Authors:
Julia Lasserre
;
Katharina Rasch
and
Roland Vollgraf
Affiliation:
Zalando Research, Germany
Keyword(s):
Computer Vision, Deep Learning, Fashion, Item Recognition, Street-to-shop.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Computer Vision, Visualization and Computer Graphics
;
Image Understanding
;
Pattern Recognition
;
Similarity and Distance Learning
;
Theory and Methods
Abstract:
Fashion is an increasingly important topic in computer vision, in particular the so-called street-to-shop task
of matching street images with shop images containing similar fashion items. Solving this problem promises
new means of making fashion searchable and helping shoppers find the articles they are looking for. This
paper focuses on finding pieces of clothing worn by a person in full-body or half-body images with neutral
backgrounds. Such images are ubiquitous on the web and in fashion blogs, and are typically studio photos, we
refer to this setting as studio-to-shop. Recent advances in computational fashion include the development of
domain-specific numerical representations. Our model Studio2Shop builds on top of such representations and
uses a deep convolutional network trained to match a query image to the numerical feature vectors of all the
articles annotated in this image. Top-k retrieval evaluation on test query images shows that the correct items
are most often
found within a range that is sufficiently small for building realistic visual search engines for the
studio-to-shop setting.
(More)