image-captioning icon indicating copy to clipboard operation
image-captioning copied to clipboard

Published 20 hours ago • verified publisher icon daveredrum

FC and Att2all

Open WangWenshan opened this issue 5 years ago • 1 comments

Hi, Thanks for your great work. I have a question that what is the difference between FC and Att2all?

Thanks.

WangWenshan avatar Apr 21 '19 13:04 WangWenshan

Thanks a lot for your interest in this repo.

Briefly, FC model is an encoder-decoder pipeline without any attention mechanism, while the Att2all is a model equipped with attention module and has the attended image features as input to all LSTM gates. Further details of FC and Att2all can be found in the paper here: "Self-critical Sequence Training for Image Captioning".

Hope that helps :)

daveredrum avatar Jul 23 '19 09:07 daveredrum