{"total":45,"rows":[{"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":"2305.13689","title":"Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Training","created":"2023-05-23","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":"2212.04155","title":"Latent Graph Representations for Critical View of Safety Assessment","created":"2022-12-08","cited_by_count":37,"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":"2308.12394","title":"Self-Supervised Learning for Endoscopic Video Analysis","created":"2023-08-23","cited_by_count":22,"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":"2312.07352","title":"CholecTrack20: A Multi-Perspective Tracking Dataset for Surgical Tools","created":"2023-12-12","cited_by_count":17,"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":"2506.02692","title":"Large-scale Self-supervised Video Foundation Model for Intelligent Surgery","created":"2025-06-03","cited_by_count":10,"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":"2306.00197","title":"SSL-CPCD: Self-supervised learning with composite pretext-class discrimination for improved generalisability in endoscopic image analysis","created":"2023-05-31","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":"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":"2405.03762","title":"Swin transformers are robust to distribution and concept drift in endoscopy-based longitudinal rectal cancer assessment","created":"2024-05-06","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":"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":"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":"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":"2510.16371","title":"Cataract-LMM Large-Scale Multi-Source Multi-Task Benchmark for Deep Learning in Surgical Video Analysis","created":"2025-10-18","cited_by_count":3,"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":"2401.06278","title":"A Study on Self-Supervised Pretraining for Vision Problems in Gastrointestinal Endoscopy","created":"2024-01-11","cited_by_count":2,"area":null},{"id":"2509.09327","title":"Exploring Pre-training Across Domains for Few-Shot Surgical Skill Assessment","created":"2025-09-11","cited_by_count":2,"area":null},{"id":"2410.14242","title":"Pseudo-label Refinement for Improving Self-Supervised Learning Systems","created":"2024-10-18","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":"2510.19829","title":"SSL-SE-EEG: A Framework for Robust Learning from Unlabeled EEG Data with Self-Supervised Learning and Squeeze-Excitation Networks","created":"2025-10-07","cited_by_count":1,"area":null},{"id":"2312.12599","title":"Unsupervised Segmentation of Colonoscopy Images","created":"2023-12-19","cited_by_count":0,"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":"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":"2508.07897","title":"NeeCo: Image Synthesis of Novel Instrument States Based on Dynamic and Deformable 3D Gaussian Reconstruction","created":"2025-08-11","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":"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":"2512.03883","title":"Dual Cross-Attention Siamese Transformer for Rectal Tumor Regrowth Assessment in Watch-and-Wait Endoscopy","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2601.18929","title":"On the Role of Depth in Surgical Vision Foundation Models: An Empirical Study of RGB-D Pre-training","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2603.24897","title":"SurgPhase: Time efficient pituitary tumor surgery phase recognition via an interactive web platform","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2605.12855","title":"Prediction of Rectal Cancer Regrowth from Longitudinal Endoscopy","created":"2026-05-13","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":"2609.04555","title":"DART: Depth-as-Target Pretraining for Surgical Vision Foundation Models","created":"2026-09-03","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}