In modern society, clothing plays an increasingly important role in people’s daily life, as a compatible outfit can largely improve one’s appearance. Nevertheless, not all people grow keen sense of aesthetics, and hence often find it difficult to make compatible outfits. Therefore, it is highly desired to develop automatic fashion compatibility modeling methods to evaluate the compatibility of a given outfit, i.e., a set of complementary items. In this presentation, we will introduce the mainstream approaches, including pair-wise, list-wise, and graph-wise approaches, to solve this task. We hope that the participants will know how to model the outfit compatibility via this presentation.

Interactive product retrieval is an emerging research topic with the objective of integrating user inputs from multiple modalities as a query for retrieval. In this presentation, we discuss different solutions for the problem of composing images and language-based or attribute-based modifications for product retrieval in the context of fashion. We present Joint Visual Semantic Matching (JVSM), an unified model that learns image-text compositional embeddings by jointly associating visual and textual modalities in a shared discriminative embedding space via compositional losses. We also propose Visio-linguistic Attention Learning (VAL), a composite transformer that can be seamlessly plugged in a CNN to selectively preserve and transform the visual features conditioned on language semantics at different levels of granularity of information. Finally, we introduce Attribute-Driven Disentangled Encoder (ADDE), a model for disentangled representations based on attribute supervision, and tailor it to attribute manipulation, outfit retrieval and conditional image retrieval.