In Search of Art

Crowley, Elliot J.; Zisserman, Andrew

doi:10.1007/978-3-319-16178-5_4

In Search of Art

Elliot J. Crowley, Andrew Zisserman

ECCVW 2014 pp. 54-70

doi:10.1007/978-3-319-16178-5_4 /eccvw/2014/crowley2014eccvw-search/

Abstract

The objective of this work is to find objects in paintings by learning object-category classifiers from available sources of natural images. Finding such objects is of much benefit to the art history community as well as being a challenging problem in large-scale retrieval and domain adaptation. We make the following contributions: (i) we show that object classifiers, learnt using Convolutional Neural Networks (CNNs) features computed from various natural image sources, can retrieve paintings containing these objects with great success; (ii) we develop a system that can learn object classifiers on-the-fly from Google images and use these to find a large variety of previously unfound objects in a dataset of 210,000 paintings; (iii) we combine object classifiers and detectors to align objects to allow for direct comparison; for example to illustrate how they have varied over time.

PDF ECCVW Semantic Scholar

Cite

Text

Crowley and Zisserman. "In Search of Art." European Conference on Computer Vision Workshops, 2014. doi:10.1007/978-3-319-16178-5_4

Markdown

[Crowley and Zisserman. "In Search of Art." European Conference on Computer Vision Workshops, 2014.](https://mlanthology.org/eccvw/2014/crowley2014eccvw-search/) doi:10.1007/978-3-319-16178-5_4

BibTeX

@inproceedings{crowley2014eccvw-search,
  title     = {{In Search of Art}},
  author    = {Crowley, Elliot J. and Zisserman, Andrew},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2014},
  pages     = {54-70},
  doi       = {10.1007/978-3-319-16178-5_4},
  url       = {https://mlanthology.org/eccvw/2014/crowley2014eccvw-search/}
}