HIGHLIGHTS
SUMMARY
The increasing demand for fashion complementary product recommendation has motivated the development of several techniques that can determine the compatibility between fashion products, through pairwise compatibility, or outfit compatibility. That is, given a subset of product items in an outfit and a set of candidate products from the missing category (i.e., one positive and three negatives), the task is to retrieve the most compatible candidate. This approach follows the paradigm of distance metric learning to learn an embedding space where complementary products are closer, and non-complementary products are distant. The authors propose . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.