Zum Inhalt springen

Dr. Paul Bodesheim
Postdoctoral Researcher in the Computer Vision Group, Department of Mathematics and Computer Science at Friedrich Schiller University Jena

Paul received a PhD in computer science (Dr.-Ing.) from the  Friedrich Schiller University Jena in 2017. His dissertation is entitled “Discovering unknown visual objects with novelty detection techniques” and focuses on novelty detection in visual object recognition, that is the identification of object categories that are unknown for a trained classifier applied in open set or open world scenarios.
After his PhD studies, he joined the Max Planck Institute for Biogeochemistry Jena as a postdoc, working for the EU Horizon 2020 project “BACI” (https://baci-h2020.eu). In this project, he applied machine learning algorithms for predicting Earth observation data, in particular for upscaling site-level measurements to produce spatially resolved maps.
In 2018, he returned to the Computer Vision Group of the Friedrich Schiller University Jena as a postdoctoral researcher, where he was also a team leader for “Computer Vision and Machine Learning” between June 2020 and December 2022.
His research interests are visual object recognition, learning from small and imbalanced data, novelty detection and open set recognition, active learning and lifelong learning, as well as fine-grained recognition and its applications in biodiversity research, including the identification of plants, mammals, birds, and insects.
He published papers in various internationally recognized journals and proceedings of conferences and workshops, including top-tier venues like IJCV, CVPR, ECCV, ACCV, and BMVC. Three of these contributions have received an award: a Best Paper Honorable Mention Award at ACCV 2012, a Best Poster Award at the FEAST Workshop on Features and Structures at ICPR 2014, and a Best Paper Award at the Anomaly Detection Workshop of ICML 2016.

Phone: +49 3641 94-6410
Mail: paul.bodesheim@uni-jena.de
List of Publications: Google Scholar

Bitte aktiviere JavaScript in deinem Browser, um dieses Formular fertigzustellen.