{
  "id": "2011.14944",
  "version": "v1",
  "published": "2020-11-30T16:09:11.000Z",
  "updated": "2020-11-30T16:09:11.000Z",
  "title": "Flood Detection via Twitter Streams using Textual and Visual Features",
  "authors": [
    "Firoj Alam",
    "Zohaib Hassan",
    "Kashif Ahmad",
    "Asma Gul",
    "Michael Reiglar",
    "Nicola Conci",
    "Ala AL-Fuqaha"
  ],
  "comment": "3 pages",
  "categories": [
    "cs.CV"
  ],
  "abstract": "The paper presents our proposed solutions for the MediaEval 2020 Flood-Related Multimedia Task, which aims to analyze and detect flooding events in multimedia content shared over Twitter. In total, we proposed four different solutions including a multi-modal solution combining textual and visual information for the mandatory run, and three single modal image and text-based solutions as optional runs. In the multimodal method, we rely on a supervised multimodal bitransformer model that combines textual and visual features in an early fusion, achieving a micro F1-score of .859 on the development data set. For the text-based flood events detection, we use a transformer network (i.e., pretrained Italian BERT model) achieving an F1-score of .853. For image-based solutions, we employed multiple deep models, pre-trained on both, the ImageNet and places data sets, individually and combined in an early fusion achieving F1-scores of .816 and .805 on the development set, respectively.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-11-30T16:09:11.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "visual features",
      "flood detection",
      "twitter streams",
      "employed multiple deep models",
      "pretrained italian bert model"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 3,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}