MMEB_Raw_Video

# MMEB-V2 (Massive Multimodal Embedding Benchmark)

[**Website**](https://tiger-ai-lab.github.io/VLM2Vec/) |[**Github**](https://github.com/TIGER-AI-Lab/VLM2Vec) | [**🏆Leaderboard**](https://huggingface.co/spaces/TIGER-Lab/MMEB) | [**📖MMEB-V2/VLM2Vec-V2 Paper**](https://arxiv.org/abs/2507.04590) | | [**📖MMEB-V1/VLM2Vec-V1 Paper**](https://arxiv.org/abs/2410.05160) |

## Introduction

Building upon on our original [**MMEB**](https://arxiv.org/abs/2410.05160), **MMEB-V2** 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 the raw video files used in MMEB-V2. Typically, video frames are all you need, but we also release the raw video files here in case they are needed.**
**Please check the [main data repository](https://huggingface.co/datasets/TIGER-Lab/MMEB-V2) for instructions on all MMEB-V2–related data.**

# MMEB-V2（大规模多模态嵌入基准测试，Massive Multimodal Embedding Benchmark）

[**官网**](https://tiger-ai-lab.github.io/VLM2Vec/) |[**Github仓库**](https://github.com/TIGER-AI-Lab/VLM2Vec) | [**🏆排行榜**](https://huggingface.co/spaces/TIGER-Lab/MMEB) | [**📖MMEB-V2/VLM2Vec-V2 论文**](https://arxiv.org/abs/2507.04590) | | [**📖MMEB-V1/VLM2Vec-V1 论文**](https://arxiv.org/abs/2410.05160) |

## 简介

本工作基于此前推出的[**MMEB（大规模多模态嵌入基准测试，Massive Multimodal Embedding Benchmark）**](https://arxiv.org/abs/2410.05160)进行拓展，**MMEB-V2**将评估范围扩展至五项全新任务：四项基于视频的任务——视频检索、片段检索、视频分类以及视频问答，以及一项面向视觉文档的任务：视觉文档检索。这套全面的评估套件可对多模态嵌入模型在静态、时序与结构化视觉数据场景下的性能开展稳健评估。

**本Hugging Face仓库包含MMEB-V2所使用的原始视频文件。通常仅需视频帧即可满足需求，但我们仍在此处发布原始视频文件以备不时之需。**
**请查阅[主数据仓库](https://huggingface.co/datasets/TIGER-Lab/MMEB-V2)以获取所有MMEB-V2相关数据的使用说明。**

搜集汇总

背景与挑战

背景概述

MMEB_Raw_Video是MMEB-V2基准测试的原始视频数据集，由TIGER-Lab发布，包含1.08TB的视频文件，用于评估多模态嵌入模型在视频检索、分类和问答等任务中的性能。该数据集作为MMEB-V2的补充资源，提供原始视频以便在需要时使用，但通常视频帧已足够用于相关研究。