Research work of the KISSKI consortium

Publications

The following publications provide an insight into the competences of the KISSKI consortium.

2024


Publications financed with KISSKI funds

Mastering Zero-Shot Interactions in Cooperative and Competitive Simultaneous Games

Yannik Mahlau, Frederik Schubert, Bodo; Rosenhahn

2024 / Proceedings of the 41st International Conference on Machine Learning (ICML)

Q-SENN: Quantized Self-Explaining Neural Networks

Thomas Norrenbrock, Marco Rudolph, Bodo Rosenhahn

2024 / AAAI Technical Track on Safe, Robust and Responsible AI

Robust Shape Fitting for 3D Scene Abstraction

Florian Kluger, Eric Brachmann, Michael Ying Yang, Bodo Rosenhahn

2024 / IEEE transactions on pattern analysis and machine intelligence (TPAMI)

SplatPose and Detect: Pose-Agnostic 3D Anomaly Detection

Mathis Kruse, Marco Rudolph, Dominik Woiwode, Bodo Rosenhahn

2024 / CVPW-WS, VAND Visual Anomaly and Novelty Detection

PARSAC: Accelerating Robust Multi-Model Fitting with Parallel Sample Consensus

Florian Kluger, Bodo Rosenhahn

2024 / AAAI

Selected publications of the KISSKI consoritum (financed without KISSKI funds)

Privacy Protection Behaviors from a New Angle: Exploratory Analysis on a Russian Sample

Denis Obrezkov

2024 / Proceedings on Privacy Enhancing Technologies Symposium

FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing

Cong,Yuren, Mengmeng Xu, Christian Simon, Shoufa Chen, Jiawei Ren, Yanping Xie, Juan-Manuel Perez-Rua, Bodo Rosenhahn, Xiang,Tao, Sen; He

2024 / International Conference on Learning Representations (ICLR)


2023


Publications financed with KISSKI funds

Compensation Learning in Semantic Segmentation

Timo Kaiser, Christoph Reinders, Bodo; Rosenhahn

2023 / Computer Vision and Pattern Recognition Workshops (CVPRW)

HyperSparse Neural Networks: Shifting Exploration to Exploitation through Adaptive Regularization

Patrick Glandorf*, Timo Kaiser*, Bodo Rosenhahn, (*contributed equally)

2023 / International Conference on Computer Vision Workshops (ICCVW)

Personalized 3D Human Pose and Shape Refinement

Tom Wehrbein, Bodo Rosenhahn, Iain Matthews, Carsten; Stoll

2023 / International Conference on Computer Vision Workshops (ICCVW)

Human Spine Motion Capture using Perforated Kinesiology Tape

Hendrik Hachmann, Bodo Rosenhahn

2023 / Computer Vision and Pattern Recognition Workshops (CVPRW)

AutoML in heavily constrained applications

Felix Neutatz, Marius Lindauer, Ziawasch Abedjan

2023 / VLDB Journal

The voraus-AD Dataset for Anomaly Detection in Robot Applications

Jan Thieß Brockmann*, Marco Rudolph*, Bodo Rosenhahn, Bastian Wandt, (* equal contribution)

2023 / Transactions on Robotics

Selected publications of the KISSKI consoritum (financed without KISSKI funds)

Asymmetric Student-Teacher Networks for Industrial Anomaly Detection

Marco Rudolph, Tom Wehrbein, Bodo Rosenhahn, Bastian Wandt

2023

Learning Activation Functions for Sparse Neural Networks

Mohammed Loni, Aditya Mohan, Mehdi Asadi, Marius Lindauer

2023 / International Conference on Automated Machine Learning

Organizing Scholarly Knowledge in the Open Research Knowledge Graph An Open-Science Platform for FAIR Scholarly Knowledge

Sören Auer, Markus Stocker, Oliver Karras, Allard Oelen, Jennifer D'Souza, Anna-Lena Lorenz

2023

Increasing Reproducibility in Science by Interlinking Semantic Artifact Descriptions in a Knowledge Graph

Hassan Hussein, Kheir Eddine Farfar, Allard Oelen, Oliver Karras, Sören Auer

2023

KPI Extraction from Maintenance Work Orders — A Comparison of Expert Labeling, Text Classification and AI-Assisted Tagging for Computing Failure Rates of Wind Turbines

Marc-Alexander Lutz, Bastian Schäfermeier, Rachael Sexton, Michael Sharp, Alden Dima, Stefan Faulstich, Jagan Mohini Aluri

2023 / Energies

Optimization of Sparsity-Constrained Neural Networks as a Mixed Integer Linear Program

Bodo Rosenhahn

2023 / Journal of Optimization Theory and Applications

Multi-Resolution Segmentation of Solar Photovoltaic Systems Using Deep Learning

Maximilian Kleebauer, Christopher Marz, Christoph Reudenbach, Martin Braun

2023 / Remote Sensing

Towards FAIR Semantic Publishing of Research Dataset Metadata in the Open Research Knowledge Graph

Raia Abu Ahmad, Jennifer D'Souza, Matthäus Zloch, Wolfgang Otto, Georg Rehm, Allard Oelen, Stefan Dietze, Sören Auer

2023

Power flow forecasts at transmission grid nodes using Graph Neural Networks

Dominik Beinert, Clara Holzhüter, Josephine M. Thomas, Stephan Vogt

2023 / Energy and AI

RelTR: Relation Transformer for Scene Graph Generation

Yuren Cong, Michael Yang, Bodo; Rosenhahn

2023 / IEEE transactions on pattern analysis and machine intelligence (TPAMI)

Deep Reinforcement Learning for Autonomous Driving Using High-Level Heterogeneous Graph Representations

Maximilian Schier, Christoph Reinders, Bodo Rosenhahn

2023 / 2023 IEEE International Conference on Robotics and Automation (ICRA)

Secure HPC: A workflow providing a secure partition on an HPC system

Hendrik Nolte, Nicolai Spicher, Andrew Russel, Tim Ehlers, Sebastian Krey, Dagmar Krefting, Julian Kunkel

2023 / Future Generation Computer Systems

Targeted adversarial attacks on wind power forecasts

René Heinrich, Christoph Scholz, Stephan Vogt, Malte Lehna

2023 / Machine Learning

Exploiting Subword Permutations to Maximize CNN Compute Performance and Efficiency

Michael Beyer, Sven Gesper, Andre Guntoro, Guillermo Payá-Vayá, Holger Blume

2023 / International Conference on Application-specific Systems, Architectures and Processors (ASAP)

Contextualize Me - The Case for Context in Reinforcement Learning

Carolin Benjamins, Theresa Eimer, Frederik Schubert, Aditya Mohan, Sebastian Döhler, André Biedenkapp, Bodo Rosenhahn, Frank Hutter, Marius Lindauer

2023 / Transactions on Machine Learning Research

Governance-Centric Paradigm: Overcoming the Information Gap between Users and Systems by Enforcing Data Management Plans on HPC-Systems

Hendrik Nolte, Julian Kunkel

2023 / INFOCOMP

Improving the Interpretability of ECoG-Signals by Identifying Significant Signal-Segments with Explainable AI

Julian Drewljau, Mesbah Alam, Joachim Krauss, Kerstin Schwabe, Holger Blume

2023 / Abstracts of the 57th Annual Meeting of the German Society of Biomedical Engineering

N2V2PRO: Neural Network Mapping Framework for a Custom Vector Processor Architecture

Sven Gesper, Gia Bao Thieu, Daniel Köhler, Markus Kock, Tim Berthold, Oliver Renke, Holger Blume, Guillermo Payá-Vayá

2023 / International Conference on Consumer Electronics-Berlin (ICCE-Berlin)

ZuSE Ki-Avf: Application-Specific AI Processor for Intelligent Sensor Signal Processing in Autonomous Driving

Thieu, Gia Bao, et al.

2023 / Design, Automation & Test in Europe Conference & Exhibition (DATE)


2022


Selected publications of the KISSKI consoritum (financed without KISSKI funds)

AI agents envisioning the future: Forecast-based operation of renewable energy storage systems using hydrogen with Deep Reinforcement Learning

Alexander Dreher, Thomas Bexten, Tobias Sieker, Malte Lehna, Jonathan Schütt, Christoph Scholz, Manfred Wirsum

2022 / Energy Conversion and Management

Efficient Automated Deep Learning for Time Series Forecasting

Difan Deng, Florian Karl, Frank Hutter, Bernd Bischl, Marius Lindauer

2022 / European Conference on Machine Learning (ECML)

Constrained Mean Shift Clustering

Maximilian Schier, Christoph Reinders, Bodo Rosenhahn

2022 / Proceedings of the 2022 SIAM International Conference on Data Mining (SDM)

ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing

Christoph Reinders, Frederik Schubert, Bodo Rosenhahn

2022 / 31st International Joint Conference on Artificial Intelligence and the 25th European Conference on Artificial Intelligence (IJCAI-ECAI)

Hands-free AutoML via Meta-Learning

Matthias Feurer, Katharina Eggensperger, Stefan Falkner, Marius Lindauer, Frank Hutter

2022 / Journal of Machine Learning Research

LMGP: Lifted Multicut Meets Geometry Projections for Multi-Camera Multi-Object Tracking

Duy Nguyen, Roberto Henschel, Bodo Rosenhahn, Daniel Sonntag, Paul Swoboda

2022 / Computer Vision and Pattern Recognition (CVPR)

A Reinforcement Learning approach for the continuous electricity market of Germany: Trading from the perspective of a wind park operator

Malte Lehna, Björn Hoppmann, Christoph Scholz, René Heinrich

2022 / Energy and AI

Secure Authorization for RESTful HPC Access with FaaS Support

Christian Köhler, Mohammed Hossein Biniaz, Sven Bingert, Hendrik Nolte, Julian Kunkel

2022 / International Journal on Advances in Security

Performance Evaluation of Open-Source Serverless Platforms for Kubernetes

Jonathan Decker, Piotr Kasprzak, Julian Martin Kunkel

2022 / Algorithms

Take 5: Interpretable Image Classification with a Handful of Features

Thomas Norrenbrock, Marco Rudolph, Bodo; Rosenhahn

2022 / Progress and Challenges in Building Trustworthy Embodied AI @NeurIPS

Predictive accuracy of CNN for cortical oscillatory activity in an acute rat model of parkinsonism

Ali Abdul Nabi Ali, Mesbah Alam, Simon Klein, Nicolai Behmann, Joachim K. Krauss, Theodor Doll, Holger Blume, Kerstin Schwabe

2022 / Neural Networks


2021


Selected publications of the KISSKI consoritum (prior to KISSKI project start)

Auto-Pytorch: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL

Lucas Zimmer, Marius Lindauer, Frank Hutter

2021 / IEEE Transactions on Pattern Analysis and Machine Intelligence

Autoencoder-based anomaly root cause analysis for wind turbines

Cyriana M.A. Roelofs, Marc-Alexander Lutz, Stefan Faulstich, Stephan Vogt

2021 / Energy and AI

Compact representations for efficient storage of semantic sensor data

Farah Karim, Maria-Esther Vidal, Sören Auer

2021

Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows

Tom Wehrbein, Marco Rudolph, Bodo Rosenhahn, Bastian Wandt

2021 / International Conference on Computer Vision (ICCV)

Semi-automatic generation of training samples for detecting renewable energy plants in high-resolution aerial images

Maximilian Kleebauer, Daniel Horst, Christopher Reudenbach

2021 / Remote Sensing

Fixed Point Analysis Workflow for efficient Design of Convolutional Neural Networks in Hearing Aids

Simon Klein, Jonas Kantic, Holger Blume

2021 / Current Directions in Biomedical Engineering