{"total":108,"rows":[{"id":"2306.16741","title":"Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train","created":"2023-06-29","cited_by_count":75,"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":"2403.11050","title":"Endora: Video Generation Models as Endoscopy Simulators","created":"2024-03-17","cited_by_count":55,"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":"2207.00449","title":"Dissecting Self-Supervised Learning Methods for Surgical Computer Vision","created":"2022-07-01","cited_by_count":48,"area":null},{"id":"2204.04746","title":"CholecTriplet2021: A benchmark challenge for surgical action triplet recognition","created":"2022-04-10","cited_by_count":44,"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":"2312.10251","title":"Advancing Surgical VQA with Scene Graph Knowledge","created":"2023-12-15","cited_by_count":41,"area":null},{"id":"2312.11250","title":"Challenges in Multi-centric Generalization: Phase and Step Recognition in Roux-en-Y Gastric Bypass Surgery","created":"2023-12-18","cited_by_count":40,"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":"2212.04582","title":"Towards Holistic Surgical Scene Understanding","created":"2022-12-08","cited_by_count":33,"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":"2503.02579","title":"MM-OR: A Large Multimodal Operating Room Dataset for Semantic Understanding of High-Intensity Surgical Environments","created":"2025-03-04","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":"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":"2204.05235","title":"Data Splits and Metrics for Method Benchmarking on Surgical Action Triplet Datasets","created":"2022-04-11","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":"2307.09548","title":"Surgical Action Triplet Detection by Mixed Supervised Learning of Instrument-Tissue Interactions","created":"2023-07-18","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":"2312.07352","title":"CholecTrack20: A Multi-Perspective Tracking Dataset for Surgical Tools","created":"2023-12-12","cited_by_count":17,"area":null},{"id":"2410.21348","title":"Large Language Model Benchmarks in Medical Tasks","created":"2024-10-28","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":"2202.13402","title":"Concept Graph Neural Networks for Surgical Video Understanding","created":"2022-02-27","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":"2409.05442","title":"EndoOmni: Zero-Shot Cross-Dataset Depth Estimation in Endoscopy by Robust Self-Learning from Noisy Labels","created":"2024-09-09","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":"2410.17751","title":"VISAGE: Video Synthesis using Action Graphs for Surgery","created":"2024-10-23","cited_by_count":11,"area":null},{"id":"2505.24287","title":"EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity Understanding","created":"2025-05-30","cited_by_count":11,"area":null},{"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":"2507.05675","title":"MedGen: Unlocking Medical Video Generation by Scaling Granularly-annotated Medical Videos","created":"2025-07-08","cited_by_count":9,"area":null},{"id":"2303.17636","title":"Whether and When does Endoscopy Domain Pretraining Make Sense?","created":"2023-03-30","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":"2207.02247","title":"Video-based Surgical Skills Assessment using Long term Tool Tracking","created":"2022-07-05","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":"2203.08674","title":"Know your sensORs -- A Modality Study For Surgical Action Classification","created":"2022-03-16","cited_by_count":6,"area":null},{"id":"2209.01148","title":"ARST: Auto-Regressive Surgical Transformer for Phase Recognition from Laparoscopic Videos","created":"2022-09-02","cited_by_count":6,"area":null},{"id":"2407.09230","title":"Surgical Text-to-Image Generation","created":"2024-07-12","cited_by_count":6,"area":null},{"id":"2308.05232","title":"SegMatch: A semi-supervised learning method for surgical instrument segmentation","created":"2023-08-09","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":"2402.01974","title":"Hypergraph-Transformer (HGT) for Interactive Event Prediction in Laparoscopic and Robotic Surgery","created":"2024-02-03","cited_by_count":5,"area":null},{"id":"2209.08647","title":"Why Deep Surgical Models Fail?: Revisiting Surgical Action Triplet Recognition through the Lens of Robustness","created":"2022-09-18","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":"2309.11718","title":"CPR-Coach: Recognizing Composite Error Actions based on Single-class Training","created":"2023-09-21","cited_by_count":4,"area":null},{"id":"2407.13132","title":"LSD3K: A Benchmark for Smoke Removal from Laparoscopic Surgery Images","created":"2024-07-18","cited_by_count":4,"area":null},{"id":"2503.18296","title":"Surgical Action Planning with Large Language Models","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2506.01130","title":"ProstaTD: Bridging Surgical Triplet from Classification to Fully Supervised Detection","created":"2025-06-01","cited_by_count":4,"area":null},{"id":"2509.12893","title":"MEJO: MLLM-Engaged Surgical Triplet Recognition via Inter- and Intra-Task Joint Optimization","created":"2025-09-16","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":"2212.12719","title":"MURPHY: Relations Matter in Surgical Workflow Analysis","created":"2022-12-24","cited_by_count":3,"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":"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":"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":"2501.09555","title":"Text-driven Adaptation of Foundation Models for Few-shot Surgical Workflow Analysis","created":"2025-01-16","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":"2505.12890","title":"Specialized Foundation Models for Intelligent Operating Rooms","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2505.17677","title":"Towards Dynamic 3D Reconstruction of Hand-Instrument Interaction in Ophthalmic Surgery","created":"2025-05-23","cited_by_count":3,"area":null},{"id":"2507.05020","title":"Adaptation of Multi-modal Representation Models for Multi-task Surgical Computer Vision","created":"2025-07-07","cited_by_count":3,"area":null},{"id":"2509.20941","title":"Decoding the Surgical Scene: A Scoping Review of Scene Graphs in Surgery","created":"2025-09-25","cited_by_count":3,"area":null},{"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":"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":"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":"2402.03093","title":"AI-Enhanced Virtual Reality in Medicine: A Comprehensive Survey","created":"2024-02-05","cited_by_count":2,"area":null},{"id":"2411.07619","title":"Artificial Intelligence for Biomedical Video Generation","created":"2024-11-12","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":"2507.05007","title":"Multi-modal Representations for Fine-grained Multi-label Critical View of Safety Recognition","created":"2025-07-07","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":"2603.16822","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":"2606.25905","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":"2205.03028","title":"Quantification of Robotic Surgeries with Vision-Based Deep Learning","created":"2022-05-06","cited_by_count":1,"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":"2502.07008","title":"Early Operative Difficulty Assessment in Laparoscopic Cholecystectomy via Snapshot-Centric Video Analysis","created":"2025-02-10","cited_by_count":1,"area":null},{"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":"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":"2603.29962","title":"SurgTEMP: Temporal-Aware Surgical Video Question Answering with Text-guided Visual Memory for Laparoscopic Cholecystectomy","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2603.29966","title":"Scaling Video Pretraining for Surgical Foundation Models","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2606.00712","title":"CASTLE2026 Team WDL Technical Report","created":"2026-05-30","cited_by_count":1,"area":null},{"id":"2503.02558","title":"Tracking-Aware Deformation Field Estimation for Non-rigid 3D Reconstruction in Robotic Surgeries","created":"2025-03-04","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":"2507.06643","title":"Learning from Sparse Point Labels for Dense Carcinosis Localization in Advanced Ovarian Cancer Assessment","created":"2025-07-09","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":"2510.12904","title":"State-Change Learning for Prediction of Future Events in Endoscopic Videos","created":"2025-10-14","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":"2511.04525","title":"Learning from Single Timestamps: Complexity Estimation in Laparoscopic Cholecystectomy","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2511.15159","title":"Generating Natural-Language Surgical Feedback: From Structured Representation to Domain-Grounded Evaluation","created":"2025-11-19","cited_by_count":0,"area":null},{"id":"2601.12312","title":"CurConMix+: A Unified Spatio-Temporal Framework for Hierarchical Surgical Workflow Understanding","created":"2026-01-18","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":"2603.25778","title":"Focus-to-Perceive Representation Learning: A Cognition-Inspired Hierarchical Framework for Endoscopic Video Analysis","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2605.11208","title":"Hi-GaTA: Hierarchical Gated Temporal Aggregation Adapter for Surgical Video Report Generation","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":"2606.30657","title":"AI for Quality Assurance in the Operating Room","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2607.19889","title":"Latent-Action-Guided Video-Language Feature Learning for Surgical Instrument-Tissue Interaction Recognition","created":"2026-07-22","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":"2608.04606","title":"TRCoRSurg: Temporal-Relational Co-Reasoning for Surgical Video Triplet Recognition","created":"2026-08-05","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}],"next_cursor":"100"}