HIGHLIGHTS
SUMMARY
Thanks to the growth of e-commerce websites and the increasing importance of fashion and style in the daily lives, the computer vision community has focused on fashion-related research over the past few years. A recent attempt to develop a fashion-oriented image captioning architecture was the model proposed by Yang et_al, which employs an LSTM language model trained with two reward functions, one related to the generation of single attributes and one that covers the semantics of the entire sentence. Although this approach can be directly employed for fashion item captioning, it . . .
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.