Milena Bagdasarian

Milena Bagdasarian is a research associate at the Computer Vision & Graphics Group at Fraunhofer Heinrich Hertz Institute. She graduated in Computer Science at the Technische Universität Berlin with a Master of Science in 2019. From 2017 to 2020 she worked as a research assistant at the Machine Learning Group at Fraunhofer Heinrich Hertz Insitute.

She is now part of the MoDL project, where she works on the integration of a priori knowledge into deep neural networks in the context of computer vision. Her research interests include machine learning techniques, computer vision and human visual perception.


since 06/2020 Research Associate, Computer Vision & Graphics Group, Fraunhofer HHI
04/2017 - 05/2020 Student Research Assistant, Machine Learning Group, Fraunhofer HHI
10/2016 - 11/2019 M. Sc. in Computer Science at Technische Universität Berlin, Germany
08/2018 - 12/2018 Semester abroad at Norwegian University of Science and Technology, Trondheim, Norway
11/2016 B. Sc. in Computer Engineering at Technische Universität Berlin, Germany



    • Bagdasarian, M. T., Hilsmann, A., Eisert, P., Curio, G., Müller, K.-R., Wiegand, T., & Bosse, S.
      EEG-Based Assessment of Perceived Realness in Stylized Face Images. In 2020 Twelfth International Conference on Quality of Multimedia Experience (QoMEX) (pp. 1-4). IEEE.


    • Bosse, S., Bagdasarian, M. T., Samek, W., Curio, G., & Wiegand, T.
      On the stimulation frequency in ssvep-based image quality assessment. In 2018 Tenth international conference on quality of multimedia experience (QoMEX) (pp. 1-6). IEEE.


      • Miklody, D., Bagdasarian, M. T., Blankertz, B.
        A low-dimensional representation for individual head geometries. In 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 3696-3699). IEEE.

      Projects/Research Topics

      Model-based deep learning for computer vision problems (MoDL)

      Read more



      HHI-Nachwuchspreis 2021

      The Young Talent Award for an outstanding master thesis is awarded by the "Gesellschaft von Freunden des Heinrich-Hertz-Instituts e.V.".