{"total":110,"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":"2401.03495","title":"Segment Anything Model for Medical Image Segmentation: Current Applications and Future Directions","created":"2024-01-07","cited_by_count":97,"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":"2309.08842","title":"MA-SAM: Modality-agnostic SAM Adaptation for 3D Medical Image Segmentation","created":"2023-09-16","cited_by_count":82,"area":null},{"id":"2206.11053","title":"Surgical-VQA: Visual Question Answering in Surgical Scenes using Transformer","created":"2022-06-22","cited_by_count":59,"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":"2304.08023","title":"Learning How To Robustly Estimate Camera Pose in Endoscopic Videos","created":"2023-04-17","cited_by_count":50,"area":null},{"id":"2304.09974","title":"SurgicalGPT: End-to-End Language-Vision GPT for Visual Question Answering in Surgery","created":"2023-04-19","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":"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":"2408.03322","title":"Segment Anything in Medical Images and Videos: Benchmark and Deployment","created":"2024-08-06","cited_by_count":42,"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":"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":"2203.15251","title":"Exploring Intra- and Inter-Video Relation for Surgical Semantic Scene Segmentation","created":"2022-03-29","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":"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":"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":"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":"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":"2107.11091","title":"Class-Incremental Domain Adaptation with Smoothing and Calibration for Surgical Report Generation","created":"2021-07-23","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":"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":"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":"2306.02651","title":"Dynamic Interactive Relation Capturing via Scene Graph Learning for Robotic Surgical Report Generation","created":"2023-06-05","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":"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":"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":"2409.06037","title":"Online 3D reconstruction and dense tracking in endoscopic videos","created":"2024-09-09","cited_by_count":10,"area":null},{"id":"2208.06643","title":"Recent Progress in Transformer-based Medical Image Analysis","created":"2022-08-13","cited_by_count":9,"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":"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":"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":"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":"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":"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":"2110.10965","title":"2020 CATARACTS Semantic Segmentation Challenge","created":"2021-10-21","cited_by_count":5,"area":null},{"id":"2207.00113","title":"Rethinking Surgical Captioning: End-to-End Window-Based MLP Transformer Using Patches","created":"2022-06-30","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":"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":"2211.15327","title":"Task-Aware Asynchronous Multi-Task Model with Class Incremental Contrastive Learning for Surgical Scene Understanding","created":"2022-11-28","cited_by_count":4,"area":null},{"id":"2307.05898","title":"Rectifying Noisy Labels with Sequential Prior: Multi-Scale Temporal Feature Affinity Learning for Robust Video Segmentation","created":"2023-07-12","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":"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":"2402.19340","title":"One model to use them all: Training a segmentation model with complementary datasets","created":"2024-02-29","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":"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":"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":"2410.17642","title":"Surgical Scene Segmentation by Transformer With Asymmetric Feature Enhancement","created":"2024-10-23","cited_by_count":2,"area":null},{"id":"2412.06470","title":"Active Learning with Context Sampling and One-vs-Rest Entropy for Semantic Segmentation","created":"2024-12-09","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":"2507.15541","title":"Towards Holistic Surgical Scene Graph","created":"2025-07-21","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":"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},{"id":"2309.00957","title":"Visual-Kinematics Graph Learning for Procedure-agnostic Instrument Tip Segmentation in Robotic Surgeries","created":"2023-09-02","cited_by_count":1,"area":null},{"id":"2401.02791","title":"Weakly Semi-supervised Tool Detection in Minimally Invasive Surgery Videos","created":"2024-01-05","cited_by_count":1,"area":null},{"id":"2504.13440","title":"Temporal Propagation of Asymmetric Feature Pyramid for Surgical Scene Segmentation","created":"2025-04-18","cited_by_count":1,"area":null},{"id":"2506.06830","title":"EndoARSS: Adapting Spatially-Aware Foundation Model for Efficient Activity Recognition and Semantic Segmentation in Endoscopic Surgery","created":"2025-06-07","cited_by_count":1,"area":null},{"id":"2507.02252","title":"SurgVisAgent: Multimodal Agentic Model for Versatile Surgical Visual Enhancement","created":"2025-07-03","cited_by_count":1,"area":null},{"id":"2511.16618","title":"SurgSLOT: Segment Anything in Surgical Videos via Semantic Long-term Tracking","created":"2025-11-20","cited_by_count":1,"area":null},{"id":"2512.07596","title":"More than Segmentation: Benchmarking SAM 3 for Segmentation, 3D Perception, and Reconstruction in Robotic Surgery","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2604.03645","title":"UniSurgSAM: A Unified Promptable Model for Reliable Surgical Video Segmentation","created":"2026-04-04","cited_by_count":1,"area":null},{"id":"2607.23694","title":"Parameter-Efficient Adaptation of SAM3 for Prompt-Driven Surgical Concept Segmentation","created":"2026-07-26","cited_by_count":1,"area":null},{"id":"2608.24541","title":"Hierarchical Prototype-Memory Adaptation of SAM for Surgical Instrument Segmentation","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2111.05408","title":"Robust deep learning-based semantic organ segmentation in hyperspectral images","created":"2021-11-09","cited_by_count":0,"area":null},{"id":"2305.10883","title":"Domain Adaptive Sim-to-Real Segmentation of Oropharyngeal Organs","created":"2023-05-18","cited_by_count":0,"area":null},{"id":"2308.09475","title":"Video-Instrument Synergistic Network for Referring Video Instrument Segmentation in Robotic Surgery","created":"2023-08-18","cited_by_count":0,"area":null},{"id":"2312.05900","title":"Deep-Learning-Assisted Analysis of Cataract Surgery Videos","created":"2023-12-10","cited_by_count":0,"area":null},{"id":"2409.09360","title":"LACOSTE: Exploiting stereo and temporal contexts for surgical instrument segmentation","created":"2024-09-14","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":"2507.04304","title":"Surg-SegFormer: A Dual Transformer-Based Model for Holistic Surgical Scene Segmentation","created":"2025-07-06","cited_by_count":0,"area":null},{"id":"2507.04317","title":"CLIP-RL: Surgical Scene Segmentation Using Contrastive Language-Vision Pretraining & Reinforcement Learning","created":"2025-07-06","cited_by_count":0,"area":null},{"id":"2507.19592","title":"SurgPIS: Surgical-instrument-level Instances and Part-level Semantics for Weakly-supervised Part-aware Instance Segmentation","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2507.23088","title":"Beyond Rigid AI: Towards Natural Human-Machine Symbiosis for Interoperative Surgical Assistance","created":"2025-07-30","cited_by_count":0,"area":null},{"id":"2512.16880","title":"ReMeDI: Refined Memory for Disambiguation of Identities with SAM3 in Surgical Segmentation","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2512.21284","title":"Toward Real-Time Surgical Scene Segmentation via a Spike-Driven Video Transformer with Spike-Informed Pretraining","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2603.09496","title":"SurgFed: Language-guided Multi-Task Federated Learning for Surgical Video Understanding","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.18544","title":"SCISSR: Scribble-Conditioned Interactive Surgical Segmentation and Refinement","created":"2026-03-19","cited_by_count":0,"area":null}],"next_cursor":"100"}