A paper of our group has been accepted for publication at the 2nd Causality in Vision Workshop at ECCV 2022! “Investigating Neural Network Training on a Feature Level using Conditional Independence” by Niklas Penzel, Christian Reimers, Paul Bodesheim and Joachim Denzler. This work will be presented during the conference which takes place October 23-27, 2022…
A paper of our group has been accepted for publication at the 26th International Conference on Pattern Recognition (ICPR)! Occlusion-Robustness of Convolutional Neural Networks via Inverted Cutout by Matthias Körschens, Paul Bodesheim, and Joachim Denzler. This work will be presented during the conference which takes place August 21-25, 2022 in Montréal, Québec, Canada.
A paper of our group has been accepted for publication at the Ninth Workshop on Fine-Grained Visual Categorization @ CVPR 2022: Automated Visual Monitoring of Nocturnal Insects with Light-based Camera Traps by Dimitri Korsch, Paul Bodesheim, Gunnar Brehm and Joachim Denzler. This work will be presented during the workshop on June 19th in New Orleans, Louisiana,…
The European Laboratory for Learning and Intelligent Systems (ELLIS) started four new units across Europe including one in Jena. Together with the Max Planck Institute for Biogeochemistry and the Institute for Data Science of the German Aerospace Center the Friedrich Schiller University Jena represented by the Computer Vision Jena joined the network as an organized…
Four papers from our group have been accepted for publication at the DAGM German Conference for Pattern Recognition (DAGM-GCPR) 2021: Dimitri Korsch and Paul Bodesheim and Joachim Denzler:End-to-end Learning of Fisher Vector Encodings for Part Features in Fine-grained Recognition Matthias Körschens and Paul Bodesheim and Christine Römermann and Solveig Franziska Bucher and Mirco Migliavacca and Josephine…
Five papers from our group have been accepted for the Computer Science for Biodiversity (CS4Biodiversity) Workshopat INFORMATIK 2021 (51. Jahrestagung der Gesellschaft für Informatik): Daphne Auer, Paul Bodesheim, Christian Fiderer, Marco Heurich and Joachim Denzler: Minimizing the Annotation Effort for Detecting Wildlife in Camera Trap Images with Active Learning Julia Böhlke, Dimitri Korsch, Paul Bodesheim and Joachim Denzler:Exploiting Web Images for Moth Species Classification…
A paper of our group has been accepted for publication at the Sixth ISIC Skin Image Analysis Workshop @ CVPR 2021: Conditional Dependence Tests Reveal the Usage of ABCD Rule Features and Bias Variables in Automatic Skin Lesion Classification by Christian Reimers, Niklas Penzel, Paul Bodesheim, Jakob Runge, and Joachim Denzler. This work will be presented during the fully-virtual workshop on June 19th.
In the context of a pupils project, Susann Janetzki qualified for the federal round of the “Jugend Forscht” competition. Additionally, she received a special award “Rundfunk-, Fernseh- und Informationstechnik” sponsored by Eduard-Rhein-Stiftung. Supervised by Christian Reimers, she worked on the topic “Die Würfel sind gefallen: Strategieoptimierung des Spieles Qwixx durch maschinelles Lernen”. She utilized an evolutionary…
The European Laboratory for Learning and Intelligent Systems offers an interdisciplinary PhD program. The ELLIS PhD program is a key element of the ELLIS initiative and its goal is to foster and educate the best talent in machine learning related research areas by pairing outstanding students with leading academic and industrial researchers in Europe. The program supports…
