Dominik Schörkhuber
Projektass. Dipl.-Ing. / BSc
Role
- PreDoc Researcher
Computer Vision, E193-01
Contact
- dominik.schoerkhuber@tuwien.ac.at
- +43-1-58801-18837
- 1040 Wien, Favoritenstrasse 11 / Room HE0440
- vCard from TISS
- orcid.org/0000-0003-2015-6507
- informatics.tuwien.ac.at/people/dominik-schoerkhuber
- tiss.tuwien.ac.at/person/230875
Projects
- 2024 – 2026 / Vienna Business Agency (WAW) / Publications (2)
- 2023 – 2026 / Austrian Research Promotion Agency (FFG) / Publications (2)
- 2021 – 2025 / Austrian Research Promotion Agency (FFG) / Publications (7)
- 2020 – 2025 / Austrian Research Promotion Agency (FFG) / Publications (7)
- 2017 – 2025 / Austrian Research Promotion Agency (FFG) / Publications (11)
- 2016 – 2023 / Vienna Business Agency (WAW) / Publication
Publications
- Kunanuntakij, T., Schörkhuber, D., Gelautz, M. (2026). Synthetic Skeletal Pose Pre-training to Mitigate Data Scarcity in In-Cabin 2D-to-3D Pose Lifting. In Proceedings of the Austrian Symposium on AI, Robotics, and Vision 2026 (pp. 119–124). Peer-reviewed.
- Brunner, L., Schörkhuber, D. (2026). A Comparative Analysis of Video- and Pose-based Action Recognition for In-cabin Driver Monitoring. In Electronic Imaging. Electronic Imaging 2026, Burlingame, United States of America (the). Peer-reviewed.
- Panadero Palenzuela, R., Schörkhuber, D., Gelautz, M. (2025). Importance-Guided Interpretability and Pruning for Video Transformers in Driver Action Recognition. In 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (pp. 5295–5304). Peer-reviewed.
- Sagmeister, D., Schörkhuber, D., Nezveda, M., Stiedl, F., Schimkowitsch, M., Gelautz, M. (2023). Transfer learning for driver pose estimation from synthetic data. In 2023 IEEE Intelligent Vehicles Symposium (IV) Proceedings. 2023 IEEE Intelligent Vehicles Symposium (IV), Anchorage, AK, United States of America (the). IEEE. Peer-reviewed.
- Schörkhuber, D., Popp, R., Chistov, O., Windbacher, F., Hödlmoser, M., Gelautz, M. (2023). Design of an automotive platform for computer vision research. Journal of Electronic Imaging, 35(16), 119-1-119–6. Peer-reviewed.DOI: 10.2352/EI.2023.35.16.AVM-119 / Project: SmartProtect
- Schörkhuber, D., Pröll, M., Gelautz, M. (2022). Feature Selection and Multi-task Learning for Pedestrian Crossing Prediction. In 2022 16th International Conference on Signal-Image Technology Internet-Based Systems (SITIS) (pp. 439–444). IEEE. Peer-reviewed.DOI: 10.1109/SITIS57111.2022.00073 / Project: SmartProtect
- Schörkhuber, D., Groh, F., Gelautz, M. (2021). Bounding Box Propagation for Semi-automatic Video Annotation of Nighttime Driving Scenes. In University of Zagreb (Ed.), 2021 12th International Symposium on Image and Signal Processing and Analysis (ISPA). University of Zagreb. Peer-reviewed.
- Hartmann, P., Artmann, M., Nezveda, M., Gelautz, M., Moreno, A., Fallmann, D., Lahmer, M., Popp, R., Groh, F., Schörkhuber, D., Frantar, E., Seitner, F., Fischer, R. (2021). Adaptive Light Function Controlled in the Control Loop with Cameras. ATZ Worldwide, 123(2), 24–29.DOI: 10.1007/s38311-020-0610-5 / Project: CarVisionLight
- Groh, F., Schörkhuber, D., Gelautz, M. (2020). A tool for semi-automatic ground truth annotation of traffic videos. In Electronic Imaging (pp. 200–207). Peer-reviewed.DOI: 10.2352/issn.2470-1173.2020.16.avm-200 / Project: CarVisionLight
- Schörkhuber, D., Seitner, F., Salzbrunn, B., Gelautz, M., Braun, G. (2017). Intelligent Film Assistant for Personalized Video Creation on Mobile Devices. In Proceedings of the 15th International Conference on Advances in Mobile Computing & Multimedia - MoMM2017. The 15th International Conference on Advances in Mobile Computing Multimedia (MoMM2017), Salzburg, Austria. ACM International Conference Proceedings Series. Peer-reviewed.DOI: 10.1145/3151848.3151881 / Project: PersonalFilmAssistant
Presentations
- Fraissl, N., Schörkhuber, D., Hödlmoser, M., Berens, T. A., Wurzinger, L., Salzbrunn, B., Eckelt, M., Dimov, R., Gelautz, M. (2026, June 2). Towards Empathic Vehicles: Simulator-Based Induction of Affective States for Emotion Recognition [Poster Presentation]. SUMO - Simulation of Urban MObility, Berlin, Germany.HDL: 20.500.12708/228981 / Project: Empathic Vehicle
- Gelautz, M., Schörkhuber, D., Stoeva, D. (2023). Computer Vision for Autonomous Driving and Robotics [Presentation]. 30 Years ICG, Graz, Austria. Invited.
- Gelautz, M., Stoeva, D., Schörkhuber, D. (2019). Body Language in Human‐Robot Interaction. Doctoral College TrustRobots: Lecture Series, Wien, Austria.HDL: 20.500.12708/86881 / Project: CarVisionLight
Theses
- Kunanuntakij, T. (2026). Monocular 3D human pose estimation for in-cabin monitoring utilizing synthetic images [Diploma Thesis, Technische Universität Wien]. reposiTUm.DOI: 10.34726/hss.2026.140003 / Download: PDF
- Brunner, L. (2025). In-cabin driver monitoring using video- and pose-based action recognition [Diploma Thesis, Technische Universität Wien]. reposiTUm.DOI: 10.34726/hss.2025.117545 / Download: PDF
- Panadero Palenzuela, R. (2025). Vision transformer interpretability for video-based action recognition [Diploma Thesis, Technische Universität Wien]. reposiTUm.DOI: 10.34726/hss.2025.117540 / Download: PDF
- Pröll, M. R. (2022). Pedestrian crossing prediction in the context of autonomous driving [Diploma Thesis, Technische Universität Wien]. reposiTUm.DOI: 10.34726/hss.2022.93700 / Download: PDF
- Schörkhuber, D. (2018). Techniques for improving mobile video creation [Diploma Thesis, Technische Universität Wien]. reposiTUm.DOI: 10.34726/hss.2018.55540 / Download: PDF