Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Multi-modal embedding for main product detection in fashion

Autor
Rubio, A.; LongLong, Y.; Simo, E.; Moreno-Noguer, F.
Tipus d'activitat
Presentació treball a congrés
Nom de l'edició
2017 ICCV Workshop on Computer Vision for Fashion
Any de l'edició
2017
Data de presentació
2017
Llibre d'actes
Proceedings of the 2017 ICCV Workshop on Computer Vision for Fashion
Pàgina inicial
2236
Pàgina final
2242
DOI
https://doi.org/10.1109/ICCVW.2017.261 Obrir en finestra nova
Activitat premiada
Si
Repositori
http://hdl.handle.net/2117/114315 Obrir en finestra nova
URL
http://ieeexplore.ieee.org/document/8265471/ Obrir en finestra nova
Resum
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...
Citació
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.
Paraules clau
common embedding, computer vision, deep learning, learning (artificial intelligence), multi-modal embedding
Grup de recerca
ROBiri - Grup de Robòtica de l'IRI

Participants