TY - GEN

T1 - BAM! the Behance Artistic Media Dataset for Recognition beyond Photography

AU - Wilber, Michael J.

AU - Fang, Chen

AU - Jin, Hailin

AU - Hertzmann, Aaron

AU - Collomosse, John

AU - Belongie, Serge

N1 - Funding Information: This work is partly funded by an NSF Graduate Research Fellowship award (NSF DGE-1144153, Author 1), a Google Focused Research award (Author 6), a Facebook equipment donation to Cornell University, and Adobe Research. Publisher Copyright: © 2017 IEEE.

PY - 2017/12/22

Y1 - 2017/12/22

N2 - Computer vision systems are designed to work well within the context of everyday photography. However, artists often render the world around them in ways that do not resemble photographs. Artwork produced by people is not constrained to mimic the physical world, making it more challenging for machines to recognize.,,This work is a step toward teaching machines how to categorize images in ways that are valuable to humans. First, we collect a large-scale dataset of contemporary artwork from Behance, a website containing millions of portfolios from professional and commercial artists. We annotate Behance imagery with rich attribute labels for content, emotions, and artistic media. Furthermore, we carry out baseline experiments to show the value of this dataset for artistic style prediction, for improving the generality of existing object classifiers, and for the study of visual domain adaptation. We believe our Behance Artistic Media dataset will be a good starting point for researchers wishing to study artistic imagery and relevant problems. This dataset can be found at https://bam-dataset.org/

AB - Computer vision systems are designed to work well within the context of everyday photography. However, artists often render the world around them in ways that do not resemble photographs. Artwork produced by people is not constrained to mimic the physical world, making it more challenging for machines to recognize.,,This work is a step toward teaching machines how to categorize images in ways that are valuable to humans. First, we collect a large-scale dataset of contemporary artwork from Behance, a website containing millions of portfolios from professional and commercial artists. We annotate Behance imagery with rich attribute labels for content, emotions, and artistic media. Furthermore, we carry out baseline experiments to show the value of this dataset for artistic style prediction, for improving the generality of existing object classifiers, and for the study of visual domain adaptation. We believe our Behance Artistic Media dataset will be a good starting point for researchers wishing to study artistic imagery and relevant problems. This dataset can be found at https://bam-dataset.org/

UR - http://www.scopus.com/inward/record.url?scp=85041906992&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2017.136

DO - 10.1109/ICCV.2017.136

M3 - Conference article

AN - SCOPUS:85041906992

SP - 1211

EP - 1220

JO - Proceedings of the IEEE International Conference on Computer Vision

JF - Proceedings of the IEEE International Conference on Computer Vision

SN - 1550-5499

T2 - 16th IEEE International Conference on Computer Vision, ICCV 2017

Y2 - 22 October 2017 through 29 October 2017

ER -