Designovel's system description for Fashion-IQ challenge 2019

no code implementations • 21 Oct 2019 • Jianri Li, Jae-whan Lee, Woo-sang Song, Ki-young Shin, Byung-Hyun Go

Then we compose candidate image vector and text representation into a single vector which is exptected to be biased toward target image vector.

Image Retrieval Metric Learning +1