Jazzcharles/charadesego_videomae_L14_feature_fps8

---
license: apache-2.0
task_categories:
- video-classification
- video-retrieval
language:
- en
size_categories:
- 100M<n<1B
---

## 📙 Overview

CharadesEgo video features extracted by VideoMAE_L14 at 8 fps. It is used for evaluating the egovideo-exovideo retrieval ability of [EgoInstructor](https://arxiv.org/pdf/2401.00789).

It contains 7860 files, each file (e.g. 005BUEGO.pth.tar) is a TxD feature vector, where T refers to the length of the video and D is 768.

## 🏋️ How-To-Use

Please refer to code [EgoInstructor](https://github.com/Jazzcharles/Egoinstructor/) for details.

## 🎓 Citation
```
@article{xu2024retrieval,
title={Retrieval-augmented egocentric video captioning},
author={Xu, Jilan and Huang, Yifei and Hou, Junlin and Chen, Guo and Zhang, Yuejie and Feng, Rui and Xie, Weidi},
journal={arXiv preprint arXiv:2401.00789},
year={2024}
}
```

原始信息汇总

数据集概述

基本信息

• 许可证: Apache-2.0
• 任务类别:
  • 视频分类
  • 视频检索
• 语言: 英语
• 数据集大小: 100M<n<1B

数据集内容

• 数据集描述: CharadesEgo视频特征，由VideoMAE_L14模型以8帧/秒提取。用于评估EgoInstructor的egovideo-exovideo检索能力。
• 文件数量: 7860个文件
• 文件格式: 每个文件（例如：005BUEGO.pth.tar）包含一个TxD特征向量，其中T表示视频长度，D为768。

使用方法

• 使用指南: 请参考EgoInstructor代码以获取详细使用方法。

引用信息

@article{xu2024retrieval, title={Retrieval-augmented egocentric video captioning}, author={Xu, Jilan and Huang, Yifei and Hou, Junlin and Chen, Guo and Zhang, Yuejie and Feng, Rui and Xie, Weidi}, journal={arXiv preprint arXiv:2401.00789}, year={2024} }