Detecting People in Artwork with CNNs
This addresses the limited research in object detection for artwork, which is an incremental improvement for computer vision applications in art analysis.
The paper tackled the problem of detecting people in artwork using CNNs, achieving state-of-the-art performance on the People-Art dataset with less than 60% AP, highlighting the cross-depiction challenge.
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