Neuroaesthetics in fashion: Modeling the perception of fashionability

Edgar Simo-Serra, Sanja Fidler, Francesc Moreno-Noguer, Raquel Urtasun

研究成果: Conference contribution

148 被引用数 (Scopus)

抄録

In this paper, we analyze the fashion of clothing of a large social website. Our goal is to learn and predict how fashionable a person looks on a photograph and suggest subtle improvements the user could make to improve her/his appeal. We propose a Conditional Random Field model that jointly reasons about several fashionability factors such as the type of outfit and garments the user is wearing, the type of the user, the photograph's setting (e.g., the scenery behind the user), and the fashionability score. Importantly, our model is able to give rich feedback back to the user, conveying which garments or even scenery she/he should change in order to improve fashionability. We demonstrate that our joint approach significantly outperforms a variety of intelligent baselines. We additionally collected a novel heterogeneous dataset with 144,169 user posts containing diverse image, textual and meta information which can be exploited for our task. We also provide a detailed analysis of the data, showing different outfit trends and fashionability scores across the globe and across a span of 6 years.

本文言語English
ホスト出版物のタイトルIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
出版社IEEE Computer Society
ページ869-877
ページ数9
ISBN(電子版)9781467369640
DOI
出版ステータスPublished - 2015 10月 14
外部発表はい
イベントIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 - Boston, United States
継続期間: 2015 6月 72015 6月 12

出版物シリーズ

名前Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
07-12-June-2015
ISSN(印刷版)1063-6919

Other

OtherIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
国/地域United States
CityBoston
Period15/6/715/6/12

ASJC Scopus subject areas

  • ソフトウェア
  • コンピュータ ビジョンおよびパターン認識

フィンガープリント

「Neuroaesthetics in fashion: Modeling the perception of fashionability」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル