Wide Eyes Technologies presented a paper about deep learning for fashion product retrieval at ICIP 2017 in Beijing
Melbourne (IJCAI, the International Joint Conference on Artificial Intelligence), Beijing (ICIP, the 2017 IEEE International Conference on Image Processing) and very soon, Venice (ICCV 2017, the International Conference on Computer Vision) and Barcelona (BCNAnalytics). The research scientists team at Wide Eyes Technologies are authentic globetrotters of AI technology.
Antonio Rubio, Senior Computer Vision Researcher at Wide Eyes Technologies and research scientists at Institut de Robòtica i Informàtica Industrial (CSIC-UPC), presented the latest research work about deep learning for fashion product retrieval at ICIP 2017 in Beijing. The international conference that brings together leading academic scientists, researchers and research scholars to exchange and share their experiences and research results on all aspects of Image Processing.
Finding a product in the fashion world can be a daunting task. Everyday, e-commerce sites are updating with thousands of images and their associated metadata (textual information), deepening the problem, akin to finding a needle in a haystack. In this sense, the paper presented during ICIP 2017 explores to leverage both the images and textual metadata, and proposes a joint multi-modal embedding that maps both the text and images into a common latent space.
The objective of this research is the creation of a space where images and texts can be represented. In this way, it’s possible to search by image from text (and vice versa) because distances can be calculated within that space to find the closest elements. At the same time, images and texts can be classified into different categories of apparel.