The OmniART dataset released

The first release of OmniArt

In the previous post I introduced a paper in which we build a shared representation of artistic data based on multiple attributes related to it. The data used in that paper is now a full featured, museum-centric dataset containing more than 1M photographic reproductions of artworks with rich metadata. The dataset is still growing and can be obtained from this site.

The dataset is growing by the minute, with more and more images being gathered in the background. Indexing the images, purifying the metadata and generating the features takes time so the data gathered at this moment will be available in the next iteration of the dataset.

If you use this dataset in your research, make sure to cite this paper:

@article{  strezoski2017omniart,
           title={OmniArt: Multi-task Deep Learning for Artistic Data Analysis},
           author={Strezoski, Gjorgji and Worring, Marcel},
           journal={arXiv preprint arXiv:1708.00684},
           year={2017}
        }

 
comments powered by Disqus