In this paper, we propose a novel cross-modal distillation method, calle...
Visual-Semantic Embedding (VSE) is a prevalent approach in image-text
re...
Pair-wise loss is an approach to metric learning that learns a semantic
...
Triplet loss is an extremely common approach to distance metric learning...
Deep metric learning is often used to learn an embedding function that
c...
Deep metric learning seeks to define an embedding where semantically sim...
Recognizing a hotel from an image of a hotel room is important for human...
Learning embedding functions, which map semantically related inputs to n...