
Shearlets as Feature Extractor for Semantic Edge Detection: The ModelBased and DataDriven Realm
Semantic edge detection has recently gained a lot of attention as an ima...
read it

Kernel of CycleGAN as a Principle homogeneous space
Unpaired imagetoimage translation has attracted significant interest d...
read it

Deep Bayesian Inversion
Characterizing statistical properties of solutions of inverse problems i...
read it

Humancentered collaborative robots with deep reinforcement learning
We present a reinforcement learning based framework for humancentered c...
read it

Decoupling Inherent Risk and Early Cancer Signs in Imagebased Breast Cancer Risk Models
The ability to accurately estimate risk of developing breast cancer woul...
read it

The Importance of Balanced Data Sets: Analyzing a Vehicle Trajectory Prediction Model based on Neural Networks and Distributed Representations
Predicting future behavior of other traffic participants is an essential...
read it

Which way? DirectionAware Attributed Graph Embedding
Graph embedding algorithms are used to efficiently represent (encode) a ...
read it

Imitating by generating: deep generative models for imitation of interactive tasks
To coordinate actions with an interaction partner requires a constant ex...
read it

Neural Outlier Rejection for SelfSupervised Keypoint Learning
Identifying salient points in images is a crucial component for visual o...
read it

Finitetime Identification of Stable Linear Systems: Optimality of the LeastSquares Estimator
We provide a new finitetime analysis of the estimation error of stable ...
read it

Coordinatesbased Resource Allocation Through Supervised Machine Learning
Appropriate allocation of system resources is essential for meeting the ...
read it

GCNv2: Efficient Correspondence Prediction for RealTime SLAM
In this paper, we present a deep learningbased network, GCNv2, for gene...
read it

Machine Learning assisted Handover and Resource Management for Cellular Connected Drones
Enabling cellular connectivity for drones introduces a wide set of chall...
read it

Analyzing the Capacity of Distributed Vector Representations to Encode Spatial Information
Vector Symbolic Architectures belong to a family of related cognitive mo...
read it

Hyperplane Arrangements of Trained ConvNets Are Biased
We investigate the geometric properties of the functions learned by trai...
read it

α Belief Propagation for Approximate Inference
Belief propagation (BP) algorithm is a widely used messagepassing metho...
read it

Beyond the Self: Using Grounded Affordances to Interpret and Describe Others' Actions
We propose a developmental approach that allows a robot to interpret and...
read it

Sparse2Dense: From direct sparse odometry to dense 3D reconstruction
In this paper, we proposed a new deep learning based dense monocular SLA...
read it

A Framework for Depth Estimation and Relative Localization of Ground Robots using Computer Vision
The 3D depth estimation and relative pose estimation problem within a de...
read it

Neural Network based Explicit Mixture Models and Expectationmaximization based Learning
We propose two neural network based mixture models in this article. The ...
read it

Tighter expected generalization error bounds via Wasserstein distance
In this work, we introduce several expected generalization error bounds ...
read it

Entropyregularized Optimal Transport Generative Models
We investigate the use of entropyregularized optimal transport (EOT) co...
read it

A Hierarchical Grocery Store Image Dataset with Visual and Semantic Labels
Image classification models built into visual support systems and other ...
read it

Explanationbased Weaklysupervised Learning of Visual Relations with Graph Networks
Visual relationship detection is fundamental for holistic image understa...
read it

Incremental inference of collective graphical models
We consider incremental inference problems from aggregate data for colle...
read it

α Belief Propagation as Fully Factorized Approximation
Belief propagation (BP) can do exact inference in loopfree graphs, but ...
read it

Bayesian nonparametric shared multisequence time series segmentation
In this paper, we introduce a method for segmenting time series data usi...
read it

Banach Wasserstein GAN
Wasserstein Generative Adversarial Networks (WGANs) can be used to gener...
read it

Optimal Attacks on Reinforcement Learning Policies
Control policies, trained using the Deep Reinforcement Learning, have be...
read it

A Survey of Behavior Trees in Robotics and AI
Behavior Trees (BTs) were invented as a tool to enable modular AI in com...
read it

Distributed sampleddata control of nonholonomic multirobot systems with proximity networks
This paper considers the distributed sampleddata control problem of a g...
read it

Interactive Robot Learning of Gestures, Language and Affordances
A growing field in robotics and Artificial Intelligence (AI) research is...
read it

SelfSupervised VisionBased Detection of the Active Speaker as a Prerequisite for SociallyAware Language Acquisition
This paper presents a selfsupervised method for detecting the active sp...
read it

Minimal Exploration in Structured Stochastic Bandits
This paper introduces and addresses a wide class of stochastic bandit pr...
read it

Advances in Variational Inference
Many modern unsupervised or semisupervised machine learning algorithms ...
read it

Learned Primaldual Reconstruction
We propose the Learned PrimalDual algorithm for tomographic reconstruct...
read it

Machine Learning and Social Robotics for Detecting Early Signs of Dementia
This paper presents the EACare project, an ambitious multidisciplinary ...
read it

On the Performance of Network Parallel Training in Artificial Neural Networks
Artificial Neural Networks (ANNs) have received increasing attention in ...
read it

Learning to solve inverse problems using Wasserstein loss
We propose using the Wasserstein loss for training in inverse problems. ...
read it

Unsupervised Object Discovery and Segmentation of RGBDimages
In this paper we introduce a system for unsupervised object discovery an...
read it

Dynamic texture recognition using timecausal and timerecursive spatiotemporal receptive fields
This work presents a first evaluation of using spatiotemporal receptive...
read it

Optimising The Input Window Alignment in CDDNN Based Phoneme Recognition for Low Latency Processing
We present a systematic analysis on the performance of a phonetic recogn...
read it

Dense scale selection over space, time and spacetime
Scale selection methods based on local extrema over scale of scalenorma...
read it

Fitting Generalized Essential Matrices from Generic 6x6 Matrices and its Applications
This paper addresses the problem of finding the closest generalized esse...
read it

A Connectedness Constraint for Learning Sparse Graphs
Graphs are naturally sparse objects that are used to study many problems...
read it

Solving illposed inverse problems using iterative deep neural networks
We propose a partially learned approach for the solution of ill posed in...
read it

Determinantal Point Processes for MiniBatch Diversification
We study a minibatch diversification scheme for stochastic gradient des...
read it

cGANbased Manga Colorization Using a Single Training Image
The Japanese comic format known as Manga is popular all over the world. ...
read it

Indirect Image Registration with Large Diffeomorphic Deformations
The paper adapts the large deformation diffeomorphic metric mapping fram...
read it

OkutamaAction: An Aerial View Video Dataset for Concurrent Human Action Detection
Despite significant progress in the development of human action detectio...
read it
KTH Royal Institute of Technology
Since its inception in 1827, KTH has developed into one of Europe's leading technical universities and an important arena for knowledge development. As Sweden's largest university for technical research and education, we bring students, researchers and faculty...