January 2018
Intermediate to advanced
310 pages
7h 48m
English
Ordonez et al., in the paper http://papers.nips.cc/paper/4470-im2text-describing-images-using-1-million-captioned-photographs.pdf, proposed a method to rank the images followed by generating captions. The flow of this process is shown here:

The high-level information extracted from the ranked images can be used to generate the text. The following image shows that the more images that are available for ranking, the better the results will be:

Read now
Unlock full access