VideoChat-Flash-Training-Data

# 🦜 VideoChat-Flash-Training-Data

This repos contains all annotaions and part videos of LongVid for training VideoChat-Flash.

## 📕 How to use the LongVid data?

For video_dir like `longvid_subset/coin_grounding_10k_zip`, you need to concat this dir to a zip file as follows:
```bash
cat ego4dhcap_eventunderstanding_2k_zip/* > ego4dhcap_eventunderstanding_2k.zip
```

## ✏️ Citation

```bibtex

@article{li2024videochatflash,
title={VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling},
author={Li, Xinhao and Wang, Yi and Yu, Jiashuo and Zeng, Xiangyu and Zhu, Yuhan and Huang, Haian and Gao, Jianfei and Li, Kunchang and He, Yinan and Wang, Chenting and others},
journal={arXiv preprint arXiv:2501.00574},
year={2024}
}

# 🦜 VideoChat-Flash 训练数据集

本代码仓库包含用于训练VideoChat-Flash的LongVid数据集的全部标注文件与部分视频素材。

## 📕 LongVid 数据集使用方法

针对形如`longvid_subset/coin_grounding_10k_zip`的视频目录，需按如下方式将该目录下的所有文件合并为单个压缩包：
bash
cat ego4dhcap_eventunderstanding_2k_zip/* > ego4dhcap_eventunderstanding_2k.zip

## ✏️ 引用格式

bibtex
@article{li2024videochatflash,
title={VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling},
author={Li, Xinhao and Wang, Yi and Yu, Jiashuo and Zeng, Xiangyu and Zhu, Yuhan and Huang, Haian and Gao, Jianfei and Li, Kunchang and He, Yinan and Wang, Chenting and others},
journal={arXiv preprint arXiv:2501.00574},
year={2024}
}

搜集汇总

背景与挑战

背景概述

VideoChat-Flash-Training-Data是一个用于训练VideoChat-Flash模型的数据集，包含LongVid的注释和部分视频内容。该数据集采用Apache 2.0许可证，由OpenGVLab提供，更新于2025年5月10日，总大小为820.97GB。