[Platform for Audiovisual General-purpose ANotation]


With the advances of machine learning, the necessity for larger datasets has grown stronger. This issue is even more critical in the field of affective computing, where collecting large amounts of emotional data can be an arduous task as existing annotation frameworks often require installation, programming knowledge, or direct researcher supervision.

PAGAN [Platform for Audiovisual General-purpose ANnotation] was designed to address these issues by providing an easy-to-use framework for multi-purpose audiovisual annotation.

If you use PAGAN in your scientific work, please cite it as:
Melhart D., Liapis A. & Yannakakis G. N. (2019). PAGAN: Video Affect Annotation Made Easy. In Proceedings of the 8th International Conference on Affective Computing and Intelligent Interaction (ACII), Cambridge, United Kingdom.

Left: PAGAN project creation; right: PAGAN annotation with RankTrace using the SEMAINE database1.

PAGAN was developed at the Institute of Digital Games at the University of Malta

The tool is free for scientific use. An open test application can be found on the How To & Test page.

Students and researchers interested in using the framework should send an email to david.melhart [at] um.edu.mt with a pargraph describing their project to gain access to the full project creation and management functionalities.

  1. G. McKeown, M. Valstar, R. Cowie, M. Pantic, and M. Schroder, “The semaine database: Annotated multimodal records of emotionally colored conversations between a person and a limited agent,” IEEE Transactionson Affective Computing, vol. 3, no. 1, pp. 5–17, 2012.