{
  "id": "1512.01289",
  "version": "v1",
  "published": "2015-12-04T00:24:16.000Z",
  "updated": "2015-12-04T00:24:16.000Z",
  "title": "Predicting psychological attributions from face photographs with a deep neural network",
  "authors": [
    "Edward Grant",
    "Stephan Sahm",
    "Mariam Zabihi",
    "Marcel van Gerven"
  ],
  "categories": [
    "cs.CV",
    "cs.LG",
    "cs.NE"
  ],
  "abstract": "Judgements about personality based on facial appearance are strong effectors in social decision making and are known to impact on areas from presidential elections to jury decisions. Recent work has shown that it is possible to predict perception of memorability, trustworthiness, intelligence and other attributes in human face images. The most successful of these approaches requires face images expertly annotated with key facial landmarks. We demonstrate a Convolutional Neural Network (CNN) model that is able perform the same task without the need for landmark features thereby greatly increasing efficiency. The model has high accuracy, surpassing human level performance in some cases. Furthermore, we use a deconvolutional approach to visualize important features for perception of 22 attributes and show that these can be described as a composites of their positive and negative components by separately visualizing both.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2015-12-04T00:24:16.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "deep neural network",
      "predicting psychological attributions",
      "face photographs",
      "surpassing human level performance",
      "convolutional neural network"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable",
      "adsabs": "2015arXiv151201289G"
    }
  }
}