{
  "id": "2206.10861",
  "version": "v1",
  "published": "2022-06-22T06:11:07.000Z",
  "updated": "2022-06-22T06:11:07.000Z",
  "title": "UniCon+: ICTCAS-UCAS Submission to the AVA-ActiveSpeaker Task at ActivityNet Challenge 2022",
  "authors": [
    "Yuanhang Zhang",
    "Susan Liang",
    "Shuang Yang",
    "Shiguang Shan"
  ],
  "comment": "5 pages, 3 figures; technical report for AVA Challenge (see https://research.google.com/ava/challenge.html) at the International Challenge on Activity Recognition (ActivityNet), CVPR 2022",
  "categories": [
    "cs.CV",
    "cs.SD",
    "eess.AS"
  ],
  "abstract": "This report presents a brief description of our winning solution to the AVA Active Speaker Detection (ASD) task at ActivityNet Challenge 2022. Our underlying model UniCon+ continues to build on our previous work, the Unified Context Network (UniCon) and Extended UniCon which are designed for robust scene-level ASD. We augment the architecture with a simple GRU-based module that allows information of recurring identities to flow across scenes through read and update operations. We report a best result of 94.47% mAP on the AVA-ActiveSpeaker test set, which continues to rank first on this year's challenge leaderboard and significantly pushes the state-of-the-art.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-06-22T06:11:07.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "activitynet challenge",
      "ictcas-ucas submission",
      "ava-activespeaker task",
      "ava-activespeaker test set",
      "ava active speaker detection"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 5,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}