Alina Roitberg Tenure-Track Assistant Professor at the University of Stuttgart
alina.roitberg [at] ki.uni-stuttgart.de

Research

With the accuracy of CNNs and Transformer models gradually reaching the ceiling, the existing gap between the published methods and their applications in practice makes us wonder about important performance aspects being overlooked. In my research, I aim to go beyond the traditional goal of high top-1 accuracy on a static carefully designed classes, and develop human activity recognition models which do not only (1) assign the correct category, but also (2) reliably identify incorrect predictions and unknown situations and (3) trace back their causes of failure, and (4) have tools for dealing with new concepts-of-interest without costly labelling. I am especially interested in developing algorithms to solve impactful problems in challenging open-world applications, such as autonomous driving and robotics. My main research topics are:

• Deep Learning and Computer Vision for Intelligent Vehicles and Robotics
• Visual and Multimodal Perception of Humans (Activities, Intentions, Emotions and Beyond)
• Uncertainty-aware and Interpretable Recognition
• Open Set and Open Domain Recognition
• Data-efficient Recognition, Zero- and Few-Shot-Learning
• Simulation- and Knowledge-enhanced Learning
• Applications for Human Assistance (e.g., Computer Vision for the Blind), Health Monitoring, Physiological Analysis and Medical Diagnostics

Short CV

• Since August 2023: Faculty member of the International Max Planck Research School for Intelligent Systems (IMPRS-IS).
• Since June 2023: Tenure-Track Assistant Professor - Autonomous Sensing and Perception Group, University of Stuttgart.
• April 2023 - May 2023: Visiting Researcher - Chair for Sustainable Transport Logistics 4.0, Johannes Kepler University Linz, Austria.
• April 2021 - May 2023: Postdoctoral Researcher - Lead of the Activity Recognition Group at CV:HCI.
• PhD at Karlsruhe Institute of Technology (summa cum laude), April 2017 - April 2021. Topic: "Uncertainty-aware Models for Deep Learning-based Human Activity Recognition and Applications in Intelligent Vehicles." Referents: Prof. Dr.-Ing. Rainer Stiefelhagen (KIT, IAR) und Prof. Dr. Mohan Trivedi (University of San Diego). The manuscript is available here. IEEE ITSS Best Dissertation Award 2021 (second prize).
• PhD internship at Facebook Zurich - Computer Vision for AR/VR, September 2020 - November```html 2020.
• Consultant at MHP - A Porsche Company, Big Data & Analytics, 2016 - 2017.
• M.Sc. in Computer Science at Technical University Munich, 2013 - 2015.
• Student Assistant at fortiss GmbH, developing human-robot-interfaces for industrial robotics, 2014 - 2015.
• Erasmus studies at Chalmers University of Technology, Gothenburg, Sweden, 2012 - 2013.
• B.Sc. in Computer Science at Technical University Munich, 2009 - 2012.

Scholarships & Awards

• Elite program for PostDocs of the BW Fondation (accepted for the year 2023) - Baden-Württemberg Fondation, Dec 2022.
• Best Dissertation Award (first prize) - IEEE ITSS Germany PhD Dissertation Award, June 2022.
• Best Dissertation Prize - KIT Faculty of Computer Science, donated by the Erika and Dr. Wolfgang Eichelberger Foundation, June 2022.
• Helmholtz Doctoral Award - yearly Helmholtz Doctoral Prize for mission-oriented research in the field "Information", Apr 2022.
• KIT Doctoral Award - yearly prize awarded by KIT to outstanding doctoral researchers, Dec 2021.
• Best Dissertation Award 2021 (second prize) - IEEE Intelligent Transportation Systems Society (ITSS), Sep 2021.
• Best Student Paper First Runner Up Award - Intelligent Vehicles Symposium (Awarded Paper: "Open Set Driver Activity Recognition"), Jan 2020.
• ECCV Women in Computer Vision Travel Grant awarded for the presentation "Towards Human Activity Recognition in Autonomous Vehicles", 2018.
• Deutschlandstipendium - German national scholarship for talented students, 2014.
• Google Summer of Code, a programming scholarship awarded by Google to support students working on open-source software (project: Point Cloud Library), 2014.
• School-time - three awards for the second and one award for the third place in the Ukrainian Mathematical Olympiadas (7th and 8th grade).

Funded Projects

• Smart Villages - Visual Recognition of Trees, Funding Source: Landesamt für Geoinformation und Landentwicklung (LGL) Baden-Württemberg, May 2024 - April 2025.
• SFB "Kreislauffabrik für das ewige Produkt", Sub-project "Visual Perception of the Human". Funding Source: DFG. Duration: Apr 2024 - Dec 2027.
• EXC 2120 IntCDC-Project: "Visual Semantic Scene Understanding for Collaborative IntCDC Wood Building System". Funding Source: DFG, Cluster of Excellence IntCDC. Duration: Jan 2024 - Dec 2025.
• EXC 2075 SIMTECH-Project: "Resource-efficient Domain Adaptation and Simulation-Enhanced Learning in Spatiotemporal Data". Funding Source: DFG, Cluster of Excellence "Data-Integrated Simulation Science (SIMTECH)". Duration: Jan 2024 - Dec 2025.
• PRIDRIVE Topic: Driver monitoring under privacy constraints. Funding Source: Elite program for PostDocs of the BW Foundation. Duration: Jul 2023 - Dec 2025.

Past Projects (as Member)

• SmartAge - Untersuchung intelligenter Formen von Selbstregulation und Ko-Regulation unter Realbedingungen (Carl-Zeiss-Stiftung, 2021 - ongoing). Role: team member, co-supervision of a PhD student, technical coordination of the video-based human observation work package. Web: www.smartage-heidelberg.com.
• JuBot - Jung bleiben mit Robotern (Carl-Zeiss-Stiftung, since 2020). Role: team member, co-supervision of a PhD student. Web: www.kcist.kit.edu/deutsch/123_1205.php.
• CC-King - Competence Center KI-Engineering (2020 - 2022). Role: team member, technical coordination of the learning from simulations work package, non-official help in the proposal conception and writing. Web: www.ki-engineering.eu.
• ESKIMO - Mit künstlicher Intelligenz die Baustelle genau im Blick (BMBF, 2020 - 2022). Role: team member, technical coordination of the computer vision work packages. Web: www.eskimo-projekt.de.
• PAKoS - Personalisierte, adaptive kooperative Systeme für automatisierte Fahrzeuge (BMBF, 2017-2021). Role: team member, project implementation (human observation for driver assistance). Web: www.projekt-pakos.de.