{
  "id": "1905.08110",
  "version": "v1",
  "published": "2019-05-20T13:43:52.000Z",
  "updated": "2019-05-20T13:43:52.000Z",
  "title": "Image Captioning based on Deep Learning Methods: A Survey",
  "authors": [
    "Yiyu Wang",
    "Jungang Xu",
    "Yingfei Sun",
    "Ben He"
  ],
  "categories": [
    "cs.CV",
    "cs.CL",
    "cs.LG"
  ],
  "abstract": "Image captioning is a challenging task and attracting more and more attention in the field of Artificial Intelligence, and which can be applied to efficient image retrieval, intelligent blind guidance and human-computer interaction, etc. In this paper, we present a survey on advances in image captioning based on Deep Learning methods, including Encoder-Decoder structure, improved methods in Encoder, improved methods in Decoder, and other improvements. Furthermore, we discussed future research directions.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-05-20T13:43:52.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "deep learning methods",
      "image captioning",
      "efficient image retrieval",
      "intelligent blind guidance",
      "research directions"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}