DavidNguyen/seed
收藏Hugging Face2024-07-09 更新2024-07-22 收录
下载链接：
https://hf-mirror.com/datasets/DavidNguyen/seed
下载链接
链接失效反馈官方服务：
资源简介：
SEED-Bench是一个大规模的多模态大语言模型（MLLMs）评估基准，包含19K个多项选择题，覆盖12个评估维度，涉及图像和视频模态的理解。数据集于2023年7月收集，图像数据来自Conceptual Captions Dataset，视频数据来自Something-Something v2、Epic-kitchen 100和Breakfast数据集。主要用途是评估模型在空间和时间理解方面的能力，目标用户为计算机视觉、自然语言处理、机器学习和人工智能领域的研究者和爱好者。
SEED-Bench is a large-scale benchmark designed to evaluate Multimodal Large Language Models (MLLMs). It consists of 19K multiple choice questions with accurate human annotations, covering 12 evaluation dimensions including the comprehension of both the image and video modality. SEED-Bench was collected in July 2023 and is primarily intended for researchers and hobbyists in the fields of computer vision, natural language processing, machine learning, and artificial intelligence. The dataset uses images from the Conceptual Captions Dataset and videos from Something-Something v2, Epic-kitchen 100, and Breakfast datasets, adhering to their respective licenses.
提供机构：
DavidNguyen
