<img src="https://raw.githubusercontent.com/V3Det/v3det_resource/main/resource/cover.png" alt="Cover Image" style="width: 820px;">

  ## Introduction
  V3Det is a Vast Vocabulary Visual Detection Dataset with accurately annotated more than 13,000 object categories, empowering more comprehensive research in object detection.  
  1)   Vast Vocabulary：V3Det contains bounding boxes of objects from more than 13,000 categories on real-world images.
  2)   Hierarchical Category Organization：V3Det is organized by a hierarchical category tree which annotates the inclusion relationship among categories.
  3)   Rich Annotations：V3Det comprises precisely annotated objects in 245k images and professional descriptions of each category written by human experts and chatgpt.

  ###  Data
![](https://github.com/ztayty/ztayty.github.io/blob/main/image/%E6%95%B0%E6%8D%AE%EF%BC%88%E8%BF%90%E8%90%A5%E6%89%8B%E5%8A%A8%E4%B8%8A%E6%9E%B6%E5%88%B0%E7%B1%BB%E5%AE%9A%E4%B9%89%EF%BC%89.jpg?raw=true)
  
  ## Citation
  Please cite the following paper when using V3Det
  ```
  @misc{wang2023v3det,  
      title={V3Det: Vast Vocabulary Visual Detection Dataset},   
      author={Jiaqi Wang and Pan Zhang and Tao Chu and Yuhang Cao and Yujie Zhou and Tong Wu and Bin Wang and Conghui He and Dahua Lin},  
      year={2023},  
      eprint={2304.03752},  
      archivePrefix={arXiv},  
      primaryClass={cs.CV}  
}
```
  ‌​‌‌​​​​‌​​​‌‌‌‌‌​​‌‌​‌​‌​​‌​​​‌‌​‌‌‌​‌‌‌​​‌‌‌‌​‌​​​‌​‌‌‌​​‌‌‌‌​‌​‌‌​​‌‌‌​​‌‌‌‌​‌​​‌‌‌​‌