Search Results for author: Shunta Nagasawa

Found 1 papers, 0 papers with code

Validity-Based Sampling and Smoothing Methods for Multiple Reference Image Captioning

no code implementations NAACL (maiworkshop) 2021 Shunta Nagasawa, Yotaro Watanabe, Hitoshi Iyatomi

In image captioning, multiple captions are often provided as ground truths, since a valid caption is not always uniquely determined.

Image Captioning

Cannot find the paper you are looking for? You can Submit a new open access paper.