Clarification of results

[alfred100p]

Hi in both the table in the readme and paper you mention a column for image captioning as C could someone verify if it's CIDER or CIDER-D.

[xiaoweihu]

The caption evaluation scores are calculated by the official COCO evaluation code, which is a submodule in this repo. You may check the evaluation code for details of CIDEr.

[alfred100p]

Thank you so based on the last lines of:

• Above mentioned code https://github.com/LuoweiZhou/coco-caption/blob/master/pycocoevalcap/cider/cider.py
• Official CIDEr implementation https://github.com/vrama91/cider/blob/master/pyciderevalcap/cider/cider.py
• Official CIDEr-D implementarion https://github.com/vrama91/cider/blob/master/pyciderevalcap/ciderD/ciderD.py

I assume it was CIDEr. But I assume it would be better if an official author could comment on what was intended in the paper.

[alfred100p]

Based on the table 1 from the paper it mentions AoANet (citation 11) and in its official paper (https://arxiv.org/pdf/2002.12204.pdf) in table 1 the score can be concluded as CIDEr-D. I have made a PR to add the score names to the README file(#137).