Volume 8 Number 1 (Feb. 2016)
Home > Archive > 2016 > Volume 8 Number 1 (Feb. 2016) >
IJCEE 2016 Vol.8(1): 31-43 ISSN: 1793-8163
DOI: 10.17706/IJCEE.2016.8.1.31-43

Fashion Meets Computer Vision and NLP at e-Commerce Search

Susana Zoghbi, Geert Heyman, Juan Carlos Gomez, Marie-Francine Moens
Abstract—In this paper, we focus on cross-modal (visual and textual) e-commerce search within the fashion domain. Particularly, we investigate two tasks: 1) given a query image, we retrieve textual descriptions that correspond to the visual attributes in the query; and 2) given a textual query that may express an interest in specific visual product characteristics, we retrieve relevant images that exhibit the required visual attributes. To this end, we introduce a new dataset that consists of 53,689 images coupled with textual descriptions. The images contain fashion garments that display a great variety of visual attributes, such as different shapes, colors and textures in natural language. Unlike previous datasets, the text provides a rough and noisy description of the item in the image. We extensively analyze this dataset in the context of cross-modal e-commerce search. We investigate two state-of-the-art latent variable models to bridge between textual and visual data: bilingual latent Dirichlet allocation and canonical correlation analysis. We use state-of-the-art visual and textual features and report promising results.

Index Terms—Content-based multimedia retrieval, internet search technologies, information retrieval.

The authors are with the Department of Computer Science, KU Leuven, Belgium.

Cite:Susana Zoghbi, Geert Heyman, Juan Carlos Gomez, Marie-Francine Moens, "Fashion Meets Computer Vision and NLP at e-Commerce Search," International Journal of Computer and Electrical Engineering vol. 8, no. 1, pp. 31-43, 2016.

General Information

ISSN: 1793-8163
Frequency: Bimonthly
Editor-in-Chief: Prof. Yucong Duan
Abstracting/ Indexing: EI (INSPEC, IET), Ulrich's Periodicals Directory, Google Scholar, EBSCO, Engineering & Technology Digital Library, ProQuest, and Electronic Journals Library
E-mail: ijcee@iap.org

What's New

  • Mar 24, 2016 News!

    IJCEE Vol. 7, No. 3 has been indexed by EI (Inspec) Inspec, created by the Institution of Engineering and Tech.!   [Click]

  • Aug 31, 2016 News!

    IJCEE Vol. 8, No. 4 is available online now.   [Click]

  • Jul 19, 2016 News!

    The dois of published papers in Vol. 8, No. 3 have been validated by Crossref.

  • Jul 06, 2016 News!

    IJCEE Vol. 8, No. 3 is available online now.   [Click]

  • May 09, 2016 News!

    The dois of published papers in Vol. 8, No. 2 have been validated by Crossref.

  • Read more>>