{
  "id": "1805.09137",
  "version": "v1",
  "published": "2018-05-13T19:13:16.000Z",
  "updated": "2018-05-13T19:13:16.000Z",
  "title": "Image Captioning",
  "authors": [
    "Vikram Mullachery",
    "Vishal Motwani"
  ],
  "comment": "arXiv admin note: text overlap with arXiv:1609.06647 by other authors",
  "categories": [
    "cs.CV",
    "cs.AI"
  ],
  "abstract": "This paper discusses and demonstrates the outcomes from our experimentation on Image Captioning. Image captioning is a much more involved task than image recognition or classification, because of the additional challenge of recognizing the interdependence between the objects/concepts in the image and the creation of a succinct sentential narration. Experiments on several labeled datasets show the accuracy of the model and the fluency of the language it learns solely from image descriptions. As a toy application, we apply image captioning to create video captions, and we advance a few hypotheses on the challenges we encountered.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2018-05-13T19:13:16.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "image captioning",
      "create video captions",
      "succinct sentential narration",
      "toy application",
      "image descriptions"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}