m-a-p/IV-Bench
收藏Hugging Face2025-04-20 更新2025-05-31 收录
下载链接:
https://hf-mirror.com/datasets/m-a-p/IV-Bench
下载链接
链接失效反馈官方服务:
资源简介:
IV-Bench是一个针对多模态大型语言模型在图像基础上的视频感知和推理的基准数据集,包含视频ID、图像-文本查询和干扰项的1680个样本。
IV-Bench is a benchmark dataset for image-grounded video perception and reasoning in multimodal large language models, consisting of 1,680 samples with video IDs, image-text queries, and distractors.
提供机构:
m-a-p



