Linköping University

research

∙ 12/07/2020

Learning Video Instance Segmentation with Recurrent Graph Neural Networks

Most existing approaches to video instance segmentation comprise multipl...

Joakim Johnander, et al. ∙

research

∙ 02/13/2021

Normalized Convolution Upsampling for Refined Optical Flow Estimation

Optical flow is a regression task where convolutional neural networks (C...

Abdelrahman Eldesokey, et al. ∙

research

∙ 06/13/2022

Estimating Causal Effects Under Image Confounding Bias with an Application to Poverty in Africa

Observational studies of causal effects require adjustment for confoundi...

Connor T. Jerzak, et al. ∙

research

∙ 07/31/2022

Repairing ℰℒ Ontologies Using Weakening and Completing

The quality of ontologies in terms of their correctness and completeness...

Ying Li, et al. ∙

research

∙ 05/15/2020

Enhancing Lattice-based Motion Planning with Introspective Learning and Reasoning

Lattice-based motion planning is a hybrid planning method where a plan m...

Mattias Tiger, et al. ∙

research

∙ 01/08/2019

Graphical model inference: Sequential Monte Carlo meets deterministic approximations

Approximate inference in probabilistic graphical models (PGMs) can be gr...

Fredrik Lindsten, et al. ∙

research

∙ 02/27/2019

Single-frame Regularization for Temporally Stable CNNs

Convolutional neural networks (CNNs) can model complicated non-linear re...

Gabriel Eilertsen, et al. ∙

research

∙ 03/21/2020

Multi-Robot Association-Path Planning in Millimeter-Wave Industrial Scenarios

The massive exploitation of robots for industry 4.0 needs advanced wirel...

Cristian Tatino, et al. ∙

research

∙ 04/18/2017

Benchmarking OpenCL, OpenACC, OpenMP, and CUDA: programming productivity, performance, and energy consumption

Many modern parallel computing systems are heterogeneous at their node l...

Suejb Memeti, et al. ∙

research

∙ 08/29/2017

Unifying DAGs and UGs

We introduce a new class of graphical models that generalizes Lauritzen-...

Jose M. Peña, et al. ∙

research

∙ 10/20/2017

HDR image reconstruction from a single exposure using deep CNNs

Camera sensors can only capture a limited range of luminance simultaneou...

Gabriel Eilertsen, et al. ∙

research

∙ 10/17/2017

Procedural Modeling and Physically Based Rendering for Synthetic Data Generation in Automotive Applications

We present an overview and evaluation of a new, systematic approach for ...

Apostolia Tsirikoglou, et al. ∙

research

∙ 12/22/2016

Causal Effect Identification in Acyclic Directed Mixed Graphs and Gated Models

We introduce a new family of graphical models that consists of graphs wi...

Jose M. Peña, et al. ∙

research

∙ 12/04/2016

Representing Independence Models with Elementary Triplets

In an independence model, the triplets that represent conditional indepe...

Jose M. Peña, et al. ∙

research

∙ 12/29/2016

High-dimensional Filtering using Nested Sequential Monte Carlo

Sequential Monte Carlo (SMC) methods comprise one of the most successful...

Christian A. Naesseth, et al. ∙

research

∙ 03/15/2017

Joint Epipolar Tracking (JET): Simultaneous optimization of epipolar geometry and feature correspondences

Traditionally, pose estimation is considered as a two step problem. Firs...

Henry Bradler, et al. ∙

research

∙ 11/18/2015

Alternative Markov and Causal Properties for Acyclic Directed Mixed Graphs

We extend Andersson-Madigan-Perlman chain graphs by (i) relaxing the sem...

Jose M. Peña, et al. ∙

research

∙ 10/08/2015

Data-Efficient Learning of Feedback Policies from Image Pixels using Deep Dynamical Models

Data-efficient reinforcement learning (RL) in continuous state-action sp...

John-Alexander M. Assael, et al. ∙

research

∙ 01/31/2016

DOLDA - a regularized supervised topic model for high-dimensional multi-class regression

Generating user interpretable multi-class predictions in data rich envir...

Måns Magnusson, et al. ∙

research

∙ 11/17/2015

Accelerating pseudo-marginal Metropolis-Hastings by correlating auxiliary variables

Pseudo-marginal Metropolis-Hastings (pmMH) is a powerful method for Baye...

Johan Dahlin, et al. ∙

research

∙ 10/05/2015

Bayesian Inference via Approximation of Log-likelihood for Priors in Exponential Family

In this paper, a Bayesian inference technique based on Taylor series app...

Tohid Ardeshiri, et al. ∙

research

∙ 08/18/2016

Efficient Multi-Frequency Phase Unwrapping using Kernel Density Estimation

In this paper we introduce an efficient method to unwrap multi-frequency...

Felix Järemo Lawin, et al. ∙

research

∙ 06/28/2013

Error AMP Chain Graphs

Any regular Gaussian probability distribution that can be represented by...

Jose M. Peña, et al. ∙

research

∙ 08/12/2016

Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking

Discriminative Correlation Filters (DCF) have demonstrated excellent per...

Martin Danelljan, et al. ∙

research

∙ 08/22/2015

Gaussian Mixture Reduction Using Reverse Kullback-Leibler Divergence

We propose a greedy mixture reduction algorithm which is capable of prun...

Tohid Ardeshiri, et al. ∙

research

∙ 03/04/2013

Learning AMP Chain Graphs and some Marginal Models Thereof under Faithfulness: Extended Version

This paper deals with chain graphs under the Andersson-Madigan-Perlman (...

Jose M. Peña, et al. ∙

research

∙ 01/30/2013

Approximate Counting of Graphical Models Via MCMC Revisited

In Peña (2007), MCMC sampling is applied to approximately calculate the ...

Jose M. Peña, et al. ∙

research

∙ 02/12/2015

Quasi-Newton particle Metropolis-Hastings

Particle Metropolis-Hastings enables Bayesian parameter inference in gen...

Johan Dahlin, et al. ∙

research

∙ 02/12/2015

Newton-based maximum likelihood estimation in nonlinear state space models

Maximum likelihood (ML) estimation using Newton's method in nonlinear st...

Manon Kok, et al. ∙

research

∙ 02/06/2015

Marginalizing Gaussian Process Hyperparameters using Sequential Monte Carlo

Gaussian process regression is a popular method for non-parametric proba...

Andreas Svensson, et al. ∙

research

∙ 11/02/2012

Parameterized Complexity and Kernel Bounds for Hard Planning Problems

The propositional planning problem is a notoriously difficult computatio...

Christer Bäckström, et al. ∙

research

∙ 11/20/2014

Maximum Entropy Kernels for System Identification

A new nonparametric approach for system identification has been recently...

Francesca Paola Carli, et al. ∙

research

∙ 08/13/2012

The Complexity of Planning Revisited - A Parameterized Analysis

The early classifications of the computational complexity of planning un...

Christer Baeckstroem, et al. ∙

research

∙ 01/29/2016

Efficient Robust Mean Value Calculation of 1D Features

A robust mean value is often a good alternative to the standard mean val...

Erik Jonsson, et al. ∙

research

∙ 04/24/2012

Learning AMP Chain Graphs under Faithfulness

This paper deals with chain graphs under the alternative Andersson-Madig...

Jose M. Peña, et al. ∙

research

∙ 04/16/2014

Speeding Up MCMC by Efficient Data Subsampling

We propose Subsampling MCMC, a Markov Chain Monte Carlo (MCMC) framework...

Matias Quiroz, et al. ∙

research

∙ 01/03/2014

Particle Gibbs with Ancestor Sampling

Particle Markov chain Monte Carlo (PMCMC) is a systematic way of combini...

Fredrik Lindsten, et al. ∙

research

∙ 09/25/2011

Towards Optimal Learning of Chain Graphs

In this paper, we extend Meek's conjecture (Meek 1997) from directed and...

Jose M. Peña, et al. ∙

research

∙ 12/10/2013

Every LWF and AMP chain graph originates from a set of causal models

This paper aims at justifying LWF and AMP chain graphs by showing that t...

Jose M. Peña, et al. ∙

research

∙ 01/10/2011

Finding Consensus Bayesian Network Structures

Suppose that multiple experts (or learning algorithms) provide us with a...

Jose M. Peña, et al. ∙

research

∙ 06/12/2013

Bayesian Inference and Learning in Gaussian Process State-Space Models with Particle MCMC

State-space models are successfully used in many areas of science, engin...

Roger Frigola, et al. ∙

research

∙ 10/21/2010

Reading Dependencies from Covariance Graphs

The covariance graph (aka bi-directed graph) of a probability distributi...

Jose M. Peña, et al. ∙

research

∙ 06/20/2009

Hybrid Rules with Well-Founded Semantics

A general framework is proposed for integration of rules and external fi...

W. Drabent, et al. ∙

research

∙ 10/25/2012

Ancestor Sampling for Particle Gibbs

We present a novel method in the family of particle MCMC methods that we...

Fredrik Lindsten, et al. ∙

research

∙ 06/27/2014

3D planar patch extraction from stereo using probabilistic region growing

This article presents a novel 3D planar patch extraction method using a ...

Vasileios Zografos, et al. ∙

research

∙ 06/24/2014

Saccadic Eye Movements and the Generalized Pareto Distribution

We describe a statistical analysis of the eye tracker measurements in a ...

Reiner Lenz, et al. ∙

research

∙ 08/13/2010

Faithfulness in Chain Graphs: The Gaussian Case

This paper deals with chain graphs under the classic Lauritzen-Wermuth-F...

Jose M. Peña, et al. ∙

research

∙ 08/22/2013

A Unified Framework for Multi-Sensor HDR Video Reconstruction

One of the most successful approaches to modern high quality HDR-video c...

Joel Kronander, et al. ∙

research

∙ 12/09/2010

Sparse motion segmentation using multiple six-point consistencies

We present a method for segmenting an arbitrary number of moving objects...

Vasileios Zografos, et al. ∙

research

∙ 04/06/2012

Efficient computational noise in GLSL

We present GLSL implementations of Perlin noise and Perlin simplex noise...

Ian McEwan, et al. ∙

Linköping University

Featured Researchers