Fashion is the way we present ourselves to the world and has become one of the world's
largest industries. Fashion, mainly conveyed by vision, has thus attracted much attention …

Outfits in online fashion data are composed of items of many different types (eg top, bottom,
shoes) that share some stylistic relationship with one another. A representation for building …

This paper proposes an automatic spatially-aware concept discovery approach using
weakly labeled image-text data from shop** websites. We first fine-tune GoogleNet by …

We argue that there are many notions of'similarity'and that models, like humans, should be
able to adapt to these dynamically. This contrasts with most representation learning …

We propose a novel approach for estimating the difficulty and transferability of supervised
classification tasks. Unlike previous work, our approach is solution agnostic and does not …

The fashion industry is on the verge of an unprecedented change. The implementation of
machine learning, computer vision, and artificial intelligence (AI) in fashion applications is …

Multi-task learning has been widely adopted in many computer vision tasks to improve
overall computation efficiency or boost the performance of individual tasks, under the …

How do we determine whether two or more clothing items are compatible or visually
appealing? Part of the answer lies in understanding of visual aesthetics, and is biased by …