12
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      SuperCaptioning: Image Captioning Using Two-dimensional Word Embedding

      Preprint

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Language and vision are processed as two different modal in current work for image captioning. However, recent work on Super Characters method shows the effectiveness of two-dimensional word embedding, which converts text classification problem into image classification problem. In this paper, we propose the SuperCaptioning method, which borrows the idea of two-dimensional word embedding from Super Characters method, and processes the information of language and vision together in one single CNN model. The experimental results on Flickr30k data shows the proposed method gives high quality image captions. An interactive demo is ready to show at the workshop.

          Related collections

          Most cited references9

          • Record: found
          • Abstract: not found
          • Conference Proceedings: not found

          Deep visual-semantic alignments for generating image descriptions

            Bookmark
            • Record: found
            • Abstract: not found
            • Conference Proceedings: not found

            Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering

              Bookmark
              • Record: found
              • Abstract: not found
              • Conference Proceedings: not found

              Self-Critical Sequence Training for Image Captioning

                Bookmark

                Author and article information

                Journal
                24 May 2019
                Article
                1905.10515
                f49708c4-4662-4576-9a90-c03650c2eb04

                http://arxiv.org/licenses/nonexclusive-distrib/1.0/

                History
                Custom metadata
                3 pages, 2 figures
                cs.CL

                Theoretical computer science
                Theoretical computer science

                Comments

                Comment on this article