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. The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-46604-0_57
Cite
@article{arxiv.1610.08871,
title = {Detecting People in Artwork with CNNs},
author = {Nicholas Westlake and Hongping Cai and Peter Hall},
journal= {arXiv preprint arXiv:1610.08871},
year = {2016}
}
Comments
14 pages, plus 3 pages of references; 7 figures in ECCV 2016 Workshops