Jun.-Prof. Dr. Vasileios Belagiannis (Βασίλειος Μπελαγιάννης)
Vasileios Belagiannis is Juniorprofessor at University of Ulm (Faculty of Engineering, Computer Science and Psychology). He holds a degree in engineering (Greece, 2009) from Democritus University of Thrace, Engineering School of Xanthi and M.Sc. in Computational Science and Engineering from TU München (Germany, 2011). He completed his doctoral studies at TU München (2015) under the supervision of Prof. Nassir Navab and Dr. Slobodan Ilic. He was CAMP member and still affiliated with the Chair. He has been post-doctoral research assistant at University of Oxford and member of the Visual Geometry Group (Prof. Andrew Zisserman). Prior to joining University of Ulm, he has spent time in industry, working as senior researcher at OSRAM.
Recent Publications (Google Scholar)
Curriculum Vitae (updated Jan. 2020)
Vasilis is interested in developing algorithms to solve problems in the field of deep learning, machine learning and computer vision. His current research includes meta-learning, self-supervised learning, neural architecture search, efficient inference, adversarial and sequential modelling. His focus is on applications related to autonomous systems, self-driving cars and medical imaging, such as multi-modal representation learning, activity recognition and forecasting, object detection, segmentation and pose estimation, signal denoising and 3D localisation.
Information for Prospective Students
- I'm looking for motivated MSc/PhD students. Please contact me for further details.
- Introduction to Deep Learning (SS2019)
- Laboratory Deep Learning for Autonomous Driving (WS2019/20)
- Seminar Trends in Applied AI, ML and DL (WS2019/20)
- Project Deep Learning for Autonomous Cars (WS2019/20)
- Julian Wiederer
- Youssef Dawoud
- Alexander Tsaregorodtsev
Selected Publications and Recent Work
Irtiza Hasan, Francesco Setti, Theodore Tsesmelis, Vasileios Belagiannis, Sikandar Amin, Alessio Del Bue, Marco Cristani, and Fabio Galasso. Forecasting people trajectories and head poses by jointly reasoning on tracklets and vislets. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019.
Vasileios Belagiannis, Azade Farshad, and Fabio Galasso. Adversarial network compression. In Computer Vision - ECCV 2018 Workshops - Munich, Germany, September 8-14, 2018, Proceedings, Part IV, volume 11132 of Lecture Notes in Computer Science, pages 431–449. Springer, 2018.
Iro Laina, Christian Rupprecht, Vasileios Belagiannis, Federico Tombari, and Nassir Navab. "Deeper depth prediction with fully convolutional residual networks." In 2016 Fourth international conference on 3D vision (3DV), pp. 239-248. IEEE, 2016.
Vasileios Belagiannis, Sikandar Amin, Mykhaylo Andriluka, Bernt Schiele, Nassir Navab, and Slobodan Ilic. "3d pictorial structures revisited: Multiple human pose estimation." IEEE transactions on pattern analysis and machine intelligence 38, no. 10 (2016): 1929-1942.
Belagiannis, Vasileios, Xinchao Wang, Horesh Beny Ben Shitrit, Kiyoshi Hashimoto, Ralf Stauder, Yoshimitsu Aoki, Michael Kranzfelder et al. "Parsing human skeletons in an operating room." Machine Vision and Applications 27, no. 7 (2016): 1035-1046.
Vasileios Belagiannis, Sikandar Amin, Mykhaylo Andriluka, Bernt Schiele, Nassir Navab, and Slobodan Ilic. "3D pictorial structures for multiple human pose estimation." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1669-1676. 2014.