De-identification in multimedia content is the process of concealing the identities of individuals captured in a given set of data (images, video, audio, text), for the purpose of protecting their privacy. The fact that a person can be identified through different characteristics such as the facial appearance, voice, silhouette or gait, indicates that the de-identification process offers interdisciplinary challenges, involving various scientific areas such as image processing, speech analysis, video tracking and biometrics.

The workshop aims to address issues related to de-identification including scientific, technical, legal, ethical and societal aspects of person de-identification and reversible de-identification in multimedia content. The workshop seeks to bring together researchers, professionals, and practitioners to present and discuss recent developments and challenges in De-identification in Multimedia Content. Topics of interest include (but are not limited to):

• De-identification methods for biometric identifiers
- still face image de-identification,
- face de-identification in video,
- speaker de-identification,
- gait and gesture de-identification,
- fingerprint de-identification
- de-identification and reversible de-identification

• De-identification of soft biometric identifiers
- tattoo, birthmark and scar de-identification,
- silhouette de-identification,
- age and gender de-identification,
- eye color, height and weight de-identification

• Non-biometric data de-identification
- de-identification of dressing style,
- de-identification of hairstyle,
- de-identification of speech context and specific social and political context

• Ethical, societal and legal aspects of de-identification and reversible deidentification

• Other techniques for privacy protection in multimedia content