Donnaphat Trakulwaranont, Marc A. Kastner, Shin'ichi Satoh
The e-commerce fashion industry is booming and comes with needs for proper search and recommendation. However, sufficient user personalization is still a challenging task. In this paper, we introduce a personalized fashion recommendation system based on high-dimensional input of user- and environment information. The proposed method is used to recommend suitable categories and style of clothing depending on customized settings such as body type, age, occasion or season. Finally, it generates a full fitting outfit from the recommended suggestions. Personal information has a high dimensionality and datasets are often very unbalanced or biased, making it difficulty to do a proper recommendation. To solve this, we propose a pairwise-attention module to improve the performance. The proposed model can improve the performance up to 53.29\% over the comparison method on MSE, mAP and Recall. Moreover, in a subjective evaluation with human participants, the recommendations of the proposed method is preferred over the comparison method.
Type: MultiMedia Modelling (MMM) 2022
Date: April 2022