{"total":38,"rows":[{"id":"2109.03223","title":"Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos","created":"2021-09-07","cited_by_count":141,"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":"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":"2212.04155","title":"Latent Graph Representations for Critical View of Safety Assessment","created":"2022-12-08","cited_by_count":37,"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":"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":"2107.04810","title":"Not End-to-End: Explore Multi-Stage Architecture for Online Surgical Phase Recognition","created":"2021-07-10","cited_by_count":20,"area":null},{"id":"2110.13972","title":"Video-based fully automatic assessment of open surgery suturing skills","created":"2021-10-26","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":"2301.07053","title":"Preserving Privacy in Surgical Video Analysis Using Artificial Intelligence: A Deep Learning Classifier to Identify Out-of-Body Scenes in Endoscopic Videos","created":"2023-01-17","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":"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":"2209.14647","title":"Bounded Future MS-TCN++ for surgical gesture recognition","created":"2022-09-29","cited_by_count":5,"area":null},{"id":"2302.10834","title":"Weakly Supervised Temporal Convolutional Networks for Fine-grained Surgical Activity Recognition","created":"2023-02-21","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":"2212.12719","title":"MURPHY: Relations Matter in Surgical Workflow Analysis","created":"2022-12-24","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":"2506.21330","title":"Holistic Surgical Phase Recognition with Hierarchical Input Dependent State Space Models","created":"2025-06-26","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":"2203.04301","title":"Live Laparoscopic Video Retrieval with Compressed Uncertainty","created":"2022-03-08","cited_by_count":2,"area":null},{"id":"2206.12320","title":"PoCaP Corpus: A Multimodal Dataset for Smart Operating Room Speech Assistant using Interventional Radiology Workflow Analysis","created":"2022-06-24","cited_by_count":2,"area":null},{"id":"2502.06708","title":"TEMSET-24K: Densely Annotated Dataset for Indexing Multipart Endoscopic Videos using Surgical Timeline Segmentation","created":"2025-02-10","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":"2109.11192","title":"Predicting the Timing of Camera Movements From the Kinematics of Instruments in Robotic-Assisted Surgery Using Artificial Neural Networks","created":"2021-09-23","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":"2502.03430","title":"A Temporal Convolutional Network-Based Approach and a Benchmark Dataset for Colonoscopy Video Temporal Segmentation","created":"2025-02-05","cited_by_count":1,"area":null},{"id":"2506.06830","title":"EndoARSS: Adapting Spatially-Aware Foundation Model for Efficient Activity Recognition and Semantic Segmentation in Endoscopic Surgery","created":"2025-06-07","cited_by_count":1,"area":null},{"id":"2507.09294","title":"Geo-RepNet: Geometry-Aware Representation Learning for Surgical Phase Recognition in Endoscopic Submucosal Dissection","created":"2025-07-12","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":"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":"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":"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":"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":"2608.20154","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":"2608.31065","title":"Multimodal Shared Latent Representation of Narration, Microscope and iOCT Images for Phase Recognition in Vitreoretinal Surgery","created":"2026-08-31","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}],"next_cursor":null}