• Home
  • Challenge
  • Download
  • Preview
δΈ­EN

Accurately annotated more than 13,000 object categories, empowering more comprehensive research in object detection.

Dataset download

Features

Vast
Vocabulary

V3Det contains bounding boxes of objects from more than 13,000 categories on real-world images.

Hierarchical Category Organization

V3Det is organized by a hierarchical category tree which annotates the inclusion relationship among categories.

Rich
Annotations

V3Det comprises precisely annotated objects in 245k images and professional descriptions of each category written by human experts and chatgpt.

Examples

Citation

Please cite the following paper when using V3Det

@inproceedings{wang2023v3det,
      title = {V3Det: Vast Vocabulary Visual Detection Dataset}, 
      author = {Wang, Jiaqi and Zhang, Pan and Chu, Tao and Cao, Yuhang and Zhou, Yujie and Wu, Tong and Wang, Bin and He, Conghui and Lin, Dahua},
      booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
      month = {October},
      year = {2023}
}