Search Results for author: Martin Längkvist

Found 4 papers, 0 papers with code

Learning Generative Image Object Manipulations from Language Instructions

no code implementations ICLR 2020 Martin Längkvist, Andreas Persson, Amy Loutfi

The use of adequate feature representations is essential for achieving high performance in high-level human cognitive tasks in computational modeling.

Object

Semantic Referee: A Neural-Symbolic Framework for Enhancing Geospatial Semantic Segmentation

no code implementations30 Apr 2019 Marjan Alirezaie, Martin Längkvist, Michael Sioutis, Amy Loutfi

Understanding why machine learning algorithms may fail is usually the task of the human expert that uses domain knowledge and contextual information to discover systematic shortcomings in either the data or the algorithm.

BIG-bench Machine Learning Semantic Segmentation

Interactive user interface based on Convolutional Auto-encoders for annotating CT-scans

no code implementations26 Apr 2019 Martin Längkvist, Jonas Widell, Per Thunberg, Amy Loutfi, Mats Lidén

It was discovered that the experienced usability and how the users interactied with the system differed between the users.

Semantic Segmentation

A Deep Learning Approach with an Attention Mechanism for Automatic Sleep Stage Classification

no code implementations14 May 2018 Martin Längkvist, Amy Loutfi

Automatic sleep staging is a challenging problem and state-of-the-art algorithms have not yet reached satisfactory performance to be used instead of manual scoring by a sleep technician.

Automatic Sleep Stage Classification Dimensionality Reduction +2

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