{
  "id": "1907.10837",
  "version": "v1",
  "published": "2019-07-25T04:48:10.000Z",
  "updated": "2019-07-25T04:48:10.000Z",
  "title": "Submission to ActivityNet Challenge 2019: Task B Spatio-temporal Action Localization",
  "authors": [
    "Chunfei Ma",
    "Joonhyang Choi",
    "Byeongwon Lee",
    "Seungji Yang"
  ],
  "comment": "4 pages, 2 fighures",
  "categories": [
    "cs.CV",
    "cs.LG"
  ],
  "abstract": "This technical report present an overview of our system proposed for the spatio-temporal action localization(SAL) task in ActivityNet Challenge 2019. Unlike previous two-streams-based works, we focus on exploring the end-to-end trainable architecture using only RGB sequential images. To this end, we employ a previously proposed simple yet effective two-branches network called SlowFast Networks which is capable of capturing both short- and long-term spatiotemporal features. Moreover, to handle the severe class imbalance and overfitting problems, we propose a correlation-preserving data augmentation method and a random label subsampling method which have been proven to be able to reduce overfitting and improve the performance.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-07-25T04:48:10.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "spatio-temporal action localization",
      "activitynet challenge",
      "submission",
      "random label subsampling method",
      "correlation-preserving data augmentation method"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 4,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}