Publications

Presentations

[1] Axel Jantsch. Efficient inference at the edge. TECoSA Seminar at the Center for Trustworthy Edge Computing Systems and Applications, November 2022. [ .pdf ]
[2] Axel Jantsch and Zhonghai Lu. Embedded machine learning. Summer School on Cyber-Physical Systems and Internet-of-Things, June 2022. [ .pdf ]
[3] Axel Jantsch. Embedded machine learning. Invited Presentation at AVL Tech Trends, March 2022. [ .pdf ]
[4] Axel Jantsch. Embedded machine learning. Invited Presentation at the AVL Open Networking Day, Oktober 2021. [ .pdf ]
[5] Axel Jantsch. Embedded machine learning. Invited Presentation at the Summer School on AI Enabled Mobility, September 2020. [ .pdf ]
[6] Horst Bischof. Computer vision for detection and tracking. Invited Presentation at the Summer School on AI Enabled Mobility, September 2020.

Journals

[1] Muhammad Jehanzeb Mirza, Cornelius Bürkle, Julio Jarquin, Michael Opitz, Fabian Oboril, Kay-Ulrich Scholl, and Horst Bischof. Robustness of object detectors in degrading weather conditions. CoRR, abs/2106.08795, 2021. [ arXiv | http ]
[2] Martin Lechner and Axel Jantsch. Blackthorn: Latency estimation framework for CNNs on embedded Nvidia platforms. IEEE Access, 2021. [ DOI | .pdf ]
[3] Amid Mozelli, Nima Taherinejad, and Axel Jantsch. A study on confidence: an unsupervised multi-agent machine learning experiment. IEEE Design & Test of Computers, 2021. [ DOI ]
[4] M. Wess, M. Ivanov, C. Unger, A. Nookala, A. Wendt, and A. Jantsch. Annette: Accurate neural network execution time estimation with stacked models. IEEE Access, 9:3545--3556, 2021. [ DOI | .pdf ]
[5] Kerstin Bellman, Nikil Dutt, Lukas Esterle, Andreas Herkersdorf, Axel Jantsch, C. Landauer, P. R. Lewis, M. Platzner, N. TaheriNejad, and K. Tammemäe. Self-aware cyber-physical systems. ACM Transactions on Cyber-Physical Systems, 4(4):1--24, June 2020. [ DOI | http ]
[6] Henrik Hoffmann, Axel Jantsch, and Nikil D. Dutt. Embodied self-aware computing systems. Proceedings of the IEEE, pages 1--20, 2020. [ DOI | .pdf ]
[7] N. TaheriNejad, A. Herkersdorf, and A. Jantsch. Autonomous systems, trust and guarantees. IEEE Design Test, pages 1--1, 2020. [ DOI | .pdf ]

Conferences

[1] Dušan Malić, Christian Fruhwirth-Reisinger, Horst Possegger, and Horst Bischof. Sailor: Scaling anchors via insights into latent object representation. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pages 623--632, January 2023. [ .html ]
[2] Martin Lechner, Axel Jantsch, and Lukas Steindl. Study of DNN-based ragweed detection from drones. In Proceedings of International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation (SAMOS), Samos, Greece, July 2022. [ .pdf ]
[3] M. Jehanzeb Mirza, Marc Masana, Horst Possegger, and Horst Bischof. An efficient domain-incremental learning approach to drive in all weather conditions. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pages 3001--3011, June 2022. [ .html ]
[4] Muhammad Jehanzeb Mirza, Jakub Micorek, Horst Possegger, and Horst Bischof. The norm must go on: Dynamic unsupervised domain adaptation by normalization. In Proceedings of the Conference on Computer Vision and Pattern Recognition, 2022.
[5] David Schinagl, Georg Krispel, Horst Possegger, Peter M. Roth, and Horst Bischof. Occam's laser: Occlusion-based attribution maps for 3d object detectors on lidar data. In Proceedings of the Conference on Computer Vision and Pattern Recognition, 2022.
[6] Bernhard Haas, Alexander Wendt, Axel Jantsch, and Matthias Wess. Neural Network Compression Through Shunt Connections and Knowledge Distillation for Semantic Segmentation Problems. In Artificial Intelligence Applications and Innovations, 17th IFIP WG 12.5 International Conference, volume 1, pages 349--361, Greece (online), 2021. Springer. [ DOI ]
[7] Andreas Glinserer, Martin Lechner, and Alexander Wendt. Automated pruning of neural networks for mobile applications. In Proceedings of IEEE International Conference on Industrial Informatics (INDIN), 2021. [ .pdf ]
[8] Christian Fruhwirth-Reisinger, Michael Opitz, Horst Possegger, and Horst Bischof. Fast3d: Flow-aware self-training for 3d object detectors. In Proceedings of the British Machine Vision Conference, 2021.
[9] Muhammad Jehanzeb Mirza, Cornelius Buerkle, Julio Jarquin, Michael Opitz, Fabian Oboril, Kay-Ulrich Scholl, and Horst Bischof. Robustness of object detectors in degrading weather conditions. In International Conference on Intelligent Transportation Systems, 2021.
[10] Alexander Wendt, Stefan Kollmann, Aleksey Bratukhin, Alireza Estaji, Thilo Sauter, and Axel Jantsch. Cognitive Architectures for Process Monitoring - an Analysis. In Proceedings of the 18th IEEE International Conference on Industrial Informatics, pages 167--173, United Kingdom (Online), July 2020. [ .pdf ]
[11] S. Holly, A. Wendt, and M. Lechner. Profiling energy consumption of deep neural networks on Nvidia Jetson Nano. In 2020 11th International Green and Sustainable Computing Workshops (IGSC), pages 1--6, Oct 2020. [ DOI ]
[12] Christian Fruhwirth-Reisinger, Georg Krispel, Horst Possegger, and Horst Bischof. Towards data-driven multi-target tracking for autonomous driving. In Proceedings of the 25th Computer Vision Winter Workshop (CVWW), pages 27--36, Slovenia, 2020. Slovenian Pattern Recognition Society.
[13] Georg Krispel, Michael Opitz, Georg Waltner, Horst Possegger, and Horst Bischof. Fuseseg: Lidar point cloud segmentation fusing multi-modal data. In The IEEE Winter Conference on Applications of Computer Vision, pages 1874--1883, 2020.
[14] Alexander Wendt, Marco Wuschnig, and Martin Lechner. Speeding up Common Hyperparameter Optimization Methods by a Two-Phase-Search. In Proceedings of IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society, pages 517--522, Singapore (Online), 2020. IEEE IES. [ http ]