TIGER-Lab/MMEB-V2

MMEB-V2（大规模多模态嵌入基准）在原始的MMEB基础上扩展了评估范围，包括五个新任务：四个基于视频的任务——视频检索、时刻检索、视频分类和视频问答，以及一个关注视觉文档的视觉文档检索任务。这套全面的评估套件能够对静态、时态和结构化视觉数据设置下的多模态嵌入模型进行稳健评估。此Hugging Face存储库仅包含MMEB-V2中使用的原始图像和视频文件，这些文件需要提前下载。MMEB-V2 (Massive Multimodal Embedding Benchmark) builds upon the original MMEB and expands the evaluation scope to include five new tasks: four video-based tasks — Video Retrieval, Moment Retrieval, Video Classification, and Video Question Answering — and one task focused on visual documents, Visual Document Retrieval. This comprehensive suite enables robust evaluation of multimodal embedding models across static, temporal, and structured visual data settings. This Hugging Face repository contains only the raw image and video files used in MMEB-V2, which need to be downloaded in advance.

搜集汇总

背景与挑战

背景概述

MMEB-V2是一个用于评估多模态嵌入模型的大规模基准测试数据集，新增了五个视频和视觉文档相关任务，提供图像和视频帧数据，需提前下载。数据集结构清晰，包含视频任务和图像任务的分类文件。