Multi-modal Embedding for Main Product Detection in Fashion

descriptionPublicationkeyboard_double_arrow_right Article , Conference object 01 Oct 2017 Spain Publisher:IEEEJournal:2017 IEEE International Conference on Computer Vision Workshops (ICCVW)

Authors: Rubio Romano, Antonio; LongLong, Yu; Simó Serra, Edgar; Moreno-Noguer, Francesc;

doi: 10.1109/iccvw.2017.261

handle: 10261/168354 , 2117/114315

Multi-modal Embedding for Main Product Detection in Fashion

- Summary
- Subjects
- Metrics

Abstract

We present an approach to detect the main product in fashion images by exploiting the textual metadata associated with each image. Our approach is based on a Convolutional Neural Network and learns a joint embedding of object proposals and textual metadata to predict the main product in the image. We additionally use several complementary classification and overlap losses in order to improve training stability and performance. Our tests on a large-scale dataset taken from eight e-commerce sites show that our approach outperforms strong baselines and is able to accurately detect the main product in a wide diversity of challenging fashion images.

This work is partly funded by the Spanish MINECO project RobInstruct TIN2014-58178-R. A. Rubio is supported by the industrial doctorate grant 2015-DI-010 of the AGAUR.

Trabajo presentado a la International Conference on Computer Vision Workshops (ICCVW), celebrada en Venice (Italy) del 22 al 29 de octubre de 2017.

Peer Reviewed

Country

Spain

Related Organizations

View all View all

Keywords

:Informàtica::Automàtica i control [Àrees temàtiques de la UPC], Classificació INSPEC::Automation, multi-modal embedding, Àrees temàtiques de la UPC::Informàtica::Automàtica i control, deep learning, learning (artificial intelligence), :Automation [Classificació INSPEC], common embedding, computer vision

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	3
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Average
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Average