{"total":148,"rows":[{"id":"2308.08746","title":"SurgicalSAM: Efficient Class Promptable Surgical Instrument Segmentation","created":"2023-08-17","cited_by_count":104,"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":"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":"2304.12637","title":"Generalist Vision Foundation Models for Medical Imaging: A Case Study of Segment Anything Model on Zero-Shot Medical Segmentation","created":"2023-04-25","cited_by_count":51,"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":"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":"2107.00229","title":"E-DSSR: Efficient Dynamic Surgical Scene Reconstruction with Transformer-based Stereoscopic Depth Perception","created":"2021-07-01","cited_by_count":46,"area":null},{"id":"2305.11692","title":"Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery","created":"2023-05-19","cited_by_count":44,"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":"2308.03726","title":"AdaptiveSAM: Towards Efficient Tuning of SAM for Surgical Scene Segmentation","created":"2023-08-07","cited_by_count":37,"area":null},{"id":"2303.09514","title":"MATIS: Masked-Attention Transformers for Surgical Instrument Segmentation","created":"2023-03-16","cited_by_count":36,"area":null},{"id":"2212.04582","title":"Towards Holistic Surgical Scene Understanding","created":"2022-12-08","cited_by_count":33,"area":null},{"id":"2211.16200","title":"From Forks to Forceps: A New Framework for Instance Segmentation of Surgical Instruments","created":"2022-11-26","cited_by_count":32,"area":null},{"id":"2308.07156","title":"SAM Meets Robotic Surgery: An Empirical Study on Generalization, Robustness and Adaptation","created":"2023-08-14","cited_by_count":30,"area":null},{"id":"2203.15177","title":"Min-Max Similarity: A Contrastive Semi-Supervised Deep Learning Network for Surgical Tools Segmentation","created":"2022-03-29","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":"2304.14674","title":"SAM Meets Robotic Surgery: An Empirical Study in Robustness Perspective","created":"2023-04-28","cited_by_count":24,"area":null},{"id":"2308.01265","title":"Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectives","created":"2023-07-18","cited_by_count":24,"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":"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":"2409.01437","title":"Kvasir-VQA: A Text-Image Pair GI Tract Dataset","created":"2024-09-02","cited_by_count":23,"area":null},{"id":"2312.17004","title":"Continual Learning in Medical Image Analysis: A Comprehensive Review of Recent Advancements and Future Prospects","created":"2023-12-28","cited_by_count":22,"area":null},{"id":"2408.04593","title":"SAM 2 in Robotic Surgery: An Empirical Evaluation for Robustness and Generalization in Surgical Video Segmentation","created":"2024-08-08","cited_by_count":21,"area":null},{"id":"2112.08189","title":"ST-MTL: Spatio-Temporal Multitask Learning Model to Predict Scanpath While Tracking Instruments in Robotic Surgery","created":"2021-12-10","cited_by_count":20,"area":null},{"id":"2308.14100","title":"Rethinking Exemplars for Continual Semantic Segmentation in Endoscopy Scenes: Entropy-based Mini-Batch Pseudo-Replay","created":"2023-08-27","cited_by_count":20,"area":null},{"id":"2210.16674","title":"Semantic-SuPer: A Semantic-aware Surgical Perception Framework for Endoscopic Tissue Identification, Reconstruction, and Tracking","created":"2022-10-29","cited_by_count":19,"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":"2203.15202","title":"SimT: Handling Open-set Noise for Domain Adaptive Semantic Segmentation","created":"2022-03-29","cited_by_count":17,"area":null},{"id":"2307.05182","title":"CAT-ViL: Co-Attention Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery","created":"2023-07-11","cited_by_count":17,"area":null},{"id":"2407.15851","title":"A Survey on Trustworthiness in Foundation Models for Medical Image Analysis","created":"2024-07-03","cited_by_count":17,"area":null},{"id":"2408.04958","title":"Surgical-VQLA++: Adversarial Contrastive Learning for Calibrated Robust Visual Question-Localized Answering in Robotic Surgery","created":"2024-08-09","cited_by_count":17,"area":null},{"id":"2206.11804","title":"Rethinking Surgical Instrument Segmentation: A Background Image Can Be All You Need","created":"2022-06-23","cited_by_count":16,"area":null},{"id":"2406.16039","title":"CholecInstanceSeg: A Tool Instance Segmentation Dataset for Laparoscopic Surgery","created":"2024-06-23","cited_by_count":16,"area":null},{"id":"2504.03198","title":"Endo3R: Unified Online Reconstruction from Dynamic Monocular Endoscopic Video","created":"2025-04-04","cited_by_count":16,"area":null},{"id":"2307.12045","title":"Revisiting Distillation for Continual Learning on Visual Question Localized-Answering in Robotic Surgery","created":"2023-07-22","cited_by_count":15,"area":null},{"id":"2505.08581","title":"ReSurgSAM2: Referring Segment Anything in Surgical Video via Credible Long-term Tracking","created":"2025-05-13","cited_by_count":15,"area":null},{"id":"2103.12988","title":"One to Many: Adaptive Instrument Segmentation via Meta Learning and Dynamic Online Adaptation in Robotic Surgical Video","created":"2021-03-24","cited_by_count":14,"area":null},{"id":"2302.03022","title":"SurgT challenge: Benchmark of Soft-Tissue Trackers for Robotic Surgery","created":"2023-02-06","cited_by_count":14,"area":null},{"id":"2408.03286","title":"Biomedical SAM 2: Segment Anything in Biomedical Images and Videos","created":"2024-08-06","cited_by_count":14,"area":null},{"id":"2403.06683","title":"Transferring Relative Monocular Depth to Surgical Vision with Temporal Consistency","created":"2024-03-11","cited_by_count":13,"area":null},{"id":"2503.12781","title":"SAM2 for Image and Video Segmentation: A Comprehensive Survey","created":"2025-03-17","cited_by_count":13,"area":null},{"id":"2407.19435","title":"ASI-Seg: Audio-Driven Surgical Instrument Segmentation with Surgeon Intention Understanding","created":"2024-07-28","cited_by_count":12,"area":null},{"id":"2408.01648","title":"Zero-Shot Surgical Tool Segmentation in Monocular Video Using Segment Anything Model 2","created":"2024-08-03","cited_by_count":11,"area":null},{"id":"2411.12195","title":"A Survey of Medical Vision-and-Language Applications and Their Techniques","created":"2024-11-19","cited_by_count":11,"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":"2108.08748","title":"FSNet: A Failure Detection Framework for Semantic Segmentation","created":"2021-08-19","cited_by_count":9,"area":null},{"id":"2305.17937","title":"Attention Mechanisms in Medical Image Segmentation: A Survey","created":"2023-05-29","cited_by_count":9,"area":null},{"id":"2308.11776","title":"WS-SfMLearner: Self-supervised Monocular Depth and Ego-motion Estimation on Surgical Videos with Unknown Camera Parameters","created":"2023-08-22","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":"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":"2206.07994","title":"Joint Class-Affinity Loss Correction for Robust Medical Image Segmentation with Noisy Labels","created":"2022-06-16","cited_by_count":8,"area":null},{"id":"2312.14481","title":"SurgicalPart-SAM: Part-to-Whole Collaborative Prompting for Surgical Instrument Segmentation","created":"2023-12-22","cited_by_count":8,"area":null},{"id":"2403.12167","title":"A Systematic Review of Generalization Research in Medical Image Classification","created":"2024-03-18","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":"2505.09274","title":"Recent Advances in Medical Imaging Segmentation: A Survey","created":"2025-05-14","cited_by_count":8,"area":null},{"id":"2507.09577","title":"Memory-Augmented SAM2 for Training-Free Surgical Video Segmentation","created":"2025-07-13","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":"2110.12555","title":"hSDB-instrument: Instrument Localization Database for Laparoscopic and Robotic Surgeries","created":"2021-10-24","cited_by_count":7,"area":null},{"id":"2501.02990","title":"SurgRIPE challenge: Benchmark of Surgical Robot Instrument Pose Estimation","created":"2025-01-06","cited_by_count":7,"area":null},{"id":"2107.03949","title":"Task Fingerprinting for Meta Learning in Biomedical Image Analysis","created":"2021-07-08","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":"2112.13815","title":"Temporally Constrained Neural Networks (TCNN): A framework for semi-supervised video semantic segmentation","created":"2021-12-27","cited_by_count":6,"area":null},{"id":"2305.11686","title":"Domain Adaptive Sim-to-Real Segmentation of Oropharyngeal Organs Towards Robot-assisted Intubation","created":"2023-05-19","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":"2106.09302","title":"How can we learn (more) from challenges? A statistical approach to driving future algorithm development","created":"2021-06-17","cited_by_count":5,"area":null},{"id":"2110.10965","title":"2020 CATARACTS Semantic Segmentation Challenge","created":"2021-10-21","cited_by_count":5,"area":null},{"id":"2307.01067","title":"Localized Questions in Medical Visual Question Answering","created":"2023-07-03","cited_by_count":5,"area":null},{"id":"2408.08315","title":"Segment Anything for Videos: A Systematic Survey","created":"2024-07-31","cited_by_count":5,"area":null},{"id":"2501.00525","title":"Systematic Evaluation and Guidelines for Segment Anything Model in Surgical Video Analysis","created":"2024-12-31","cited_by_count":5,"area":null},{"id":"2501.06678","title":"Imbalanced Medical Image Segmentation with Pixel-dependent Noisy Labels","created":"2025-01-12","cited_by_count":5,"area":null},{"id":"2503.04082","title":"Instrument-Splatting: Controllable Photorealistic Reconstruction of Surgical Instruments Using Gaussian Splatting","created":"2025-03-06","cited_by_count":5,"area":null},{"id":"2112.11554","title":"Distribution-aware Margin Calibration for Semantic Segmentation in Images","created":"2021-12-21","cited_by_count":4,"area":null},{"id":"2204.01712","title":"Histogram of Oriented Gradients Meet Deep Learning: A Novel Multi-task Deep Network for Medical Image Semantic Segmentation","created":"2022-04-02","cited_by_count":4,"area":null},{"id":"2311.08811","title":"Correlation-aware active learning for surgery video segmentation","created":"2023-11-15","cited_by_count":4,"area":null},{"id":"2408.07266","title":"Enhanced Scale-aware Depth Estimation for Monocular Endoscopic Scenes with Geometric Modeling","created":"2024-08-14","cited_by_count":4,"area":null},{"id":"2410.01813","title":"Privacy-Preserving SAM Quantization for Efficient Edge Intelligence in Healthcare","created":"2024-09-14","cited_by_count":4,"area":null},{"id":"2506.23759","title":"Spatio-Temporal Representation Decoupling and Enhancement for Federated Instrument Segmentation in Surgical Videos","created":"2025-06-30","cited_by_count":4,"area":null},{"id":"2302.14237","title":"Towards Surgical Context Inference and Translation to Gestures","created":"2023-02-28","cited_by_count":3,"area":null},{"id":"2402.17972","title":"From Generalization to Precision: Exploring SAM for Tool Segmentation in Surgical Environments","created":"2024-02-28","cited_by_count":3,"area":null},{"id":"2408.03208","title":"Personalizing Federated Instrument Segmentation with Visual Trait Priors in Robotic Surgery","created":"2024-08-06","cited_by_count":3,"area":null},{"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":"2409.11299","title":"TTT-Unet: Enhancing U-Net with Test-Time Training Layers for Biomedical Image Segmentation","created":"2024-09-17","cited_by_count":3,"area":null},{"id":"2502.16459","title":"Deep learning approaches to surgical video segmentation and object detection: A Scoping Review","created":"2025-02-23","cited_by_count":3,"area":null},{"id":"2503.18755","title":"EgoSurgery-HTS: A Dataset for Egocentric Hand-Tool Segmentation in Open Surgery Videos","created":"2025-03-24","cited_by_count":3,"area":null},{"id":"2508.01713","title":"Dynamic Robot-Assisted Surgery with Hierarchical Class-Incremental Semantic Segmentation","created":"2025-08-03","cited_by_count":3,"area":null},{"id":"2509.14610","title":"Enhancing Feature Fusion of U-like Networks with Dynamic Skip Connections","created":"2025-09-18","cited_by_count":3,"area":null},{"id":"2306.16285","title":"Generalizing Surgical Instruments Segmentation to Unseen Domains with One-to-Many Synthesis","created":"2023-06-28","cited_by_count":2,"area":null},{"id":"2308.12789","title":"Robotic Scene Segmentation with Memory Network for Runtime Surgical Context Inference","created":"2023-08-24","cited_by_count":2,"area":null},{"id":"2309.01723","title":"SAF-IS: a Spatial Annotation Free Framework for Instance Segmentation of Surgical Tools","created":"2023-09-04","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":"2407.12138","title":"Monocular pose estimation of articulated open surgery tools -- in the wild","created":"2024-07-16","cited_by_count":2,"area":null},{"id":"2501.15326","title":"Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised Data","created":"2025-01-25","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":"2507.00209","title":"SurgiSR4K: A High-Resolution Endoscopic Video Dataset for Robotic-Assisted Minimally Invasive Procedures","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2603.27460","title":"Project Imaging-X: A Survey of 1000+ Open-Access Medical Imaging Datasets for Foundation Model Development","created":"2026-03-29","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":"2606.25905","title":"SurgAtlas: A Large-Scale Surgical Video-Language Dataset with 2,391 Hours of Open and Minimally Invasive Surgery","created":"2026-06-24","cited_by_count":2,"area":null},{"id":"2109.15098","title":"Deep Homography Estimation in Dynamic Surgical Scenes for Laparoscopic Camera Motion Extraction","created":"2021-09-30","cited_by_count":1,"area":null},{"id":"2212.11511","title":"Confidence-Aware Paced-Curriculum Learning by Label Smoothing for Surgical Scene Understanding","created":"2022-12-22","cited_by_count":1,"area":null}],"next_cursor":"100"}