Action_Recognition_in_the_Dark
收藏魔搭社区2025-08-06 更新2024-08-31 收录
下载链接:
https://modelscope.cn/datasets/OmniData/Action_Recognition_in_the_Dark
下载链接
链接失效反馈官方服务:
资源简介:
displayName: Action Recognition in the Dark (ARID)
labelTypes:
- Classification
license:
- CC BY 4.0
mediaTypes:
- Video
paperUrl: https://arxiv.org/pdf/2006.03876v3.pdf
publishDate: "2021"
publishUrl: https://xuyu0010.github.io/arid
publisher:
- Nanyang Technological University
- NVIDIA AI
tags:
- Action
- Human Body
taskTypes:
- Action Recognition
- Video Classification
---
# 数据集介绍
## 简介
ARID 是用于在黑暗视频中进行动作识别的数据集。它包含在11个动作类别中的利用普通摄像机拍摄的超过5,572个视频剪辑(v1.5)。这些视频剪辑涵盖了24个不同的室内/室外黑暗场景。它的最新版本为v1.5版本,其v1版本仍然可以被下载/使用(两个版本均已提供,请按需下载)。
## 类定义
```
Drinking
Jumping
Picking
Pouring
Pushing
Running
Sitting
Standing
Turning
Walking
Waving
```
## 引文
```
@article{xu2020arid,
title={ARID: A Comprehensive Study on Recognizing Actions in the Dark and A New Benchmark Dataset},
author={Xu, Yuecong and Yang, Jianfei and Cao, Haozhi and Mao, Kezhi and Yin, Jianxiong and See, Simon},
journal={arXiv preprint arXiv:2006.03876},
year={2020}
}
```
## Download dataset
:modelscope-code[]{type="git"}
displayName: 黑暗环境下动作识别(Action Recognition in the Dark, ARID)
labelTypes:
- 分类(Classification)
license:
- 知识共享署名4.0(CC BY 4.0)
mediaTypes:
- 视频(Video)
paperUrl: https://arxiv.org/pdf/2006.03876v3.pdf
publishDate: "2021"
publishUrl: https://xuyu0010.github.io/arid
publisher:
- 南洋理工大学(Nanyang Technological University)
- 英伟达人工智能(NVIDIA AI)
tags:
- 动作(Action)
- 人体(Human Body)
taskTypes:
- 动作识别(Action Recognition)
- 视频分类(Video Classification)
---
# 数据集介绍
## 简介
ARID是面向黑暗场景视频动作识别的专用基准数据集。其v1.5版本包含11个动作类别下、由普通消费级摄像机采集的超5572段视频剪辑,涵盖24种不同的室内/室外黑暗场景。当前最新版本为v1.5,v1版本仍可下载使用(两个版本均已提供,可按需获取)。
## 类定义
饮酒(Drinking)
跳跃(Jumping)
拾取(Picking)
倾倒(Pouring)
推挤(Pushing)
奔跑(Running)
就坐(Sitting)
站立(Standing)
转身(Turning)
行走(Walking)
挥手(Waving)
## 引文
@article{xu2020arid,
title={ARID: A Comprehensive Study on Recognizing Actions in the Dark and A New Benchmark Dataset},
author={Xu, Yuecong and Yang, Jianfei and Cao, Haozhi and Mao, Kezhi and Yin, Jianxiong and See, Simon},
journal={arXiv preprint arXiv:2006.03876},
year={2020}
}
## 下载数据集
:modelscope-code[]{type="git"}
提供机构:
maas
创建时间:
2024-06-29



