{"total":18,"rows":[{"id":"2203.06667","title":"Towards Visual-Prompt Temporal Answering Grounding in Medical Instructional Video","created":"2022-03-13","cited_by_count":43,"area":null},{"id":"2405.06887","title":"FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment","created":"2024-05-11","cited_by_count":25,"area":null},{"id":"2310.13347","title":"NurViD: A Large Expert-Level Video Database for Nursing Procedure Activity Understanding","created":"2023-10-20","cited_by_count":20,"area":null},{"id":"2410.21348","title":"Large Language Model Benchmarks in Medical Tasks","created":"2024-10-28","cited_by_count":17,"area":null},{"id":"2504.11373","title":"Cancer-Myth: Evaluating Large Language Models on Patient Questions with False Presuppositions","created":"2025-04-15","cited_by_count":15,"area":null},{"id":"2210.05423","title":"Learning to Locate Visual Answer in Video Corpus Using Question","created":"2022-10-11","cited_by_count":10,"area":null},{"id":"2210.14823","title":"Visual Answer Localization with Cross-modal Mutual Knowledge Transfer","created":"2022-10-26","cited_by_count":7,"area":null},{"id":"2210.02401","title":"Medical Image Retrieval via Nearest Neighbor Search on Pre-trained Image Features","created":"2022-10-05","cited_by_count":3,"area":null},{"id":"2211.01824","title":"Human in the loop approaches in multi-modal conversational task guidance system development","created":"2022-11-03","cited_by_count":2,"area":null},{"id":"2407.06597","title":"TVR-Ranking: A Dataset for Ranked Video Moment Retrieval with Imprecise Queries","created":"2024-07-09","cited_by_count":2,"area":null},{"id":"2412.11056","title":"Overview of TREC 2024 Medical Video Question Answering (MedVidQA) Track","created":"2024-12-15","cited_by_count":2,"area":null},{"id":"2504.15918","title":"Ask2Loc: Learning to Locate Instructional Visual Answers by Asking Questions","created":"2025-04-22","cited_by_count":2,"area":null},{"id":"2512.01045","title":"Med-CRAFT: An Information System for Explainable and Configurable Construction of Multimodal Medical QA Datasets","created":"2025-11-30","cited_by_count":2,"area":null},{"id":"2309.12224","title":"Towards Answering Health-related Questions from Medical Videos: Datasets and Approaches","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2607.06618","title":"Overview of the NLPCC 2026 Shared Task 1: Difficulty-Aware Multilingual and Multimodal Medical Instructional Video Understanding Evaluation","created":"2026-07-07","cited_by_count":1,"area":null},{"id":"2402.15096","title":"Multimodal Transformer With a Low-Computational-Cost Guarantee","created":"2024-02-23","cited_by_count":0,"area":null},{"id":"2608.06869","title":"DAEP: Difficulty-Aware Evidence Planning for Medical Video Corpus Temporal Answer Grounding","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2609.32957","title":"DynamicDx: Evaluating Evidence Acquisition in Video-Based Diagnosis","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}