The authors replace next-word log-likelihood training with word-embedding regression in an encoder-decoder captioning model and report CIDEr 125.0 and BLEU-4 50.5 on MS-COCO, exceeding prior bests of 117.1 and 48.0.
Image captioning with mem- orized knowledge,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Deep Decoder Structure Based on WordEmbedding Regression for An Encoder-Decoder Based Model for Image Captioning
The authors replace next-word log-likelihood training with word-embedding regression in an encoder-decoder captioning model and report CIDEr 125.0 and BLEU-4 50.5 on MS-COCO, exceeding prior bests of 117.1 and 48.0.