{"total":106,"rows":[{"id":"2312.10251","title":"Advancing Surgical VQA with Scene Graph Knowledge","created":"2023-12-15","cited_by_count":41,"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":"2308.03726","title":"AdaptiveSAM: Towards Efficient Tuning of SAM for Surgical Scene Segmentation","created":"2023-08-07","cited_by_count":37,"area":null},{"id":"2308.05737","title":"Follow Anything: Open-set detection, tracking, and following in real-time","created":"2023-08-10","cited_by_count":29,"area":null},{"id":"2306.09244","title":"Text Promptable Surgical Instrument Segmentation with Vision-Language Models","created":"2023-06-15","cited_by_count":28,"area":"mllm"},{"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":"2601.10880","title":"Medical SAM3: A Foundation Model for Universal Prompt-Driven Medical Image Segmentation","created":"2026-01-15","cited_by_count":25,"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":"2312.12429","title":"The Endoscapes Dataset for Surgical Scene Segmentation, Object Detection, and Critical View of Safety Assessment: Official Splits and Benchmark","created":"2023-12-19","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":"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":"2306.11052","title":"A spatio-temporal network for video semantic segmentation in surgical videos","created":"2023-06-19","cited_by_count":17,"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":"2401.00678","title":"General-purpose foundation models for increased autonomy in robot-assisted surgery","created":"2024-01-01","cited_by_count":15,"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":"2505.02874","title":"Uncertainty Quantification for Machine Learning in Healthcare: A Survey","created":"2025-05-04","cited_by_count":14,"area":null},{"id":"2410.09750","title":"Surgical-LLaVA: Toward Surgical Scenario Understanding via Large Language and Vision Models","created":"2024-10-13","cited_by_count":13,"area":null},{"id":"2408.06447","title":"S-SAM: SVD-based Fine-Tuning of Segment Anything Model for Medical Image Segmentation","created":"2024-08-12","cited_by_count":11,"area":null},{"id":"2309.03048","title":"Exploring Semantic Consistency in Unpaired Image Translation to Generate Data for Surgical Applications","created":"2023-09-06","cited_by_count":9,"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":"2404.00322","title":"Instrument-tissue Interaction Detection Framework for Surgical Video Understanding","created":"2024-03-30","cited_by_count":8,"area":null},{"id":"2406.06537","title":"Interactive Generation of Laparoscopic Videos with Diffusion Models","created":"2024-04-23","cited_by_count":8,"area":"diffusion"},{"id":"2410.07753","title":"Data Augmentation for Surgical Scene Segmentation with Anatomy-Aware Diffusion Models","created":"2024-10-10","cited_by_count":8,"area":"diffusion"},{"id":"2506.21287","title":"HieraSurg: Hierarchy-Aware Diffusion Model for Surgical Video Generation","created":"2025-06-26","cited_by_count":8,"area":"diffusion"},{"id":"2311.02719","title":"Uncertainty Estimation for Safety-critical Scene Segmentation via Fine-grained Reward Maximization","created":"2023-11-05","cited_by_count":7,"area":null},{"id":"2312.03043","title":"Navigating the Synthetic Realm: Harnessing Diffusion-based Models for Laparoscopic Text-to-Image Generation","created":"2023-12-05","cited_by_count":7,"area":null},{"id":"2403.08003","title":"Augmenting Efficient Real-time Surgical Instrument Segmentation in Video with Point Tracking and Segment Anything","created":"2024-03-12","cited_by_count":7,"area":null},{"id":"2407.17904","title":"Exploring the Effect of Dataset Diversity in Self-Supervised Learning for Surgical Computer Vision","created":"2024-07-25","cited_by_count":7,"area":null},{"id":"2506.23309","title":"SurgTPGS: Semantic 3D Surgical Scene Understanding with Text Promptable Gaussian Splatting","created":"2025-06-29","cited_by_count":7,"area":"mllm"},{"id":"2603.06570","title":"SUREON: A Benchmark and Vision-Language-Model for Surgical Reasoning","created":"2026-03-06","cited_by_count":7,"area":"lr"},{"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":"2401.08256","title":"Multitask Learning in Minimally Invasive Surgical Vision: A Review","created":"2024-01-16","cited_by_count":5,"area":null},{"id":"2407.15794","title":"Disentangling spatio-temporal knowledge for weakly supervised object detection and segmentation in surgical video","created":"2024-07-22","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":"2309.17264","title":"A Foundation Model for General Moving Object Segmentation in Medical Images","created":"2023-09-29","cited_by_count":4,"area":null},{"id":"2408.09822","title":"SurgicaL-CD: Generating Surgical Images via Unpaired Image Translation with Latent Consistency Diffusion Models","created":"2024-08-19","cited_by_count":4,"area":"diffusion"},{"id":"2501.12477","title":"Slot-BERT: Self-supervised Object Discovery in Surgical Video","created":"2025-01-21","cited_by_count":4,"area":null},{"id":"2502.09653","title":"SASVi -- Segment Any Surgical Video","created":"2025-02-12","cited_by_count":4,"area":null},{"id":"2508.06993","title":"OctreeNCA: Single-Pass 184 MP Segmentation on Consumer Hardware","created":"2025-08-09","cited_by_count":4,"area":null},{"id":"2309.07330","title":"Automated Assessment of Critical View of Safety in Laparoscopic Cholecystectomy","created":"2023-09-13","cited_by_count":3,"area":null},{"id":"2406.00907","title":"DDA: Dimensionality Driven Augmentation Search for Contrastive Learning in Laparoscopic Surgery","created":"2024-06-03","cited_by_count":3,"area":null},{"id":"2407.06795","title":"CycleSAM: Few-Shot Surgical Scene Segmentation with Cycle- and Scene-Consistent Feature Matching","created":"2024-07-09","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":"2411.03695","title":"AMNCutter: Affinity-Attention-Guided Multi-View Normalized Cutter for Unsupervised Surgical Instrument Segmentation","created":"2024-11-06","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":"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":"2507.00868","title":"Is Visual in-Context Learning for Compositional Medical Tasks within Reach?","created":"2025-07-01","cited_by_count":3,"area":null},{"id":"2509.15596","title":"EyePCR: A Comprehensive Benchmark for Fine-Grained Perception, Knowledge Comprehension and Clinical Reasoning in Ophthalmic Surgery","created":"2025-09-19","cited_by_count":3,"area":"lr"},{"id":"2601.12224","title":"Where It Moves, It Matters: Referring Surgical Instrument Segmentation via Motion","created":"2026-01-18","cited_by_count":3,"area":null},{"id":"2302.10698","title":"Unpaired Translation from Semantic Label Maps to Images by Leveraging Domain-Specific Simulations","created":"2023-02-21","cited_by_count":2,"area":null},{"id":"2403.19265","title":"Neural Fields for 3D Tracking of Anatomy and Surgical Instruments in Monocular Laparoscopic Video Clips","created":"2024-03-28","cited_by_count":2,"area":null},{"id":"2407.19714","title":"Rethinking RGB-D Fusion for Semantic Segmentation in Surgical Datasets","created":"2024-07-29","cited_by_count":2,"area":null},{"id":"2412.03401","title":"Benchmarking Pretrained Attention-based Models for Real-Time Recognition in Robot-Assisted Esophagectomy","created":"2024-12-04","cited_by_count":2,"area":null},{"id":"2501.04184","title":"MedicalNarratives: Connecting Medical Vision and Language with Localized Narratives","created":"2025-01-07","cited_by_count":2,"area":null},{"id":"2503.03942","title":"SurgiSAM2: Fine-tuning a foundational model for surgical video anatomy segmentation and detection","created":"2025-03-05","cited_by_count":2,"area":null},{"id":"2507.01882","title":"Future Slot Prediction for Unsupervised Object Discovery in Surgical Video","created":"2025-07-02","cited_by_count":2,"area":null},{"id":"2508.21096","title":"ROBUST-MIPS: A Combined Skeletal Pose and Instance Segmentation Dataset for Laparoscopic Surgical Instruments","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2509.18642","title":"Zero-shot Monocular Metric Depth for Endoscopic Images","created":"2025-09-23","cited_by_count":2,"area":null},{"id":"2511.21926","title":"Comparing SAM 2 and SAM 3 for Zero-Shot Segmentation of 3D Medical Data","created":"2025-11-26","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":"2606.25905","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":"2402.17903","title":"Surgment: Segmentation-enabled Semantic Search and Creation of Visual Question and Feedback to Support Video-Based Surgery Learning","created":"2024-02-27","cited_by_count":1,"area":null},{"id":"2501.10819","title":"GAUDA: Generative Adaptive Uncertainty-guided Diffusion-based Augmentation for Surgical Segmentation","created":"2025-01-18","cited_by_count":1,"area":"diffusion"},{"id":"2502.20934","title":"Revisiting the Evaluation Bias Introduced by Frame Sampling Strategies in Surgical Video Segmentation Using SAM2","created":"2025-02-28","cited_by_count":1,"area":null},{"id":"2503.19661","title":"CoSimGen: Controllable Diffusion Model for Simultaneous Image and Mask Generation","created":"2025-03-25","cited_by_count":1,"area":"diffusion"},{"id":"2511.00643","title":"Grounding Surgical Action Triplets with Instrument Instance Segmentation: A Dataset and Target-Aware Fusion Approach","created":"2025-11-01","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":"2512.05529","title":"See in Depth: Training-Free Surgical Scene Segmentation with Monocular Depth Priors","created":"2025-12-05","cited_by_count":1,"area":null},{"id":"2512.08439","title":"LapFM: A Laparoscopic Segmentation Foundation Model via Hierarchical Concept Evolving Pre-training","created":"2025-12-09","cited_by_count":1,"area":null},{"id":"2604.02877","title":"Unlocking Positive Transfer in Incrementally Learning Surgical Instruments: A Self-reflection Hierarchical Prompt Framework","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2605.16022","title":"EndoGSim: Physics-Aware 4D Dynamic Endoscopic Scene Simulations via MLLM-Guided Gaussian Splatting","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2606.22124","title":"Surgical Anatomy Recognition with Context Learning using Foundation Representations","created":"2026-06-20","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":"2608.16469","title":"Sterilizable Scene Graph Generation for Operating Rooms","created":"2026-08-17","cited_by_count":1,"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":"2403.10216","title":"Exploring Optical Flow Inclusion into nnU-Net Framework for Surgical Instrument Segmentation","created":"2024-03-15","cited_by_count":0,"area":null},{"id":"2410.08509","title":"A Bayesian Approach to Weakly-supervised Laparoscopic Image Segmentation","created":"2024-10-11","cited_by_count":0,"area":null},{"id":"2503.02228","title":"One Patient's Annotation is Another One's Initialization: Towards Zero-Shot Surgical Video Segmentation with Cross-Patient Initialization","created":"2025-03-04","cited_by_count":0,"area":null},{"id":"2504.12573","title":"Parsimonious Dataset Construction for Laparoscopic Cholecystectomy Structure Segmentation","created":"2025-04-17","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":"2507.16429","title":"Robust Noisy Pseudo-label Learning for Semi-supervised Medical Image Segmentation Using Diffusion Model","created":"2025-07-22","cited_by_count":0,"area":"diffusion"},{"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":"2510.02100","title":"When Tracking Fails: Analyzing Failure Modes of SAM2 for Point-Based Tracking in Surgical Videos","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2511.04525","title":"Learning from Single Timestamps: Complexity Estimation in Laparoscopic Cholecystectomy","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2511.05059","title":"SurgiATM: A Physics-Guided Plug-and-Play Model for Deep Learning-Based Smoke Removal in Laparoscopic Surgery","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2511.16430","title":"Graph Neural Networks for Surgical Scene Segmentation","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2512.02188","title":"RobustSurg: Tackling domain generalisation for out-of-distribution surgical scene segmentation","created":"2025-12-01","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":"2603.01108","title":"GroundedSurg: A Multi-Procedure Benchmark for Language-Conditioned Surgical Tool Segmentation","created":"2026-03-01","cited_by_count":0,"area":null},{"id":"2603.07839","title":"Training-free Temporal Object Tracking in Surgical Videos","created":"2026-03-08","cited_by_count":0,"area":"diffusion"},{"id":"2603.18544","title":"SCISSR: Scribble-Conditioned Interactive Surgical Segmentation and Refinement","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2604.20319","title":"SurgCoT: Advancing Spatiotemporal Reasoning in Surgical Videos through a Chain-of-Thought Benchmark","created":"2026-04-22","cited_by_count":0,"area":"lr"},{"id":"2605.11265","title":"DenseTRF: Texture-Aware Unsupervised Representation Adaptation for Surgical Scene Dense Prediction","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.21861","title":"Learning Emergent Modular Representations in Multi-modality Medical Vision Foundation Models","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2606.13332","title":"OR-Action: Multi-Role Video Understanding with Fine-Grained Actions","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.31007","title":"Dense Structural Priors for Sparse Functional Landmark Localization in Surgical Videos","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.04761","title":"DeGenseGS: Geometrically and Semantically Decoupled Surgical Scene Understanding in 4D Gaussian Splatting","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.08397","title":"Attribute Retrieving for Open-Vocabulary Endoscopic Compositional Referring Segmentation","created":"2026-07-09","cited_by_count":0,"area":null}],"next_cursor":"100"}