{
  "id": "1806.04391",
  "version": "v1",
  "published": "2018-06-12T08:42:55.000Z",
  "updated": "2018-06-12T08:42:55.000Z",
  "title": "Qiniu Submission to ActivityNet Challenge 2018",
  "authors": [
    "Xiaoteng Zhang",
    "Yixin Bao",
    "Feiyun Zhang",
    "Kai Hu",
    "Yicheng Wang",
    "Liang Zhu",
    "Qinzhu He",
    "Yining Lin",
    "Jie Shao",
    "Yao Peng"
  ],
  "comment": "4 pages, 3 figures, CVPR workshop",
  "categories": [
    "cs.CV"
  ],
  "abstract": "In this paper, we introduce our submissions for the tasks of trimmed activity recognition (Kinetics) and trimmed event recognition (Moments in Time) for Activitynet Challenge 2018. In the two tasks, non-local neural networks and temporal segment networks are implemented as our base models. Multi-modal cues such as RGB image, optical flow and acoustic signal have also been used in our method. We also propose new non-local-based models for further improvement on the recognition accuracy. The final submissions after ensembling the models achieve 83.5% top-1 accuracy and 96.8% top-5 accuracy on the Kinetics validation set, 35.81% top-1 accuracy and 62.59% top-5 accuracy on the MIT validation set.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2018-06-12T08:42:55.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "activitynet challenge",
      "qiniu submission",
      "mit validation set",
      "kinetics validation set",
      "temporal segment networks"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 4,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}