Technische Universität München

research

∙ 11/14/2019

A Comparative Study between Bayesian and Frequentist Neural Networks for Remaining Useful Life Estimation in Condition-Based Maintenance

In the last decade, deep learning (DL) has outperformed model-based and ...

Luca Della Libera, et al. ∙

research

∙ 07/13/2022

Approximate Nash Equilibrium Learning for n-Player Markov Games in Dynamic Pricing

We investigate Nash equilibrium learning in a competitive Markov Game (M...

Larkin Liu, et al. ∙

research

∙ 02/25/2021

Machine Learning-Based Optimal Mesh Generation in Computational Fluid Dynamics

Computational Fluid Dynamics (CFD) is a major sub-field of engineering. ...

Keefe Huang, et al. ∙

research

∙ 08/22/2021

Graph2Pix: A Graph-Based Image to Image Translation Framework

In this paper, we propose a graph-based image-to-image translation frame...

Dilara Gokay, et al. ∙

research

∙ 08/30/2021

Whole Brain Vessel Graphs: A Dataset and Benchmark for Graph Learning and Neuroscience (VesselGraph)

Biological neural networks define the brain function and intelligence of...

Johannes C. Paetzold, et al. ∙

research

∙ 11/07/2021

Learn-Morph-Infer: a new way of solving the inverse problem for brain tumor modeling

Current treatment planning of patients diagnosed with brain tumor could ...

Ivan Ezhov, et al. ∙

research

∙ 05/02/2022

A Deep Learning-based Integrated Framework for Quality-aware Undersampled Cine Cardiac MRI Reconstruction and Analysis

Cine cardiac magnetic resonance (CMR) imaging is considered the gold sta...

Inês P. Machado, et al. ∙

research

∙ 06/16/2022

SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation

Adapting to a continuously evolving environment is a safety-critical cha...

Tao Sun, et al. ∙

research

∙ 08/01/2022

A knee cannot have lung disease: out-of-distribution detection with in-distribution voting using the medical example of chest X-ray classification

Deep learning models are being applied to more and more use cases with a...

Alessandro Wollek, et al. ∙

research

∙ 03/10/2021

Are we using appropriate segmentation metrics? Identifying correlates of human expert perception for CNN training beyond rolling the DICE coefficient

In this study, we explore quantitative correlates of qualitative human e...

Florian Kofler, et al. ∙

research

∙ 12/02/2021

Object-aware Monocular Depth Prediction with Instance Convolutions

With the advent of deep learning, estimating depth from a single RGB ima...

enis-simsar, et al. ∙

research

∙ 03/09/2022

NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimation

Pose estimation of 3D objects in monocular images is a fundamental and l...

Fu Li, et al. ∙

research

∙ 05/10/2022

Predictive Compliance Monitoring in Process-Aware Information Systems: State of the Art, Functionalities, Research Directions

Business process compliance is a key area of business process management...

Stefanie Rinderle-Ma, et al. ∙

research

∙ 11/26/2019

Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priors

We present an automatic annotation pipeline to recover 9D cuboids and 3D...

Sergey Zakharov, et al. ∙

research

∙ 10/13/2021

Sustainability Through Cognition Aware Safety Systems – Next Level Human-Machine-Interaction

Industrial Safety deals with the physical integrity of humans, machines ...

Juergen Mangler, et al. ∙

research

∙ 03/15/2022

From 2D to 3D: Re-thinking Benchmarking of Monocular Depth Prediction

There have been numerous recently proposed methods for monocular depth p...

Evin Pınar Örnek, et al. ∙

research

∙ 08/25/2019

Adversarial Convolutional Networks with Weak Domain-Transfer for Multi-Sequence Cardiac MR Images Segmentation

Analysis and modeling of the ventricles and myocardium are important in ...

Jingkun Chen, et al. ∙

research

∙ 07/06/2021

Enabling Un-/Semi-Supervised Machine Learning for MDSE of the Real-World CPS/IoT Applications

In this paper, we propose a novel approach to support domain-specific Mo...

Armin Moin, et al. ∙

research

∙ 10/20/2021

SocialVisTUM: An Interactive Visualization Toolkit for Correlated Neural Topic Models on Social Media Opinion Mining

Recent research in opinion mining proposed word embedding-based topic mo...

Gerhard Hagerer, et al. ∙

research

∙ 02/02/2020

WeatherBench: A benchmark dataset for data-driven weather forecasting

Data-driven approaches, most prominently deep learning, have become powe...

Stephan Rasp, et al. ∙

research

∙ 07/30/2021

NeuralDP Differentially private neural networks by design

The application of differential privacy to the training of deep neural n...

Moritz Knolle, et al. ∙

research

∙ 07/29/2021

U-GAT: Multimodal Graph Attention Network for COVID-19 Outcome Prediction

During the first wave of COVID-19, hospitals were overwhelmed with the h...

Matthias Keicher, et al. ∙

research

∙ 09/18/2018

Predictive Collective Variable Discovery with Deep Bayesian Models

Extending spatio-temporal scale limitations of models for complex atomis...

Markus Schöberl, et al. ∙

research

∙ 03/16/2020

clDice – a Topology-Preserving Loss Function for Tubular Structure Segmentation

Accurate segmentation of tubular, network-like structures, such as vesse...

Suprosanna, et al. ∙

research

∙ 05/23/2020

Hierarchical Feature Embedding for Attribute Recognition

Attribute recognition is a crucial but challenging task due to viewpoint...

Jie Yang, et al. ∙

research

∙ 06/21/2020

Generalized Zero and Few-Shot Transfer for Facial Forgery Detection

We propose Deep Distribution Transfer(DDT), a new transfer learning appr...

Shivangi Aneja, et al. ∙

research

∙ 09/05/2021

Towards high-accuracy deep learning inference of compressible turbulent flows over aerofoils

The present study investigates the accurate inference of Reynolds-averag...

Li-Wei Chen, et al. ∙

research

∙ 01/25/2020

e-UDA: Efficient Unsupervised Domain Adaptation for Cross-Site Medical Image Segmentation

Domain adaptation in healthcare data is a potentially critical component...

Hongwei Li, et al. ∙

research

∙ 01/30/2020

ERA: A Dataset and Deep Learning Benchmark for Event Recognition in Aerial Videos

Along with the increasing use of unmanned aerial vehicles (UAVs), large ...

Lichao Mou, et al. ∙

research

∙ 05/15/2020

A Deep Learning-based Radar and Camera Sensor Fusion Architecture for Object Detection

Object detection in camera images, using deep learning has been proven s...

Felix Nobis, et al. ∙

research

∙ 10/26/2021

CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration

We study the problem of extracting correspondences between a pair of poi...

Hao Yu, et al. ∙

research

∙ 01/17/2022

Disentangled Latent Transformer for Interpretable Monocular Height Estimation

Monocular height estimation (MHE) from remote sensing imagery has high p...

Zhitong Xiong Sining Chen, et al. ∙

research

∙ 03/17/2022

Vox2Cortex: Fast Explicit Reconstruction of Cortical Surfaces from 3D MRI Scans with Geometric Deep Neural Networks

The reconstruction of cortical surfaces from brain magnetic resonance im...

Fabian Bongratz, et al. ∙

research

∙ 12/16/2019

Learning a Neural Solver for Multiple Object Tracking

Graphs offer a natural way to formulate Multiple Object Tracking (MOT) w...

Guillem Brasó, et al. ∙

research

∙ 05/08/2021

On Linear Interpolation in the Latent Space of Deep Generative Models

The underlying geometrical structure of the latent space in deep generat...

Mike Yan Michelis, et al. ∙

research

∙ 06/02/2021

Undecidability of Learnability

Machine learning researchers and practitioners steadily enlarge the mult...

Matthias C. Caro, et al. ∙

research

∙ 05/10/2022

VesNet-RL: Simulation-based Reinforcement Learning for Real-World US Probe Navigation

Ultrasound (US) is one of the most common medical imaging modalities sin...

Yuan Bi, et al. ∙

research

∙ 10/02/2018

FutureGAN: Anticipating the Future Frames of Video Sequences using Spatio-Temporal 3d Convolutions in Progressively Growing Autoencoder GANs

We propose a new Autoencoder GAN model, FutureGAN, that predicts future ...

Sandra Aigner, et al. ∙

research

∙ 09/29/2019

SteReFo: Efficient Image Refocusing with Stereo Vision

Whether to attract viewer attention to a particular object, give the imp...

Benjamin Busam, et al. ∙

research

∙ 12/13/2019

Inferring Super-Resolution Depth from a Moving Light-Source Enhanced RGB-D Sensor: A Variational Approach

A novel approach towards depth map super-resolution using multi-view unc...

Lu Sang, et al. ∙

research

∙ 02/03/2021

Learning Graph Embeddings for Compositional Zero-shot Learning

In compositional zero-shot learning, the goal is to recognize unseen com...

Muhammad Ferjad Naeem, et al. ∙

research

∙ 04/01/2022

Graph-in-Graph (GiG): Learning interpretable latent graphs in non-Euclidean domain for biological and healthcare applications

Graphs are a powerful tool for representing and analyzing unstructured, ...

Kamilia Mullakaeva, et al. ∙

research

∙ 07/25/2019

MultiDepth: Single-Image Depth Estimation via Multi-Task Regression and Classification

We introduce MultiDepth, a novel training strategy and convolutional neu...

Lukas Liebel, et al. ∙

research

∙ 05/07/2020

Planning from Images with Deep Latent Gaussian Process Dynamics

Planning is a powerful approach to control problems with known environme...

Nathanael Bosch, et al. ∙

research

∙ 11/11/2021

AlphaGarden: Learning to Autonomously Tend a Polyculture Garden

This paper presents AlphaGarden: an autonomous polyculture garden that p...

Mark Presten, et al. ∙

research

∙ 08/29/2019

CorNet: Generic 3D Corners for 6D Pose Estimation of New Objects without Retraining

We present a novel approach to the detection and 3D pose estimation of o...

Giorgia Pitteri, et al. ∙

research

∙ 12/11/2019

HistoNet: Predicting size histograms of object instances

We propose to predict histograms of object sizes in crowded scenes direc...

Kishan Sharma, et al. ∙

research

∙ 03/30/2020

Ultrasound-Guided Robotic Navigation with Deep Reinforcement Learning

In this paper we introduce the first reinforcement learning (RL) based r...

Hannes Hase, et al. ∙

research

∙ 06/01/2021

A Road-map to Robot Task Execution with the Functional Object-Oriented Network

Following work on joint object-action representations, the functional ob...

David Paulius, et al. ∙

research

∙ 08/20/2021

Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval from a Single Image

3D perception of object shapes from RGB image input is fundamental towar...

Weicheng Kuo, et al. ∙

Technische Universität München

Featured Researchers