Loading...
Loading...

Go to the content (press return)

Multi-modal embedding for main product detection in fashion

Author
Rubio, A.; LongLong, Y.; Simo, E.; Moreno-Noguer, F.
Type of activity
Presentation of work at congresses
Name of edition
2017 ICCV Workshop on Computer Vision for Fashion
Date of publication
2017
Presentation's date
2017
Book of congress proceedings
Proceedings of the 2017 ICCV Workshop on Computer Vision for Fashion
First page
2236
Last page
2242
DOI
https://doi.org/10.1109/ICCVW.2017.261 Open in new window
Rewarded activity
Yes
Repository
http://hdl.handle.net/2117/114315 Open in new window
URL
http://ieeexplore.ieee.org/document/8265471/ Open in new window
Abstract
Best Paper Award a la 2017 IEEE International Conference on Computer Vision Workshops 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...
Citation
Rubio, A., LongLong, Y., Simo, E., Moreno-Noguer, F. Multi-modal embedding for main product detection in fashion. A: ICCV Workshop on Computer Vision for Fashion. "Proceedings of the 2017 ICCV Workshop on Computer Vision for Fashion". Venice: 2017, p. 2236-2242.
Keywords
common embedding, computer vision, deep learning, learning (artificial intelligence), multi-modal embedding
Group of research
ROBiri - IRI Robotics Group

Participants

  • Rubio Romano, Antonio  (author and speaker )
  • LongLong, Yu  (author and speaker )
  • Simo Serra, Edgar  (author and speaker )
  • Moreno Noguer, Francesc d'Assis  (author and speaker )