Learning to Match Clothing From Textual Feature-Based Compatible Relationships

This paper presents a new framework for matching clothes by considering item in-between compatibility. In contrast to the use of visual features of clothing items, we only utilized their textual descriptions, i.e., title sentences, to constitute the basic features. Specifically, a longshort-term memory (LSTM) network was used for feature embeddings of title sentences. Given item pairs of queries and candidates, their feature embeddings achieved by Siamese LSTMs were integrated into style-compatible space characterized by a compatibility matrix. Our framework is examined on three large-scaled clothing item sets collected from Amazon, Taobao, and Polyvore, respectively. Experiments confirm the efficacy of our approach compared with several baseline methods.