ITEm: Unsupervised Image-Text Embedding Learning for eCommerce

arXiv:2311.02084v2 Announce Type: replace
Abstract: Product embedding serves as a cornerstone for a wide range of applications in eCommerce. The product embedding learned from multiple modalities shows significant improvement over that from a single modality, since different modalities provide complementary information. However, some modalities are more informatively dominant than others. How to teach a model to learn embedding from different modalities without neglecting information from the less dominant modality is challenging. We present an image-text embedding model (ITEm), an unsupervised …

abstract applications arxiv cs.cl cs.cv cs.ir ecommerce embedding image improvement information multiple product shows text text embedding type unsupervised