A large scale visual attributes dataset with explicitly labelled positive and negative attributes
Our CVPR 2021 paper discusses the details about the construction of the VAW dataset as well as describes our novel SCoNe algorithm to improve visual attribute prediction in the wild. If you use our VAW dataset or components of our SCoNe algorithm, Please cite us as:
@InProceedings{Pham_2021_CVPR,
author = {Pham, Khoi and Kafle, Kushal and Lin, Zhe and Ding, Zhihong and Cohen, Scott and Tran, Quan and Shrivastava, Abhinav},
title = {Learning To Predict Visual Attributes in the Wild},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2021},
pages = {13018-13028}
}
The VAW dataset can be downloaded from our github repo, which also shows license terms and usage instructions README for using our VAW dataset.
This dataset contains objects labeled with a variety of attributes, including those applied to people. Datasets and their use are the subject of important ongoing discussions in the AI community, especially datasets that include people, and we hope to play an active role in those discussions. If you have any feedback regarding this dataset, we welcome your input at kkafle@adobe.com
Please feel free to contact us for any questions or comments regarding either our paper or the dataset. Our emails are found in the paper PDF.