{"total":69,"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":"2103.16327","title":"Temporal Memory Relation Network for Workflow Recognition from Surgical Video","created":"2021-03-30","cited_by_count":66,"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":"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":"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":"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":"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":"2103.13111","title":"MIcro-Surgical Anastomose Workflow recognition challenge report","created":"2021-03-24","cited_by_count":28,"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":"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":"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":"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":"2305.13961","title":"Metrics Matter in Surgical Phase Recognition","created":"2023-05-23","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":"2202.13402","title":"Concept Graph Neural Networks for Surgical Video Understanding","created":"2022-02-27","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":"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":"2103.10308","title":"Future Frame Prediction for Robot-assisted Surgery","created":"2021-03-18","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":"2109.12448","title":"ReCal-Net: Joint Region-Channel-Wise Calibrated Network for Semantic Segmentation in Cataract Surgery Videos","created":"2021-09-25","cited_by_count":8,"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":"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":"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":"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":"2107.06397","title":"SurgeonAssist-Net: Towards Context-Aware Head-Mounted Display-Based Augmented Reality for Surgical Guidance","created":"2021-07-13","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":"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":"2311.18666","title":"Action Recognition in Video Recordings from Gynecologic Laparoscopy","created":"2023-11-30","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":"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":"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":"2505.12890","title":"Specialized Foundation Models for Intelligent Operating Rooms","created":"2025-05-19","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":"2203.04301","title":"Live Laparoscopic Video Retrieval with Compressed Uncertainty","created":"2022-03-08","cited_by_count":2,"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":"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":"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":"2504.19918","title":"Enhancing Surgical Documentation through Multimodal Visual-Temporal Transformers and Generative AI","created":"2025-04-28","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":"2404.04992","title":"Efficient Surgical Tool Recognition via HMM-Stabilized Deep Learning","created":"2024-04-07","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":"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":"2501.02618","title":"Identifying Surgical Instruments in Pedagogical Cataract Surgery Videos through an Optimized Aggregation Network","created":"2025-01-05","cited_by_count":0,"area":null},{"id":"2504.18756","title":"Multi-Stage Boundary-Aware Transformer Network for Action Segmentation in Untrimmed Surgical Videos","created":"2025-04-26","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":"2508.10215","title":"Data-Efficient Learning for Generalizable Surgical Video Understanding","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2510.14525","title":"Real-Time Surgical Instrument Defect Detection via Non-Destructive Testing","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2510.15372","title":"Adaptive transfer learning for surgical tool presence detection in laparoscopic videos through gradual freezing fine-tuning","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2603.19920","title":"PanORama: Multiview Consistent Panoptic Segmentation in Operating Rooms","created":"2026-03-20","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":"2605.26483","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":"2606.26634","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":"2610.08838","title":"Deep Learning for Longitudinal Medical Imaging: A Scoping Review","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}