xmodaler icon indicating copy to clipboard operation
xmodaler copied to clipboard

Published 20 hours ago • verified publisher icon YehLi

Image to text search using clip

Open ltp1995 opened this issue 2 years ago • 2 comments

Hi, dear author, in your latest CVPR2022 paper (Comprehending and Ordering Semantics for Image Captioning), how to retrieve semantically similar sentences for the input image using clip model, can you give some tutorials? Thanks a lot!

ltp1995 avatar Jul 03 '22 03:07 ltp1995

You can refer to the openai github (https://github.com/openai/CLIP) for more details.

YehLi avatar Jul 04 '22 07:07 YehLi

I see the vocabulary of the semantics label is in size of 907. Why is 907, and how can we get the word's meaning.

catfish132 avatar Aug 18 '22 08:08 catfish132

The semantics label file is uploaded to configs/image_caption/cosnet/semantics labels.txt

YehLi avatar Sep 26 '22 06:09 YehLi