LORIS

# Dataset Card for LORIS

## Dataset Description

- **Homepage:** [LORIS](https://justinyuu.github.io/LORIS)
- **Repository:** [OpenGVLab-LORIS](https://github.com/OpenGVLab/LORIS)
- **Paper:** [2305.01319](https://arxiv.org/pdf/2305.01319.pdf)
- **Point of Contact:** [Jiashuo Yu](mailto:[e-mail])

### Dataset Summary

LORIS dataset is a large-scale rhythmic video soundtrack dataset that includes 86.43h long-term, high-quality raw videos with corresponding 2D poses, RGB features, and ameliorated audio waveforms. This dataset is originally used for the video background music generation task (a.k.a. video soundtracks).

### Get Started

from datasets import load_dataset
dataset = load_dataset("OpenGVLab/LORIS")

### Citation Information

@inproceedings{Yu2023Long,
title={Long-Term Rhythmic Video Soundtracker},
author={Yu, Jiashuo and Wang, Yaohui and Chen, Xinyuan and Sun, Xiao and Qiao, Yu },
booktitle={International Conference on Machine Learning (ICML)},
year={2023}
}

# LORIS 数据集卡片

## 数据集说明
- **项目主页：** [LORIS](https://justinyuu.github.io/LORIS)
- **代码仓库：** [OpenGVLab-LORIS](https://github.com/OpenGVLab/LORIS)
- **论文：** [2305.01319](https://arxiv.org/pdf/2305.01319.pdf)
- **联系人：** [Jiashuo Yu](mailto:[e-mail])

### 数据集概述
LORIS数据集是一款大规模节律性视频配乐数据集，包含86.43小时的长期高质量原始视频，以及对应的2D姿态（2D poses）、RGB特征与优化后的音频波形。本数据集最初用于视频背景音乐生成任务（亦称为视频配乐任务）。

### 快速上手
from datasets import load_dataset
dataset = load_dataset("OpenGVLab/LORIS")

### 引用信息
@inproceedings{Yu2023Long,
title={长时序节律视频配乐器},
author={Yu, Jiashuo and Wang, Yaohui and Chen, Xinyuan and Sun, Xiao and Qiao, Yu },
booktitle={国际机器学习大会（ICML)},
year={2023}
}