Fashion-Specific Attributes Interpretation via Dual Gaussian Visual-Semantic Embedding
This addresses the challenge of understanding vague fashion terms for users and experts, though it is incremental as it builds on existing probabilistic embedding methods.
The paper tackles the problem of interpreting subjective and abstract fashion-specific terms like 'casual' by proposing a dual Gaussian visual-semantic embedding model that maps images and attributes into a shared projective space, demonstrating effectiveness through experiments in image retrieval and re-ordering.
Several techniques to map various types of components, such as words, attributes, and images, into the embedded space have been studied. Most of them estimate the embedded representation of target entity as a point in the projective space. Some models, such as Word2Gauss, assume a probability distribution behind the embedded representation, which enables the spread or variance of the meaning of embedded target components to be captured and considered in more detail. We examine the method of estimating embedded representations as probability distributions for the interpretation of fashion-specific abstract and difficult-to-understand terms. Terms, such as "casual," "adult-casual,'' "beauty-casual," and "formal," are extremely subjective and abstract and are difficult for both experts and non-experts to understand, which discourages users from trying new fashion. We propose an end-to-end model called dual Gaussian visual-semantic embedding, which maps images and attributes in the same projective space and enables the interpretation of the meaning of these terms by its broad applications. We demonstrate the effectiveness of the proposed method through multifaceted experiments involving image and attribute mapping, image retrieval and re-ordering techniques, and a detailed theoretical/analytical discussion of the distance measure included in the loss function.