TencentARC/Video-Holmes
收藏Hugging Face2025-09-23 更新2025-05-31 收录
下载链接：
https://hf-mirror.com/datasets/TencentARC/Video-Holmes
下载链接
链接失效反馈官方服务：
资源简介：
Video-Holmes是一个评估多模态大型语言模型在复杂视频推理方面的能力的基准数据集。它由270个手动注释的悬疑短片（长度在1到5分钟之间）组成，共包含7个精心设计的任务。每个任务都通过识别影片中的关键事件和因果关系来构造，并设计出需要模型积极定位和连接不同视频片段中多个相关视觉线索的问题。
Video-Holmes is a benchmark designed to evaluate the complex video reasoning capabilities of Multimodal Large Language Models (MLLMs). It consists of 270 manually annotated suspense short films (ranging from 1 to 5 minutes), which encompass seven carefully designed tasks. Each task is constructed by identifying key events and causal relationships within films and then designing questions that require models to actively locate and connect multiple relevant visual clues scattered across different video segments.
提供机构：
TencentARC
