About

I am a Computer Vision and Robotics PhD researcher at Graz University of Technology in the Learning, Recognition & Perception group at the Institute of Visual Computing, supervised by Prof. Horst Bischof and Horst Possegger.

My research focuses on perception and prediction models for autonomous systems, with particular interests in motion forecasting, behavior prediction, and environment modeling. Passionate about advancing perception systems for robotics and autonomous vehicles, I specialize in developing efficient deep learning models and deploying them for practical use. My work spans both academic research and industrial R&D, utilizing real-world data and simulations to bring advanced models to deployment.

Publications

DESCENT: Directed Edge Scene Encoding for Airport Surface Movement Prediction
Alexander Prutsch, David Schinagl, Horst Possegger
Proceedings of the International Conference on Intelligent Robots and Systems (IROS), 2026.

Code Project Page

SHARP: Short-Window Streaming for Accurate and Robust Prediction in Motion Forecasting
Alexander Prutsch, Christian Fruhwirth-Reisinger, David Schinagl, Horst Possegger
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.

PDF arXiv Code Project Page Poster Publication

ASCENT: Transformer-Based Aircraft Trajectory Prediction in Non-Towered Terminal Airspace
Alexander Prutsch, David Schinagl, Horst Possegger
Proceedings of the International Conference on Robotics and Automation (ICRA), 2026.

PDF arXiv Code Project Page Poster

Learn to Rank: Visual Attribution by Learning Importance Ranking
David Schinagl, Christian Fruhwirth-Reisinger, Alexander Prutsch, Samuel Schulter, Horst Possegger
arXiv, 2026.

arXiv

Streaming Real-Time Trajectory Prediction Using Endpoint-Aware Modeling
Alexander Prutsch, David Schinagl, Horst Possegger
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) - Oral & Award Finalist, 2026.

PDF arXiv Code Project Page Publication

Lanes Are Not Enough: Enhancing Trajectory Prediction in Intralogistics Through Detailed Environmental Context
Alexander Prutsch, Matthias Wess, Horst Possegger
Proceedings of the International Conference on Intelligent Robots and Systems (IROS), 2025.

PDF Publication

Leveraging Foundation Models for Labeling Custom Object Masks in LiDAR Point Cloud Sequences
Alexander Prutsch, Mathias Schustereder, Horst Possegger
Proceedings of the European Conference on Mobile Robots (ECMR), 2025.

PDF Publication

Learning to Predict Mixed-Traffic Trajectories in Urban Scenarios from Little Training Data with Refined Environment Modeling
Alexander Prutsch, Horst Possegger
Proceedings of the IEEE Intelligent Vehicles Symposium (IV), 2025.

PDF Publication

Efficient Motion Prediction: A Lightweight & Accurate Trajectory Prediction Model With Fast Training and Inference Speed
Alexander Prutsch, Horst Bischof, Horst Possegger
Proceedings of the International Conference on Intelligent Robots and Systems (IROS), 2024.

PDF arXiv Code Publication

Action-By-Detection: Efficient Forklift Action Detection for Autonomous Mobile Robots in Warehouses
Alexander Prutsch, Horst Possegger, Horst Bischof
Proceedings of the International Conference on Robotics and Automation (ICRA), 2024.

PDF Publication

Studierfenster: An Open Science Cloud-Based Medical Imaging Analysis Platform
Jan Egger, Daniel Wild, Maximilian Weber, Christopher A Ramirez Bedoya, Florian Karner, Alexander Prutsch, Michael Schmied, Christina Dionysio, Dominik Krobath, Yuan Jin, Christina Gsaxner, Jianning Li, Antonio Pepe
Journal of Digital Imaging, 2022.

Publication

Design and Development of a Web-based Tool for Inpainting of Dissected Aortae in Angiography Images
Alexander Prutsch, Antonio Pepe, Jan Egger
Proceedings of the Central European Seminar on Computer Graphics (CESCG), 2020.

PDF arXiv Publication

Academic Service

Conference Reviewer for major vision, robotics, AI, and transportation venues, including ICCV, ECCV, ICRA, IROS, NeurIPS, and IV.