{"total":141,"rows":[{"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":"2110.01406","title":"MedPerf: Open Benchmarking Platform for Medical Artificial Intelligence using Federated Evaluation","created":"2021-09-29","cited_by_count":88,"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":"2103.03873","title":"OperA: Attention-Regularized Transformers for Surgical Phase Recognition","created":"2021-03-05","cited_by_count":60,"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":"2203.11937","title":"4D-OR: Semantic Scene Graphs for OR Domain Modeling","created":"2022-03-22","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":"2405.10075","title":"HecVL: Hierarchical Video-Language Pretraining for Zero-shot Surgical Phase Recognition","created":"2024-05-16","cited_by_count":42,"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":"2212.04155","title":"Latent Graph Representations for Critical View of Safety Assessment","created":"2022-12-08","cited_by_count":37,"area":null},{"id":"2408.07981","title":"LLaVA-Surg: Towards Multimodal Surgical Assistant via Structured Surgical Video Learning","created":"2024-08-15","cited_by_count":34,"area":"mllm"},{"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":"2408.03867","title":"Surgformer: Surgical Transformer with Hierarchical Temporal Attention for Surgical Phase Recognition","created":"2024-08-07","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":"2403.05949","title":"General surgery vision transformer: A video pre-trained foundation model for general surgery","created":"2024-03-09","cited_by_count":25,"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":"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":"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":"2308.12394","title":"Self-Supervised Learning for Endoscopic Video Analysis","created":"2023-08-23","cited_by_count":22,"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":"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":"2405.19644","title":"EgoSurgery-Phase: A Dataset of Surgical Phase Recognition from Egocentric Open Surgery Videos","created":"2024-05-30","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":"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":"2509.10555","title":"SurgLaVi: Large-Scale Hierarchical Dataset for Surgical Vision-Language Representation Learning","created":"2025-09-09","cited_by_count":16,"area":"mllm"},{"id":"2305.13961","title":"Metrics Matter in Surgical Phase Recognition","created":"2023-05-23","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":"2205.02805","title":"An Empirical Study on Activity Recognition in Long Surgical Videos","created":"2022-05-05","cited_by_count":13,"area":null},{"id":"2311.09965","title":"SurgPLAN: Surgical Phase Localization Network for Phase Recognition","created":"2023-11-16","cited_by_count":12,"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":"2109.13593","title":"Efficient Global-Local Memory for Real-time Instrument Segmentation of Robotic Surgical Video","created":"2021-09-28","cited_by_count":10,"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":"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":"2307.14241","title":"DisguisOR: Holistic Face Anonymization for the Operating Room","created":"2023-07-26","cited_by_count":9,"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":"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":"2208.00902","title":"Retrieval of surgical phase transitions using reinforcement learning","created":"2022-08-01","cited_by_count":7,"area":null},{"id":"2305.11451","title":"SurgMAE: Masked Autoencoders for Long Surgical Video Analysis","created":"2023-05-19","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":"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":"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":"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":"2306.08859","title":"SF-TMN: SlowFast Temporal Modeling Network for Surgical Phase Recognition","created":"2023-06-15","cited_by_count":5,"area":null},{"id":"2307.11081","title":"GLSFormer: Gated - Long, Short Sequence Transformer for Step Recognition in Surgical Videos","created":"2023-07-20","cited_by_count":5,"area":null},{"id":"2312.00593","title":"Event Recognition in Laparoscopic Gynecology Videos with Hybrid Transformers","created":"2023-12-01","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":"2411.18018","title":"Neural Finite-State Machines for Surgical Phase Recognition","created":"2024-11-27","cited_by_count":5,"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":"2412.18849","title":"SWAG: Long-term Surgical Workflow Prediction with Generative-based Anticipation","created":"2024-12-25","cited_by_count":4,"area":null},{"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":"2111.04733","title":"Real-time landmark detection for precise endoscopic submucosal dissection via shape-aware relation network","created":"2021-11-08","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":"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":"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":"2409.20083","title":"SurgPETL: Parameter-Efficient Image-to-Surgical-Video Transfer Learning for Surgical Phase Recognition","created":"2024-09-30","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":"2505.01766","title":"Multimodal Graph Representation Learning for Robust Surgical Workflow Recognition with Adversarial Feature Disentanglement","created":"2025-05-03","cited_by_count":3,"area":null},{"id":"2510.16371","title":"Cataract-LMM Large-Scale Multi-Source Multi-Task Benchmark for Deep Learning in Surgical Video Analysis","created":"2025-10-18","cited_by_count":3,"area":null},{"id":"2605.29368","title":"SURGENT: A Surgical Multi-Agent Assistance System Across the Perioperative Workflow","created":"2026-05-28","cited_by_count":3,"area":"agents"},{"id":"2203.04301","title":"Live Laparoscopic Video Retrieval with Compressed Uncertainty","created":"2022-03-08","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":"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":"2501.11153","title":"Efficient Frame Extraction: A Novel Approach Through Frame Similarity and Surgical Tool Tracking for Video Segmentation","created":"2025-01-19","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":"2503.00695","title":"MoSFormer: Augmenting Temporal Context with Memory of Surgery for Surgical Phase Recognition","created":"2025-03-02","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":"2506.01471","title":"SemiVT-Surge: Semi-Supervised Video Transformer for Surgical Phase Recognition","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2507.22059","title":"StepAL: Step-aware Active Learning for Cataract Surgical Videos","created":"2025-07-29","cited_by_count":2,"area":null},{"id":"2606.15647","title":"Towards Next-Generation Healthcare: A Survey of Medical Embodied AI for Perception, Decision-Making, and Action","created":"2026-04-05","cited_by_count":2,"area":null},{"id":"2203.04752","title":"Human Gaze Guided Attention for Surgical Activity Recognition","created":"2022-03-09","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":"2310.13097","title":"A Multi-Stage Temporal Convolutional Network for Volleyball Jumps Classification Using a Waist-Mounted IMU","created":"2023-10-19","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":"2403.19786","title":"Zero-shot Prompt-based Video Encoder for Surgical Gesture Recognition","created":"2024-03-28","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}],"next_cursor":"100"}