2022-12-08","cited_by_count":33,"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":"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":"2102.00027","title":"Gesture Recognition in Robotic Surgery: a Review","created":"2021-01-29","cited_by_count":23,"area":null},{"id":"2102.09528","title":"Image Compositing for Segmentation of Surgical Tools without Manual Annotations","created":"2021-02-18","cited_by_count":23,"area":null},{"id":"2111.11044","title":"Exploring Segment-level Semantics for Online Phase Recognition from Surgical Videos","created":"2021-11-22","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":"2103.17204","title":"Long-Term Temporally Consistent Unpaired Video Translation from Simulated Surgical 3D Data","created":"2021-03-31","cited_by_count":21,"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":"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":"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":"2312.07352","title":"CholecTrack20: A Multi-Perspective Tracking Dataset for Surgical Tools","created":"2023-12-12","cited_by_count":17,"area":null},{"id":"2411.12783","title":"Med-2E3: A 2D-Enhanced 3D Medical Multimodal Large Language Model","created":"2024-11-19","cited_by_count":15,"area":"mllm"},{"id":"2102.13644","title":"Surgical Visual Domain Adaptation: Results from the MICCAI 2020 SurgVisDom Challenge","created":"2021-02-26","cited_by_count":14,"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":"2404.07031","title":"ORacle: Large Vision-Language Models for Knowledge-Guided Holistic OR Domain Modeling","created":"2024-04-10","cited_by_count":14,"area":"mllm"},{"id":"2202.08199","title":"Less is More: Surgical Phase Recognition from Timestamp Supervision","created":"2022-02-16","cited_by_count":13,"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":"2103.00586","title":"A Kinematic Bottleneck Approach For Pose Regression of Flexible Surgical Instruments directly from Images","created":"2021-02-28","cited_by_count":11,"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":"2106.05923","title":"FetReg: Placental Vessel Segmentation and Registration in Fetoscopy Challenge Dataset","created":"2021-06-10","cited_by_count":9,"area":null},{"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":"2103.09276","title":"Co-Generation and Segmentation for Generalized Surgical Instrument Segmentation on Unlabelled Data","created":"2021-03-16","cited_by_count":8,"area":null},{"id":"2106.10916","title":"Surgical data science for safe cholecystectomy: a protocol for segmentation of hepatocystic anatomy and assessment of the critical view of safety","created":"2021-06-21","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":"2312.05968","title":"Jumpstarting Surgical Computer Vision","created":"2023-12-10","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":"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":"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":"2106.15309","title":"Multimodal Semantic Scene Graphs for Holistic Modeling of Surgical Procedures","created":"2021-06-09","cited_by_count":6,"area":null},{"id":"2108.03534","title":"Reducing Annotating Load: Active Learning with Synthetic Images in Surgical Instrument Segmentation","created":"2021-08-07","cited_by_count":6,"area":null},{"id":"2205.06416","title":"Video-based assessment of intraoperative surgical skill","created":"2022-05-13","cited_by_count":6,"area":null},{"id":"2208.03824","title":"Towards Graph Representation Learning Based Surgical Workflow Anticipation","created":"2022-08-07","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":"2209.14647","title":"Bounded Future MS-TCN++ for surgical gesture recognition","created":"2022-09-29","cited_by_count":5,"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":"2504.02799","title":"Systematic Evaluation of Large Vision-Language Models for Surgical Artificial Intelligence","created":"2025-04-03","cited_by_count":5,"area":"mllm"},{"id":"2102.12308","title":"\"Train one, Classify one, Teach one\" -- Cross-surgery transfer learning for surgical step recognition","created":"2021-02-24","cited_by_count":4,"area":null},{"id":"2203.00737","title":"Runtime Detection of Executional Errors in Robot-Assisted Surgery","created":"2022-03-01","cited_by_count":4,"area":null},{"id":"2207.09664","title":"Pseudo-label Guided Cross-video Pixel Contrast for Robotic Surgical Scene Segmentation with Limited Annotations","created":"2022-07-20","cited_by_count":4,"area":null},{"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":"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":"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":"2304.14589","title":"Uncertainty-aware Self-supervised Learning for Cross-domain Technical Skill Assessment in Robot-assisted Surgery","created":"2023-04-28","cited_by_count":3,"area":null},{"id":"2406.15920","title":"SEDMamba: Enhancing Selective State Space Modelling with Bottleneck Mechanism and Fine-to-Coarse Temporal Fusion for Efficient Error Detection in Robot-Assisted Surgery","created":"2024-06-22","cited_by_count":3,"area":"ssm"},{"id":"2408.14789","title":"Revisiting Surgical Instrument Segmentation Without Human Intervention: A Graph Partitioning View","created":"2024-08-27","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":"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":"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":"2505.12890","title":"Specialized Foundation Models for Intelligent Operating Rooms","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2508.08764","title":"CARES: Collaborative Agentic Reasoning for Error Detection in Surgery","created":"2025-08-12","cited_by_count":3,"area":"agents"},{"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":"2603.24539","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":"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":"2306.08961","title":"Self-Knowledge Distillation for Surgical Phase Recognition","created":"2023-06-15","cited_by_count":2,"area":"distill"},{"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":"2412.06454","title":"Adaptive Graph Learning from Spatial Information for Surgical Workflow Anticipation","created":"2024-12-09","cited_by_count":2,"area":null},{"id":"2504.19918","title":"Enhancing Surgical Documentation through Multimodal Visual-Temporal Transformers and Generative AI","created":"2025-04-28","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":"2507.22059","title":"StepAL: Step-aware Active Learning for Cataract Surgical Videos","created":"2025-07-29","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":"2601.21971","title":"Supervised Mixture-of-Experts for Surgical Grasping and Retraction","created":"2026-01-29","cited_by_count":2,"area":"moe"},{"id":"2603.26720","title":"SutureFormer: Learning Surgical Trajectories via Goal-conditioned Offline RL in Pixel Space","created":"2026-03-19","cited_by_count":2,"area":"offlinerl"},{"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":"2402.14461","title":"S^2Former-OR: Single-Stage Bi-Modal Transformer for Scene Graph Generation in OR","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2410.11703","title":"Robotic Arm Platform for Multi-View Image Acquisition and 3D Reconstruction in Minimally Invasive Surgery","created":"2024-10-15","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":"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":"2510.07345","title":"Mitigating Surgical Data Imbalance with Dual-Prediction Video Diffusion Model","created":"2025-10-07","cited_by_count":1,"area":"diffusion"},{"id":"2602.17473","title":"4D Monocular Surgical Reconstruction under Arbitrary Camera Motions","created":"2026-02-19","cited_by_count":1,"area":null},{"id":"2603.09466","title":"TopoOR: A Unified Topological Scene Representation for the Operating Room","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2604.00784","title":"An Approach to Enriching Surgical Video Datasets for Fine-Grained Spatial-Temporal Understanding of Vision-Language Models","created":"2026-04-01","cited_by_count":1,"area":"mllm"},{"id":"2206.07198","title":"Surgical Phase Recognition in Laparoscopic Cholecystectomy","created":"2022-06-14","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":"2303.18106","title":"Automatic Detection of Out-of-body Frames in Surgical Videos for Privacy Protection Using Self-supervised Learning and Minimal Labels","created":"2023-03-31","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":"2506.14303","title":"orGAN: A Synthetic Data Augmentation Pipeline for Simultaneous Generation of Surgical Images and Ground Truth Labels","created":"2025-06-17","cited_by_count":0,"area":null}],"next_cursor":"100"}