Outfit Generation and Style Extraction via Bidirectional LSTM and Autoencoder

Abstract

When creating an outfit, style is a criterion in selecting each fashion item. This means that style can be regarded as a feature of the overall outfit. However, in various previous studies on outfit generation, there have been few methods focusing on global information obtained from an outfit. To address this deficiency, we have incorporated an unsupervised style extraction module into a model to learn outfits. Using the style information of an outfit as a whole, the proposed model succeeded in generating outfits more flexibly without requiring additional information. Moreover, the style information extracted by the proposed model is easy to interpret. The proposed model was evaluated on two human-generated outfit datasets. In a fashion item prediction task (missing prediction task), the proposed model outperformed a baseline method. In a style extraction task, the proposed model extracted some easily distinguishable styles. In an outfit generation task, the proposed model generated an outfit while controlling its styles. This capability allows us to generate fashionable outfits according to various preferences.

9 pages, 5 figures, KDD Workshop AI for fashion

References in corpus (1)

• An LSTM-Based Dynamic Customer Model for Fashion Recommendation

Cited by in corpus (10)

• Improving Outfit Recommendation with Co-supervision of Fashion Generation
• Exchangeable deep neural networks for set-to-set matching and learning
• Machine learning based co-creative design framework
• Context-Aware Visual Compatibility Prediction
• Learning Color Compatibility in Fashion Outfits
• Theme-Matters: Fashion Compatibility Learning via Theme Attention
• Learning Tuple Compatibility for Conditional OutfitRecommendation
• Inductive learning for product assortment graph completion
• POG: Personalized Outfit Generation for Fashion Recommendation at Alibaba iFashion
• An Application to Generate Style Guided Compatible Outfit