---
title: VILD
canonical_url: "https://www.modelscope.cn/models/pai/VILD"
md_url: "https://www.modelscope.cn/models/pai/VILD.md"
repository: pai/VILD
last_updated: 2025-04-08
license: cc-by-nc-sa-4.0
library_name:
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 512
stars: 0
---

# VILD

> VILD - pai 在 ModelScope 开源的模型。The VILD Dataset (VIdeo and Long-Description)

pai/VILD 是 ModelScope 魔搭社区上的机器学习模型，采用 cc-by-nc-sa-4.0 许可。

- **Repository**: pai/VILD
- **License**: cc-by-nc-sa-4.0
- **Downloads**: 512
- **Stars**: 0
- **Last updated**: 2025-04-08

Source: https://www.modelscope.cn/models/pai/VILD

---

# The VILD Dataset (VIdeo and Long-Description)

This dataset is proposed from [VideoCLIP-XL](https://arxiv.org/abs/2410.00741). 
We establish an automatic data collection system, designed to aggregate sufficient and high-quality pairs from multiple data sources. 
We have successfully collected over 2M (VIdeo, Long Description) pairs, denoted as our VILD dataset.

# Format
```json 
{
  "short_captions": [
        "...",
    ],
  "long_captions": [
        "...",
    ],
  "video_id": "..."
}
{
  .....
},
.....
```


# Source
~~~
@misc{wang2024videoclipxladvancinglongdescription,
      title={VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models}, 
      author={Jiapeng Wang and Chengyu Wang and Kunzhe Huang and Jun Huang and Lianwen Jin},
      year={2024},
      eprint={2410.00741},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2410.00741}, 
}
~~~