{"total":80,"rows":[{"id":"2201.09873","title":"Transformers in Medical Imaging: A Survey","created":"2022-01-24","cited_by_count":245,"area":null},{"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":"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":"2305.08989","title":"LoViT: Long Video Transformer for Surgical Phase Recognition","created":"2023-05-15","cited_by_count":56,"area":null},{"id":"2401.00496","title":"SAR-RARP50: Segmentation of surgical instrumentation and Action Recognition on Robot-Assisted Radical Prostatectomy Challenge","created":"2023-12-31","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":"2202.08453","title":"TraSeTR: Track-to-Segment Transformer with Contrastive Query for Instance-level Instrument Segmentation in Robotic Surgery","created":"2022-02-17","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":"2212.04582","title":"Towards Holistic Surgical Scene Understanding","created":"2022-12-08","cited_by_count":33,"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":"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":"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":"2204.05235","title":"Data Splits and Metrics for Method Benchmarking on Surgical Action Triplet Datasets","created":"2022-04-11","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":"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":"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":"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":"2202.08199","title":"Less is More: Surgical Phase Recognition from Timestamp Supervision","created":"2022-02-16","cited_by_count":13,"area":null},{"id":"2212.01683","title":"Recognition and Prediction of Surgical Gestures and Trajectories Using Transformer Models in Robot-Assisted Surgery","created":"2022-12-03","cited_by_count":12,"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":"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":"2205.09292","title":"Free Lunch for Surgical Video Understanding by Distilling Self-Supervisions","created":"2022-05-19","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":"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":"2509.06467","title":"Does DINOv3 Set a New Medical Vision Standard? Benchmarking 2D and 3D Classification, Segmentation, and Registration","created":"2025-09-08","cited_by_count":7,"area":null},{"id":"2202.05821","title":"PEg TRAnsfer Workflow recognition challenge report: Does multi-modal data improve recognition?","created":"2022-02-11","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":"2404.09231","title":"Tri-modal Confluence with Temporal Dynamics for Scene Graph Generation in Operating Rooms","created":"2024-04-14","cited_by_count":6,"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":"2402.01974","title":"Hypergraph-Transformer (HGT) for Interactive Event Prediction in Laparoscopic and Robotic Surgery","created":"2024-02-03","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":"2412.18849","title":"SWAG: Long-term Surgical Workflow Prediction with Generative-based Anticipation","created":"2024-12-25","cited_by_count":4,"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":"2409.20083","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":"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":"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":"2502.06708","title":"TEMSET-24K: Densely Annotated Dataset for Indexing Multipart Endoscopic Videos using Surgical Timeline Segmentation","created":"2025-02-10","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":"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":"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":"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":"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":"2502.03430","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":"2507.09294","title":"Geo-RepNet: Geometry-Aware Representation Learning for Surgical Phase Recognition in Endoscopic Submucosal Dissection","created":"2025-07-12","cited_by_count":1,"area":null},{"id":"2509.18802","title":"Surgical Video Understanding with Label Interpolation","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2608.22879","title":"Large-Small Model Collaboration for Zero-Shot Surgical Phase Recognition","created":"2026-08-24","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":"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":"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":"2506.01980","title":"Surgical Foundation Model Leveraging Compression and Entropy Maximization for Image-Guided Surgical Assistance","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2509.23672","title":"Token Merging via Spatiotemporal Information Mining for Surgical Video Understanding","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2601.12312","title":"CurConMix+: A Unified Spatio-Temporal Framework for Hierarchical Surgical Workflow Understanding","created":"2026-01-18","cited_by_count":0,"area":null},{"id":"2602.20500","title":"Strategy-Supervised Autonomous Laparoscopic Camera Control via Event-Driven Graph Mining","created":"2026-02-24","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":"2604.07577","title":"Event-Level Detection of Surgical Instrument Handovers in Videos with Interpretable Vision Models","created":"2026-04-08","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":"2605.16387","title":"Stabilizing Temporal Inference Dynamics for Online Surgical Phase Recognition","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.25598","title":"SurfSurg6D: Geometry Consistent Dense Correspondence for Textureless Surgical Instrument Pose Estimation","created":"2026-05-25","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":"2605.28119","title":"ST-ColoNet: Spatio-Temporal Colon Segment Recognition via Hybrid Attention and Edge-Guided Feature Learning","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.13032","title":"GeoCFNet: Geometry-Aware Confidence Field Network for Robot-Assisted Endoscopic Submucosal Dissection","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.26634","title":"Temporally Consistent Label Interpolation for Robust Surgical Multi-Task Learning under Challenging Conditions","created":"2026-06-25","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":"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}