Can I read Transformer-based Graph Neural Networks for Outfit Generation on EtoBox?

Transformer-based Graph Neural Networks for Outfit Generation by Becattini, Federico; Teotini, Federico Maria; Del Bimbo, Alberto is a scholarly article available to read on EtoBox.

What is Transformer-based Graph Neural Networks for Outfit Generation about?

Suggesting complementary clothing items to compose an outfit is a process of emerging interest, yet it involves a fine understanding of fashion trends and visual aesthetics. Previous works have mainly focused on recommendation by scoring visual appeal and representing garments as ordered sequences or as collections of pairwise-compatible items. This limits the full usage of relations among clothes. We attempt to bridge the gap between outfit recommendation and generation by leveraging a graph-based representation of items in a collection. The work carried out in this paper, tries to build a bridge between outfit recommendation and generation, by discovering new appealing outfits starting from a collection of pre-existing ones. We propose a transformer-based architecture, named TGNN, which exploits multi-headed self attention to capture relations between clothing items in a graph as a message passing step in Convolutional Graph Neural Networks. Specifically, starting from a seed, i.e.~one or more garments, outfit generation is performed by iteratively choosing the garment that is most compatible with the previously chosen ones. Extensive experimentations are conducted with two diffe

Author

Becattini, Federico; Teotini, Federico Maria; Del Bimbo, Alberto

Published

2023

Language

EN