{
  "id": "1806.09278",
  "version": "v1",
  "published": "2018-06-25T04:11:03.000Z",
  "updated": "2018-06-25T04:11:03.000Z",
  "title": "Best Vision Technologies Submission to ActivityNet Challenge 2018-Task: Dense-Captioning Events in Videos",
  "authors": [
    "Yuan Liu",
    "Moyini Yao"
  ],
  "comment": "Rank 2 in ActivityNet Captions Challenge 2018",
  "categories": [
    "cs.CV"
  ],
  "abstract": "This note describes the details of our solution to the dense-captioning events in videos task of ActivityNet Challenge 2018. Specifically, we solve this problem with a two-stage way, i.e., first temporal event proposal and then sentence generation. For temporal event proposal, we directly leverage the three-stage workflow in [13, 16]. For sentence generation, we capitalize on LSTM-based captioning framework with temporal attention mechanism (dubbed as LSTM-T). Moreover, the input visual sequence to the LSTM-based video captioning model is comprised of RGB and optical flow images. At inference, we adopt a late fusion scheme to fuse the two LSTM-based captioning models for sentence generation.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2018-06-25T04:11:03.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "best vision technologies submission",
      "activitynet challenge",
      "dense-captioning events",
      "sentence generation",
      "first temporal event proposal"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}