{"total":32,"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":"2109.14956","title":"Comparative Validation of Machine Learning Algorithms for Surgical Workflow and Skill Analysis with the HeiChole Benchmark","created":"2021-09-30","cited_by_count":60,"area":null},{"id":"2305.08989","title":"LoViT: Long Video Transformer for Surgical Phase Recognition","created":"2023-05-15","cited_by_count":56,"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":"2102.12218","title":"Multi-Task Temporal Convolutional Networks for Joint Recognition of Surgical Phases and Steps in Gastric Bypass Procedures","created":"2021-02-24","cited_by_count":42,"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":"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":"2108.02238","title":"The Impact of Machine Learning on 2D/3D Registration for Image-guided Interventions: A Systematic Review and Perspective","created":"2021-08-04","cited_by_count":22,"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":"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":"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":"2108.11801","title":"Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the operating room","created":"2021-08-26","cited_by_count":7,"area":null},{"id":"2112.13815","title":"Temporally Constrained Neural Networks (TCNN): A framework for semi-supervised video semantic segmentation","created":"2021-12-27","cited_by_count":6,"area":null},{"id":"2312.12250","title":"ST(OR)2: Spatio-Temporal Object Level Reasoning for Activity Recognition in the Operating Room","created":"2023-12-19","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":"2207.03083","title":"Adaptation of Surgical Activity Recognition Models Across Operating Rooms","created":"2022-07-07","cited_by_count":5,"area":null},{"id":"2212.14177","title":"Current State of Community-Driven Radiological AI Deployment in Medical Imaging","created":"2022-12-29","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":"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":"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":"2105.00762","title":"VECA : A Toolkit for Building Virtual Environments to Train and Test Human-like Agents","created":"2021-05-03","cited_by_count":1,"area":null},{"id":"2409.07801","title":"SURGIVID: Annotation-Efficient Surgical Video Object Discovery","created":"2024-09-12","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":"2509.10748","title":"SCOPE: Speech-guided COllaborative PErception Framework for Surgical Scene Segmentation","created":"2025-09-12","cited_by_count":1,"area":null},{"id":"2603.16024","title":"Speak, Segment, Track, Navigate: An Interactive System for Video-Guided Skull-Base Surgery","created":"2026-03-17","cited_by_count":1,"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":"2512.10379","title":"Self-Supervised Contrastive Embedding Adaptation for Endoscopic Image Matching","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2602.02850","title":"Self-Supervised Uncalibrated Multi-View Video Anonymization in the Operating Room","created":"2026-02-02","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}],"next_cursor":null}