Peter Roth, PhD
Professor of Computer Science
COSC 1550 Computer Programming
COSC 2010 Computer Topics
COSC 3910 Project
MATH 2200 Statistic
MBA 5020 Quantitative Methods for the MBA
STAT 1100 Descriptive Statistics
Peter M. Roth, PhD is a full Professor of Computer Science at Webster Vienna Private University. Roth earned his doctorate from Graz University of Technology in January 2008, following doctoral studies in Computer Science, and completed his habilitation in Applied Computer Science at the same institution in December 2022. He holds a master's degree in Mathematics from Graz University of Technology.
His research focuses on machine learning, pattern recognition, statistical methods, image processing and computer vision, with particular emphasis on applying computational approaches to veterinary medicine and the life sciences. He has accumulated approximately 9,800 scientific citations, with an h-index of 36.
Roth is a senior member of the IEEE and serves as chairman of the Austrian Association of Pattern Recognition, a position he has held since 2013.
Before joining Webster Vienna Private University in 2025, he served as full professor at the University of Veterinary Medicine, Vienna, as full guest professor at the Technical University of Munich's International AI Future Lab, as university assistant at Graz University of Technology, and a scientist at the Austrian Institute of Technology. He holds external lecturing positions at FH Wiener Neustadt and FH Joanneum since 2017 and 2015, respectively.
Among his honors, Roth received the Best Conference Paper Award at the International Symposium on Mixed and Augmented Reality in 2021, the Best Presentation Award at the Computer Vision Winterworkshop in 2019 and the Best Paper Award at the Asian Conference on Computer Vision in 2012. He has co-authored more than 150 peer-reviewed publications and holds multiple U.S. patents in the areas of pose estimation and semantic segmentation.
Peter M. Roth, Martin Hirzer, Martin Köstinger, Csaba Beleznai, and Horst Bischof. Person Re-Identification, chapter Mahalanobis Distance Learning for Person Re-Identification, pages 249–270. Springer, 2014.
Martin Godec, Peter M. Roth, and Horst Bischof. Hough-based tracking of non-rigid objects. Computer Vision and Image Understanding, 117(10):1245–1256, 2013.
Peter M. Roth, Sabine Sternig, and Horst Bischof. Advanced Topics in Computer Vision and Pattern Recognition, chapter Learning Object Detectors in Stationary Environments, pages 377–409. Springer, 2013.
Martin Hirzer, Peter M. Roth, Martin Köstinger, and Horst Bischof. Relaxed pairwise learned metric for person re-identification. In Proc. European Conf. on Computer Vision, 2012.
Martin Köstinger, Martin Hirzer, Paul Wohlhart, Peter M. Roth, and Horst Bischof. Large scale metric learning from equivalence constraints. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 2012.
Martin Köstinger, Peter M. Roth, and Horst Bischof. Synergy-based learning of facial identity. In Proc. DAGM-OAGM Symposium, 2012. (Main Prize).
Martin Köstinger, Paul Wohlhart, Peter M. Roth, and Horst Bischof. Annotated facial landmarks in the wild: A large-scale, real-world database for facial landmark localization. In First IEEE International Workshop on Benchmarking Facial Image Analysis Technologies, 2011.
Paul Wohlhart, Michael Donoser, Peter M. Roth, and Horst Bischof. Detecting partially occluded objects with an implicit shape model random field. In Proc. Asian Conf. on Computer Vision, 2012. (Best Paper Award).
Sabine Sternig, Peter M. Roth, and Horst Bischof. Inverse multiple instance learning for classifier grids. In Proc. Int'l Conf. on Pattern Recognition, 2010. (Best Scientific Paper Award).
Peter M. Roth and Martin Winter. Survey of appearance-based methods for object recognition. Technical Report ICG-TR-08/01, Graz University of Technology, Institute for Computer Graphics and Vision, 2008.
Email: peter.roth@webster.ac.at
Anna Beer, PhD
Assistant Professor, Computer Science
Computer Science Project
Mathematics for Computer Science
Anna Beer, PhD has been an Assistant Professor of Computer Science at WVPU since March 2026. She was previously a postdoctoral researcher at the University of Vienna and at Aarhus University, Denmark. She received her doctorate in Computer Science from LMU Munich in 2021.
Her research focuses on fundamental problems in data mining and unsupervised machine learning, with an emphasis on clustering and evaluation methods. While developing theoretically grounded and elegant solutions to complex problems is a core aspect of her work, she is also interested in interdisciplinary projects. At Aarhus University, she worked on methods for analyzing molecular dynamics data, and her current research addresses challenges arising in astrophysical data.
Her research interests include clustering with a focus on density-based methods (and spectral and hierarchical clustering); evaluation of data mining, machine learning and artificial intelligence; unsupervised machine learning; fairness in machine learning.
Beer, A., Krieger, L., Weber, P., Ritzert, M., Assent, I., & Plant, C. (2026). Internal Evaluation of Density-Based Clusterings with Noise. In: International Conference on Learning Representations (in press) (2026). Preprint available at https://doi.org/10.48550/arXiv.2503.00127.
Krieger, L., Beer, A., Matthews, P., Thiesson, A. M., & Assent, I. (2025). FairDen: Fair Density-based Clustering. In The Thirteenth International Conference on Learning Representations. Vol. 2025. 2025, pp. 101017–101036. url: https://proceedings.iclr.cc/paper_files/paper/2025/file/fab555c41271e821dee964687253106c-Paper-Conference.pdf
Draganov, A. A., Weber, P., Jørgensen, R. S. M., Beer, A., Plant, C., & Assent, I. (2025). Ultrametric Cluster Hierarchies: I Want ‘em All!. In Advances in Neural Information Processing Systems 2025. url: https://openreview.net/pdf?id=E0033NpFm0.
Beer, A., Weber, P., Miklautz, L., Leiber, C., Durani, W., Böhm, C., & Plant, C. (2024, December). Shade: Deep density-based clustering. In 2024 IEEE International Conference on Data Mining (ICDM) (pp. 675-680). IEEE. doi: https://doi.org/10.1109/ICDM59182.2024.00075.
Beer, A., Draganov, A., Hohma, E., Jahn, P., Frey, C. M., & Assent, I. (2023, August). Connecting the Dots--Density-Connectivity Distance unifies DBSCAN, k-Center and Spectral Clustering. In Proceedings of the 29th ACM SIGKDD conference on knowledge discovery and data mining (pp. 80-92). doi: https://doi.org/10.1145/3580305.3599283.
Ullmann, T., Beer, A., Hünemörder, M., Seidl, T., & Boulesteix, A. L. (2023). Over-optimistic evaluation and reporting of novel cluster algorithms: an illustrative study. Advances in Data Analysis and Classification, 17(1), 211-238. doi: https://doi.org/10.1007/s11634-022-00496-5.