no code implementations • 25 Jul 2019 • Murium Iqbal, Kamelia Aryafar, Timothy Anderton
We propose Style Conditioned Recommendations (SCR) and introduce style injection as a method to diversify recommendations.
no code implementations • 24 Jul 2019 • Murium Iqbal, Nishan Subedi, Kamelia Aryafar
The problem of ranking is a multi-billion dollar problem.
no code implementations • 28 Jun 2018 • Murium Iqbal, Adair Kovac, Kamelia Aryafar
The second system extends the first by incorporating text data and applying polylingual topic modeling to infer style over both modalities.
no code implementations • 23 Apr 2018 • Murium Iqbal, Adair Kovac, Kamelia Aryafar
In this paper, we explore Latent Dirichlet Allocation (LDA) and Polylingual Latent Dirichlet Allocation (PolyLDA), as a means to discover trending styles in Overstock from deep visual semantic features transferred from a pretrained convolutional neural network and text-based item attributes.