Detecting People in Artwork with CNNs
Abstract
CNNs have massively improved performance in object detection in photographs. However research into object detection in artwork remains limited. We show state-of-the-art performance on a challenging dataset, People-Art, which contains people from photos, cartoons and 41 different artwork movements. We achieve this high performance by fine-tuning a CNN for this task, thus also demonstrating that training CNNs on photos results in overfitting for photos: only the first three or four layers transfer from photos to artwork. Although the CNN’s performance is the highest yet, it remains less than 60 % AP, suggesting further work is needed for the cross-depiction problem.
Cite
Text
Westlake et al. "Detecting People in Artwork with CNNs." European Conference on Computer Vision, 2016. doi:10.1007/978-3-319-46604-0_57Markdown
[Westlake et al. "Detecting People in Artwork with CNNs." European Conference on Computer Vision, 2016.](https://mlanthology.org/eccv/2016/westlake2016eccv-detecting/) doi:10.1007/978-3-319-46604-0_57BibTeX
@inproceedings{westlake2016eccv-detecting,
title = {{Detecting People in Artwork with CNNs}},
author = {Westlake, Nicholas and Cai, Hongping and Hall, Peter},
booktitle = {European Conference on Computer Vision},
year = {2016},
pages = {825-841},
doi = {10.1007/978-3-319-46604-0_57},
url = {https://mlanthology.org/eccv/2016/westlake2016eccv-detecting/}
}