Search Results for author:
Found 1 papers, 1 papers with code
Towards Unique and Informative Captioning of Images
We find that modern captioning systems return higher likelihoods for incorrect distractor sentences compared to ground truth captions, and that evaluation metrics like SPICE can be 'topped' using simple captioning systems relying on object detectors.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
