{"total":15,"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":"2307.03719","title":"Polybot: Training One Policy Across Robots While Embracing Variability","created":"2023-07-07","cited_by_count":28,"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":"2107.11091","title":"Class-Incremental Domain Adaptation with Smoothing and Calibration for Surgical Report Generation","created":"2021-07-23","cited_by_count":18,"area":null},{"id":"2306.00451","title":"S$^2$ME: Spatial-Spectral Mutual Teaching and Ensemble Learning for Scribble-supervised Polyp Segmentation","created":"2023-06-01","cited_by_count":15,"area":null},{"id":"2306.02651","title":"Dynamic Interactive Relation Capturing via Scene Graph Learning for Robotic Surgical Report Generation","created":"2023-06-05","cited_by_count":14,"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":"2306.03511","title":"Curriculum-Based Augmented Fourier Domain Adaptation for Robust Medical Image Segmentation","created":"2023-06-06","cited_by_count":7,"area":null},{"id":"2207.00113","title":"Rethinking Surgical Captioning: End-to-End Window-Based MLP Transformer Using Patches","created":"2022-06-30","cited_by_count":5,"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":"2306.16285","title":"Generalizing Surgical Instruments Segmentation to Unseen Domains with One-to-Many Synthesis","created":"2023-06-28","cited_by_count":2,"area":null},{"id":"2504.19918","title":"Enhancing Surgical Documentation through Multimodal Visual-Temporal Transformers and Generative AI","created":"2025-04-28","cited_by_count":2,"area":null},{"id":"2212.11511","title":"Confidence-Aware Paced-Curriculum Learning by Label Smoothing for Surgical Scene Understanding","created":"2022-12-22","cited_by_count":1,"area":null},{"id":"2511.12026","title":"Bridging Vision and Language for Robust Context-Aware Surgical Point Tracking: The VL-SurgPT Dataset and Benchmark","created":"2025-11-15","cited_by_count":0,"area":null}],"next_cursor":null}