Paper accepted at WACV 2023
The paper "What’s Outside the Intersection? Fine-grained Error Analysis for Semantic Segmentation Beyond IoU"
by Maximilian Bernhard, Yannic Kindermann, Roberto Amoroso, Matthias Schubert, Lorenzo Baraldi, Rita Cucchiara and Volker Tresp
has been accepted at the IEEE/CVF Winter Conference on Applications of Computer Vision
(WACV 24), 4.01–08.01 2024,
Waikoloa, Hawaii
Paper accepted at ECAI 2023
The paper "Simplex Decomposition for Portfolio Allocation Constraints in Reinforcement Learning"
by David Winkel, Niklas Strauß, Matthias Schubert, Thomas Seidl
has been accepted at the 26th European Conference on Artificial Intelligence
(Ecai 2023), 30.09–05.10 2023,
Kraków, Poland
Paper accepted at ICCV 2023
The paper "MapFormer: Boosting Change Detection by Using Pre-change Information" "
by Maximilian Bernhard, Niklas Strauss, Matthias Schubert
has been accepted at the IEEE/CVF International Conference on Computer Vision (ICCV 23), 2-5 October 2023, Paris, France
Paper accepted at SSTD 2023
The paper "DEAR: Dynamic Electric Ambulance Redeployment"
by Lukas Rottkamp, Niklas Strauß, Matthias Schubert
has been accepted at the 18th International Symposium on Spatial and Temporal Data
(SSTD 2023), 23–25 August 2023,
Calgary, AB, Canada
PhD Defense -- Christian Frey
On 19th June 2023, Christian Frey successfully defended his PHD-Thesis "Learning from Complex Networks".
Congratulations Chris!!!
Paper accepted at PAKDD 2023
The paper "Constrained Portfolio Management using Action Space Decomposition for Reinforcement Learning"
by David Winkel, Niklas Strauß, Matthias Schubert, Yunpu Ma, Thomas Seidl
has been accepted at the 27th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2023),
25–28 May 2023, Osaka, Japan
Announcement
Abby-Net Summer School'23
on Natural Resource Management and Energy Systems Under Changing Environmental Conditions
The 8th Abby-Net summer school will be hosted by the University of Calgary at the Barrier Lake Station. For further informaction click here.
Paper accepted at AAAI 2023
The paper "InstanceFormer: An Online Video Instance Segmentation Framework"
by Rajat Koner, Tanveer Hannan, Suprosanna Shit, Sahand Sharifzadeh, Matthias Schubert, Thomas Seidl, Volker Tresp
has been accepted at the 37th AAAI Conference on Artificial Intelligence
7-14 February 2023, Washington D.C., USA
about AI-Beyond
AI-beyond strives to advance modern AI technology to enable automated systems to make rational decisions and optimize their behaviour. Our research is centered around spatial applications like analysing and acquiring sensor data. We optimize mobility tasks with respect to various optimization criteria. As members of the Abby-Net research network, we lay a particular focus on sustainability and actively explore the connection point between modern AI, sustainable mobility, and energy solutions. Thus, we actively support projects monitoring environmental change.
Current Members
Matthias Schubert
Professor for Artificial Intelligence and Data Management
at LMU Munich
Niklas Strauss
PhD student working on reinforcement learning and sequential planning in mobility applications.
Maximilian Bernhard
PhD student working on computer vision and remote sensing.
Zongyue Li
PhD student working on recommendation systems and meta reinforcement learning.
Lukas Rottkamp
PhD student working on spatial analytics and planning methods based on sensor data.
Thomas Ramsauer
PhD student working on multispectral remote sensing data.
(co-supervized with Prof. Ralf Ludwig (geography))
David Winkel
PhD student working onreinforcement learning in financial applications.
(co-supervized with Prof. Thomas Seidl)
Former group members/Supervised PhD thesis
Evgeniy Faerman
former Phd student
Phd thesis: "Representation learning on relational data"
Christian Frey
former Phd student
Phd thesis: "Learning from complex Networks"
Yunpu Ma
postdoctoral researcher within MCML
Sebastian Schmoll
former Phd student
Phd thesis: "Navigation with uncertain Spatio-Temporal Resources"
Gregor Jósse
former Phd student
Phd thesis: "Query processing in complex modern traffic networks"