Improving Image Captioning with Better Use of Caption
ACL, pp. 7454-7464, 2020.
This paper presents a novel image captioning architecture that constructs caption-guided visual relationship graphs to introduce beneficial inductive bias to better utilize captions
Image captioning is a multimodal problem that has drawn extensive attention in both the natural language processing and computer vision community. In this paper, we present a novel image captioning architecture to better explore semantics available in captions and leverage that to enhance both image representation and caption generation...More
PPT (Upload PPT)