You're currently viewing an old version of this dataset. To see the current version, click here.

ImageNet VID dataset

The ImageNet VID dataset is a large scale benchmark for video object detection task consisting of 3,862 videos in the training set and 555 videos in the validation set. 30 object categories are contained in this dataset.

Data and Resources

Cite this as

Lu He, Qianyu Zhou, Xiangtai Li, Li Niu, Guangliang Cheng, Xiao Li, Wenxuan Liu, Yunhai Tong, Lizhuang Ma, Liqing Zhang (2024). Dataset: ImageNet VID dataset. https://doi.org/10.57702/58xou3kx

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.1811.05340
Citation
  • https://doi.org/10.48550/arXiv.1710.03958
  • https://doi.org/10.48550/arXiv.1703.10025
Author Lu He
More Authors
Qianyu Zhou
Xiangtai Li
Li Niu
Guangliang Cheng
Xiao Li
Wenxuan Liu
Yunhai Tong
Lizhuang Ma
Liqing Zhang
Homepage https://ai.stanford.edu/~jkrause/vid/vid.html