{"total":32,"rows":[{"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":"2410.00263","title":"Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation","created":"2024-09-30","cited_by_count":39,"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":"2410.21348","title":"Large Language Model Benchmarks in Medical Tasks","created":"2024-10-28","cited_by_count":17,"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":"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":"2504.16749","title":"Feature Mixing Approach for Detecting Intraoperative Adverse Events in Laparoscopic Roux-en-Y Gastric Bypass Surgery","created":"2025-04-23","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":"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":"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":"2411.07619","title":"Artificial Intelligence for Biomedical Video Generation","created":"2024-11-12","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":"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":"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":"2506.08258","title":"Surgeons Awareness, Expectations, and Involvement with Artificial Intelligence: a Survey Pre and Post the GPT Era","created":"2025-06-09","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":"2605.21132","title":"SurgOnAir: Hierarchy-Aware Real-Time Surgical Video Commentary","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2406.18481","title":"Robust Surgical Phase Recognition From Annotation Efficient Supervision","created":"2024-06-26","cited_by_count":0,"area":null},{"id":"2509.06831","title":"Leveraging Generic Foundation Models for Multimodal Surgical Data Analysis","created":"2025-09-08","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":"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":"2606.22829","title":"DBT-Bleed: Dual-Branch Temporal Modeling with Key-Frame Selection for Surgical Bleeding Detection","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2608.02188","title":"SPIRIT: Spatio-temporal Pairwise Relational Modeling of Instrument-Tissue Interactions for Surgical Action Triplet Recognition","created":"2026-08-03","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":"2608.20154","title":"Artificial Intelligence for Workflow Analysis in Colorectal Surgery: A Multicentric, Cross-Procedural Development and Generalization Study","created":"2026-08-20","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}