arXiv cs.AI· Junseob Kim, Jade Chng, Ayman Ali, Victor Moas, Yichun Lee, Po-Chun Chin, Sunil Hwang, Rishikesan Kamaleswaran·· 10 天前AI 评分22
TC3-VQA：面向战术战伤救治的视觉问答数据集发布
A doctrine-grounded visual question answering dataset for Tactical Combat Casualty Care
AI 导读
研究者发布 TC3-VQA 数据集，用于让视觉语言模型把伤情与干预的视觉观察同权威 TC3 指南关联起来。数据集由公开教学与实战 TC3 视频及权威 TC3 文档构建，含 581 个条目、覆盖 11 个概念、共 1,860 个问题，涉及干预识别、指南、临床推理、操作指导及视觉信息不足时的拒答。
正文 · 原文
Abstract:Tactical Combat Casualty Care (TC3) requires responders to connect visual observations of injuries and interventions with established clinical guidance. Developing vision-language models to support this process requires supervision that links visible evidence to traceable doctrine. We present TC3-VQA, a dataset constructed from public instructional and field TC3 videos and authoritative TC3 documents. It contains 581 items spanning 11 concepts, with 1,860 questions covering intervention recognition, doctrine, clinical reasoning, procedural guidance, and refusal when visual information is insufficient. Doctrine-based answers preserve verbatim source passages and character offsets. Construction combines visual annotation, passage retrieval, entailment checks, and verification across model families. Equipment boxes, anatomical labels, temporal segments, and source metadata accompany the question-answer pairs. Automated audits and ratings by two physicians and two medical students characterize annotation quality, with human ratings available for 88 retained items. The dataset provides a resource for adapting vision-language models to TC3, studying the connection between visual evidence and clinical knowledge, and evaluating recognition, doctrine recall, and abstention.
| Comments: | 20 pages, 6 figures, 5 tables. Dataset: this https URL code: this https URL |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.07339 [cs.CV] |
| (or arXiv:2610.07339v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07339 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Junseob Kim [view email]
[v1]
Mon, 5 Oct 2026 20:14:31 UTC (984 KB)
来源：arXiv cs.AI · arxiv.org