paper

Generating captions without looking beyond objects

arXiv:1610.03708

Abstract

This paper explores new evaluation perspectives for image captioning and introduces a noun translation task that achieves comparative image caption generation performance by translating from a set of nouns to captions. This implies that in image captioning, all word categories other than nouns can be evoked by a powerful language model without sacrificing performance on n-gram precision. The paper also investigates lower and upper bounds of how much individual word categories in the captions contribute to the final BLEU score. A large possible improvement exists for nouns, verbs, and prepositions.

This paper was presented at the ECCV2016 2nd Workshop on Storytelling with Images and Videos (VisStory)

References in corpus (1)

Generating captions without looking beyond objects · wovepaper