Recognizing Image Style

Sergey Karayev, Matthew Trentacoste, Helen Han, Aseem Agarwala, Trevor Darrell, Aaron Hertzmann, and Holger Winnemoeller

In Proceedings British Machine Vision Conference 2014
http://dx.doi.org/10.5244/C.28.122

Abstract

The style of an image plays a significant role in how it is viewed, but has received little attention in computer vision research. We describe an approach to predicting style of images, and perform a thorough evaluation of different image features for these tasks. We find that features learned in a multi-layer network generally perform best -- even when trained with object class (not style) labels. Our large-scale learning methods results in the best published performance on an existing dataset of aesthetic ratings and photographic style annotations. We present two novel datasets: 80K Flickr photographs annotated with curated style labels, and 85K paintings annotated with style and genre labels. Our approach shows excellent classification performance on both datasets. We use the learned classifiers to extend traditional tag-based image search to consider stylistic constraints, and demonstrate cross-dataset understanding of style.

Session

Poster Session

Files

Extended Abstract (PDF, 1 page, 1.6M)

Paper (PDF, 11 pages, 2.8M)

Supplemental Materials (ZIP, 1.6M)

Bibtex File

Citation

Sergey Karayev, Matthew Trentacoste, Helen Han, Aseem Agarwala, Trevor Darrell, Aaron Hertzmann, and Holger Winnemoeller. Recognizing Image Style. Proceedings of the British Machine Vision Conference. BMVA Press, September 2014.

BibTex

@inproceedings{BMVC.28.122
	title = {Recognizing Image Style},
	author = {Karayev, Sergey and Trentacoste, Matthew and Han, Helen and Agarwala, Aseem and Darrell, Trevor and Hertzmann, Aaron and Winnemoeller, Holger},
	year = {2014},
	booktitle = {Proceedings of the British Machine Vision Conference},
	publisher = {BMVA Press},
	editors = {Valstar, Michel and French, Andrew and Pridmore, Tony}
	doi = { http://dx.doi.org/10.5244/C.28.122 }
}