{"total":85,"rows":[{"id":"2305.08989","title":"LoViT: Long Video Transformer for Surgical Phase Recognition","created":"2023-05-15","cited_by_count":56,"area":null},{"id":"2405.10075","title":"HecVL: Hierarchical Video-Language Pretraining for Zero-shot Surgical Phase Recognition","created":"2024-05-16","cited_by_count":42,"area":null},{"id":"2304.14660","title":"Segment Anything Model for Medical Images?","created":"2023-04-28","cited_by_count":39,"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":"2406.07471","title":"OphNet: A Large-Scale Video Benchmark for Ophthalmic Surgical Workflow Understanding","created":"2024-06-11","cited_by_count":32,"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":"2501.09436","title":"Scaling up self-supervised learning for improved surgical foundation models","created":"2025-01-16","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":"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":"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":"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":"2509.10555","title":"SurgLaVi: Large-Scale Hierarchical Dataset for Surgical Vision-Language Representation Learning","created":"2025-09-09","cited_by_count":16,"area":"mllm"},{"id":"2408.10538","title":"Surgical Workflow Recognition and Blocking Effectiveness Detection in Laparoscopic Liver Resections with Pringle Maneuver","created":"2024-08-20","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":"2308.03193","title":"Syn-Mediverse: A Multimodal Synthetic Dataset for Intelligent Scene Understanding of Healthcare Facilities","created":"2023-08-06","cited_by_count":11,"area":null},{"id":"2502.19090","title":"EndoMamba: An Efficient Foundation Model for Endoscopic Videos via Hierarchical Pre-training","created":"2025-02-26","cited_by_count":11,"area":"ssm"},{"id":"2511.01775","title":"How Far Are Surgeons from Surgical World Models? A Pilot Study on Zero-shot Surgical Video Generation with Expert Assessment","created":"2025-11-03","cited_by_count":11,"area":"wm"},{"id":"2512.23162","title":"Cosmos-H-Surgical: Learning Surgical Robot Policies from Videos via World Modeling","created":"2025-12-29","cited_by_count":11,"area":"wm"},{"id":"2506.02692","title":"Large-scale Self-supervised Video Foundation Model for Intelligent Surgery","created":"2025-06-03","cited_by_count":10,"area":null},{"id":"2506.07603","title":"SurgBench: A Unified Large-Scale Benchmark for Surgical Video Analysis","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2312.05968","title":"Jumpstarting Surgical Computer Vision","created":"2023-12-10","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":"2505.11852","title":"MedSG-Bench: A Benchmark for Medical Image Sequences Grounding","created":"2025-05-17","cited_by_count":8,"area":"lr"},{"id":"2506.11356","title":"GynSurg: A Comprehensive Gynecology Laparoscopic Surgery Dataset","created":"2025-06-12","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":"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":"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":"2504.02799","title":"Systematic Evaluation of Large Vision-Language Models for Surgical Artificial Intelligence","created":"2025-04-03","cited_by_count":5,"area":"mllm"},{"id":"2309.03837","title":"Cross-Task Attention Network: Improving Multi-Task Learning for Medical Imaging Applications","created":"2023-09-07","cited_by_count":4,"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":"2506.20254","title":"Recognizing Surgical Phases Anywhere: Few-Shot Test-time Adaptation and Task-graph Guided Refinement","created":"2025-06-25","cited_by_count":4,"area":null},{"id":"2602.05638","title":"SurgMotion: A Video-Native Foundation Model for Universal Understanding of Surgical Videos","created":"2026-02-05","cited_by_count":4,"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":"2409.12108","title":"SPRMamba: Surgical Phase Recognition for Endoscopic Submucosal Dissection with Mamba","created":"2024-09-18","cited_by_count":3,"area":"ssm"},{"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":"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":"2511.21339","title":"SurgMLLMBench: A Multimodal Large Language Model Benchmark Dataset for Surgical Scene Understanding","created":"2025-11-26","cited_by_count":3,"area":"mllm"},{"id":"2603.12787","title":"Generalized Recognition of Basic Surgical Actions Enables Skill Assessment and Vision-Language-Model-based Surgical Planning","created":"2026-03-13","cited_by_count":3,"area":null},{"id":"2603.24539","title":"CliPPER: Contextual Video-Language Pretraining on Long-form Intraoperative Surgical Procedures for Event Recognition","created":"2026-03-25","cited_by_count":3,"area":null},{"id":"2605.06537","title":"MedHorizon: Towards Long-context Medical Video Understanding in the Wild","created":"2026-05-07","cited_by_count":3,"area":"mllm"},{"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":"2407.19714","title":"Rethinking RGB-D Fusion for Semantic Segmentation in Surgical Datasets","created":"2024-07-29","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":"2504.15327","title":"Advancing Embodied Intelligence in Robotic-Assisted Endovascular Procedures: A Systematic Review of AI Solutions","created":"2025-04-21","cited_by_count":2,"area":null},{"id":"2603.12430","title":"Surg-R1: A Hierarchical Reasoning Foundation Model for Scalable and Interpretable Surgical Decision Support with Multi-Center Clinical Validation","created":"2026-03-12","cited_by_count":2,"area":"lr"},{"id":"2603.16822","title":"Surg$\\Sigma$: A Spectrum of Large-Scale Multimodal Data and Foundation Models for Surgical Intelligence","created":"2026-03-17","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":"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":"2508.16730","title":"Analysis of Transferability Estimation Metrics for Surgical Phase Recognition","created":"2025-08-22","cited_by_count":1,"area":null},{"id":"2510.07345","title":"Mitigating Surgical Data Imbalance with Dual-Prediction Video Diffusion Model","created":"2025-10-07","cited_by_count":1,"area":"diffusion"},{"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":"2512.08439","title":"LapFM: A Laparoscopic Segmentation Foundation Model via Hierarchical Concept Evolving Pre-training","created":"2025-12-09","cited_by_count":1,"area":null},{"id":"2512.19387","title":"DSTED: Decoupling Temporal Stabilization and Discriminative Enhancement for Surgical Workflow Recognition","created":"2025-12-22","cited_by_count":1,"area":null},{"id":"2602.20636","title":"SurgAtt-Tracker: Online Surgical Attention Tracking via Temporal Proposal Reranking and Motion-Aware Refinement","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2604.18134","title":"Can LLM-Generated Text Empower Surgical Vision-Language Pre-training?","created":"2026-04-20","cited_by_count":1,"area":"mllm"},{"id":"2606.31245","title":"HyperVLP: Enhancing Hierarchical Surgical Video-Language Pre-training in Hyperbolic Space","created":"2026-06-30","cited_by_count":1,"area":"mllm"},{"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":"2410.08509","title":"A Bayesian Approach to Weakly-supervised Laparoscopic Image Segmentation","created":"2024-10-11","cited_by_count":0,"area":null},{"id":"2503.10216","title":"CoStoDet-DDPM: Collaborative Training of Stochastic and Deterministic Models Improves Surgical Workflow Anticipation and Recognition","created":"2025-03-13","cited_by_count":0,"area":"diffusion"},{"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":"2506.14181","title":"Meta-SurDiff: Classification Diffusion Model Optimized by Meta Learning is Reliable for Online Surgical Phase Recognition","created":"2025-06-17","cited_by_count":0,"area":"diffusion"},{"id":"2507.18288","title":"TCM-Tongue: A Standardized Tongue Image Dataset with Pathological Annotations for AI-Assisted TCM Diagnosis","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2509.18796","title":"Towards Application Aligned Synthetic Surgical Image Synthesis","created":"2025-09-23","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":"2511.17805","title":"A Stitch in Time: Learning Procedural Workflow via Self-Supervised Plackett-Luce Ranking","created":"2025-11-21","cited_by_count":0,"area":null},{"id":"2512.24861","title":"OFL-SAM2: Prompt SAM2 with Online Few-shot Learner for Efficient Medical Image Segmentation","created":"2025-12-31","cited_by_count":0,"area":null},{"id":"2602.24138","title":"Multimodal Optimal Transport for Training-free Temporal Segmentation in Surgical Robotics","created":"2026-02-27","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":"2603.09496","title":"SurgFed: Language-guided Multi-Task Federated Learning for Surgical Video Understanding","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.20116","title":"Chain-of-Adaptation: Surgical Vision-Language Adaptation with Reinforcement Learning","created":"2026-03-20","cited_by_count":0,"area":"deeprl"},{"id":"2603.26400","title":"SHANDS: A Multi-View Dataset and Benchmark for Surgical Hand-Gesture and Error Recognition Toward Medical Training","created":"2026-03-27","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":"2606.23131","title":"Expert Consensus on Criteria for the Automated Assessment of Laparoscopic Camera Navigation","created":"2026-06-22","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":"2607.08397","title":"Attribute Retrieving for Open-Vocabulary Endoscopic Compositional Referring Segmentation","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.04676","title":"SurgNarrator: A Generative Retrieval Framework for Surgical Video Understanding","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.17935","title":"Beyond Instrument Motion: Recognizing Tissue Tension Toward Surgical Skill Assessment","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2609.23067","title":"LD-RSVIS: A Large-Scale and Diverse Benchmark for Referring Surgical Video Instrument Segmentation","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.27139","title":"A Hierarchy-Aware Video-Language Model Evaluation and Hyperbolic Baseline for Surgery","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.31821","title":"A Surgical Foundation Model Reveals Task-Dependent Label Efficiency","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}