Search Results for author: Hedvig Kjellström

Found 36 papers, 20 papers with code

Optimal transport for causal discovery

no code implementations ICLR 2022 Ruibo Tu, Kun Zhang, Hedvig Kjellström, Cheng Zhang

With this criterion, we propose a novel optimal transport-based algorithm for ANMs which is robust to the choice of models and extend it to post-nonlinear models.

Causal Discovery

Recur, Attend or Convolve? Frame Dependency Modeling Matters for Cross-Domain Robustness in Action Recognition

2 code implementations22 Dec 2021 Sofia Broomé, Ernest Pokropek, Boyu Li, Hedvig Kjellström

We find that when controlling for performance and layer structure, convolutional-recurrent models show better out-of-domain generalization ability on the Temporal Shape dataset than 3D convolution- and attention-based models.

Action Recognition Domain Generalization +1

Aligned Multi-Task Gaussian Process

no code implementations29 Oct 2021 Olga Mikheeva, Ieva Kazlauskaite, Adam Hartshorne, Hedvig Kjellström, Carl Henrik Ek, Neill D. F. Campbell

Building on the previous work by Kazlauskaiteet al. [2019], we include a separate monotonic warp of the input data to model temporal misalignment.

Bayesian Inference Gaussian Processes +2

Sharing Pain: Using Pain Domain Transfer for Video Recognition of Low Grade Orthopedic Pain in Horses

1 code implementation21 May 2021 Sofia Broomé, Katrina Ask, Maheen Rashid, Pia Haubro Andersen, Hedvig Kjellström

Moreover, we present a human expert baseline for the problem, as well as an extensive empirical study of various domain transfer methods and of what is detected by the pain recognition method trained on clean experimental pain in the orthopedic dataset.

Fine-grained Action Recognition Video Recognition

Automated Detection of Equine Facial Action Units

1 code implementation17 Feb 2021 Zhenghong Li, Sofia Broomé, Pia Haubro Andersen, Hedvig Kjellström

To automate parts of this process, we propose a Deep Learning-based method to detect EquiFACS units automatically from images.

Facial Action Unit Detection

Asymptotically Exact and Fast Gaussian Copula Models for Imputation of Mixed Data Types

1 code implementation4 Feb 2021 Benjamin Christoffersen, Mark Clements, Keith Humphreys, Hedvig Kjellström

Missing values with mixed data types is a common problem in a large number of machine learning applications such as processing of surveys and in different medical applications.


A Subjective Model of Human Decision Making Based on Quantum Decision Theory

no code implementations14 Jan 2021 Chenda Zhang, Hedvig Kjellström

Computer modeling of human decision making is of large importance for, e. g., sustainable transport, urban development, and online recommendation systems.

Decision Making Recommendation Systems

Full-Glow: Fully conditional Glow for more realistic image generation

1 code implementation10 Dec 2020 Moein Sorkhei, Gustav Eje Henter, Hedvig Kjellström

Autonomous agents, such as driverless cars, require large amounts of labeled visual data for their training.

Image Generation Object Recognition +1

How Do Fair Decisions Fare in Long-term Qualification?

1 code implementation NeurIPS 2020 Xueru Zhang, Ruibo Tu, Yang Liu, Mingyan Liu, Hedvig Kjellström, Kun Zhang, Cheng Zhang

Our results show that static fairness constraints can either promote equality or exacerbate disparity depending on the driving factor of qualification transitions and the effect of sensitive attributes on feature distributions.

Decision Making Fairness

Moving fast and slow: Analysis of representations and post-processing in speech-driven automatic gesture generation

1 code implementation16 Jul 2020 Taras Kucherenko, Dai Hasegawa, Naoshi Kaneko, Gustav Eje Henter, Hedvig Kjellström

We provide an analysis of different representations for the input (speech) and the output (motion) of the network by both objective and subjective evaluations.

Gesture Generation Representation Learning

Interpreting video features: a comparison of 3D convolutional networks and convolutional LSTM networks

2 code implementations2 Feb 2020 Joonatan Mänttäri, Sofia Broomé, John Folkesson, Hedvig Kjellström

A number of techniques for interpretability have been presented for deep learning in computer vision, typically with the goal of understanding what the networks have based their classification on.

General Classification

Bayesian nonparametric shared multi-sequence time series segmentation

no code implementations27 Jan 2020 Olga Mikheeva, Ieva Kazlauskaite, Hedvig Kjellström, Carl Henrik Ek

In this paper, we introduce a method for segmenting time series data using tools from Bayesian nonparametrics.

Time Series

Non-Parametric Calibration for Classification

1 code implementation12 Jun 2019 Jonathan Wenger, Hedvig Kjellström, Rudolph Triebel

Many applications of classification methods not only require high accuracy but also reliable estimation of predictive uncertainty.

Active Learning Classification +2

Analyzing Input and Output Representations for Speech-Driven Gesture Generation

1 code implementation arXiv 2019 Taras Kucherenko, Dai Hasegawa, Gustav Eje Henter, Naoshi Kaneko, Hedvig Kjellström

We evaluate different representation sizes in order to find the most effective dimensionality for the representation.

Gesture Generation Human-Computer Interaction I.2.6; I.5.1; J.4

Dynamics are Important for the Recognition of Equine Pain in Video

1 code implementation7 Jan 2019 Sofia Broomé, Karina Bech Gleerup, Pia Haubro Andersen, Hedvig Kjellström

Sequential models are experimentally compared to single-frame models, showing the importance of the temporal dimension of the data, and are benchmarked against a veterinary expert classification of the data.


A Hierarchical Grocery Store Image Dataset with Visual and Semantic Labels

3 code implementations3 Jan 2019 Marcus Klasson, Cheng Zhang, Hedvig Kjellström

In this paper, we provide a new benchmark dataset for a challenging task in this application - classification of fruits, vegetables, and refrigerated products, e. g. milk packages and juice cartons, in grocery stores.

Classification General Classification +1

Mixed Likelihood Gaussian Process Latent Variable Model

1 code implementation19 Nov 2018 Samuel Murray, Hedvig Kjellström

We present the Mixed Likelihood Gaussian process latent variable model (GP-LVM), capable of modeling data with attributes of different types.

Variational Inference

A Probabilistic Semi-Supervised Approach to Multi-Task Human Activity Modeling

1 code implementation24 Sep 2018 Judith Bütepage, Hedvig Kjellström, Danica Kragic

Therefore, video-based human activity modeling is concerned with a number of tasks such as inferring current and future semantic labels, predicting future continuous observations as well as imagining possible future label and feature sequences.

Action Classification General Classification +2

Simultaneous Measurement Imputation and Outcome Prediction for Achilles Tendon Rupture Rehabilitation

no code implementations8 Sep 2018 Charles Hamesse, Ruibo Tu, Paul Ackermann, Hedvig Kjellström, Cheng Zhang

However, it is challenging to train an automatic method for predicting the ATR rehabilitation outcome from treatment data, due to a massive amount of missing entries in the data recorded from ATR patients, as well as complex nonlinear relations between measurements and outcomes.


Causal Discovery in the Presence of Missing Data

1 code implementation11 Jul 2018 Ruibo Tu, Kun Zhang, Paul Ackermann, Bo Christer Bertilson, Clark Glymour, Hedvig Kjellström, Cheng Zhang

When these data entries are not missing completely at random, the (conditional) independence relations in the observed data may be different from those in the complete data generated by the underlying causal process.

Causal Discovery

A Neural Network Approach to Missing Marker Reconstruction in Human Motion Capture

1 code implementation7 Mar 2018 Taras Kucherenko, Jonas Beskow, Hedvig Kjellström

Optical motion capture systems have become a widely used technology in various fields, such as augmented reality, robotics, movie production, etc.

3D Reconstruction Missing Markers Reconstruction

Causality Refined Diagnostic Prediction

no code implementations29 Nov 2017 Marcus Klasson, Kun Zhang, Bo C. Bertilson, Cheng Zhang, Hedvig Kjellström

In this work, we explore the possibility of utilizing causal relationships to refine diagnostic prediction.

Causal Identification Decision Making

Deep representation learning for human motion prediction and classification

no code implementations CVPR 2017 Judith Bütepage, Michael Black, Danica Kragic, Hedvig Kjellström

To quantify the learned features, we use the output of different layers for action classification and visualize the receptive fields of the network units.

Action Classification Classification +4

Bridging Medical Data Inference to Achilles Tendon Rupture Rehabilitation

no code implementations7 Dec 2016 An Qu, Cheng Zhang, Paul Ackermann, Hedvig Kjellström

Imputing incomplete medical tests and predicting patient outcomes are crucial for guiding the decision making for therapy, such as after an Achilles Tendon Rupture (ATR).

Collaborative Filtering Decision Making +3

Persistent Homology for Learning Densities with Bounded Support

no code implementations NeurIPS 2012 Florian T. Pokorny, Hedvig Kjellström, Danica Kragic, Carl Ek

We present a novel method for learning densities with bounded support which enables us to incorporate `hard' topological constraints.

Density Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.