yale-nlp/MMVU
收藏Hugging Face2025-02-28 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/yale-nlp/MMVU
下载链接
链接失效反馈官方服务：
资源简介：
MMVU（多学科视频理解测量）数据集是一个包含3,000个专家注释的问答示例的数据集，这些示例涵盖了1,529个跨四个关键学科（科学、医疗保健、人文社会科学和工程）的专业领域视频。每个示例都提供了专家注释的推理理由和相关的领域知识，以评估模型在专业视频理解方面的推理质量和答案准确性。
MMVU (Measuring Expert-Level Multi-Discipline Video Understanding) is a dataset containing 3,000 expert-annotated QA examples across 1,529 specialized-domain videos in four key disciplines (Science, Healthcare, Humanities & Social Sciences, and Engineering). Each example comes with expert-annotated reasoning rationales and relevant domain knowledge to assess the models reasoning quality and answer correctness in specialized video understanding.
提供机构：
yale-nlp
