Preserving people’s privacy is a crucial issue faced by many computer vision applications. While exploiting video data from RGB cameras has been proven successful in many human analysis scenarios, it may come at the higher cost of compromising observed individual’s sensitive data. This negatively affects the popularity — and hence the deployment — of visual information systems despite their enormous potential to help people in their everyday life. Privacy-aware systems need to minimize the amount of potentially sensitive information about observed subjects that is being collected and/or handled through their pipelines while still achieving a reliable performance. We aim to compile latest efforts and research advances from the scientific community in all aspects of privacy in computer vision/pattern recognition algorithms at data collection, learning, and inference stages. In addition, we are organizing a competition associated to this workshop on identity-preserving human detection (please refer to (



  • Albert Clapés, Computer Vision Center (Universitat Autònoma de Barcelona),
  • Carla Morral, Universitat de Barcelona,
  • Julio C. S. Jacques Junior, Universitat Oberta de Catalunya & Computer Vision Center (Universitat Autònoma de Barcelona),
  • Sergio Escalera,  Universitat de Barcelona & Computer Vision Center (Universitat Autònoma de Barcelona),