{
  "id": "1711.04323",
  "version": "v1",
  "published": "2017-11-12T17:30:05.000Z",
  "updated": "2017-11-12T17:30:05.000Z",
  "title": "High-Order Attention Models for Visual Question Answering",
  "authors": [
    "Idan Schwartz",
    "Alexander G. Schwing",
    "Tamir Hazan"
  ],
  "comment": "9 pages, 8 figures, NIPS 2017",
  "categories": [
    "cs.CV",
    "cs.AI",
    "cs.LG"
  ],
  "abstract": "The quest for algorithms that enable cognitive abilities is an important part of machine learning. A common trait in many recently investigated cognitive-like tasks is that they take into account different data modalities, such as visual and textual input. In this paper we propose a novel and generally applicable form of attention mechanism that learns high-order correlations between various data modalities. We show that high-order correlations effectively direct the appropriate attention to the relevant elements in the different data modalities that are required to solve the joint task. We demonstrate the effectiveness of our high-order attention mechanism on the task of visual question answering (VQA), where we achieve state-of-the-art performance on the standard VQA dataset.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2017-11-12T17:30:05.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "visual question answering",
      "high-order attention models",
      "data modalities",
      "learns high-order correlations",
      "high-order correlations effectively direct"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 9,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}