98 citations · 163 across the 13 of their papers we have counts for
19 papers
Combining geolocation and height estimation of objects from street level imagery
Matej Ulicny, Vladimir A. Krylov, Julie Connelly +1
We propose a pipeline for combined multi-class object geolocation and height estimation from street level RGB imagery, which is considered as a single available input data modality…
Model-based inexact graph matching on top of CNNs for semantic scene understanding
Jérémy Chopin, Jean-Baptiste Fasquel, Harold Mouchère +2
Deep learning based pipelines for semantic segmentation often ignore structural information available on annotated images used for training. We propose a novel post-processing modu…
Principal Component Classification
Rozenn Dahyot
We propose to directly compute classification estimates by learning features encoded with their class scores using PCA. Our resulting model has a encoder-decoder structure suitable…
DR-VNet: Retinal Vessel Segmentation via Dense Residual UNet
Ali Karaali, Rozenn Dahyot, Donal J. Sexton
Accurate retinal vessel segmentation is an important task for many computer-aided diagnosis systems. Yet, it is still a challenging problem due to the complex vessel structures of…
3D point cloud segmentation using GIS
Chao-Jung Liu, Vladimir Krylov, Rozenn Dahyot
In this paper we propose an approach to perform semantic segmentation of 3D point cloud data by importing the geographic information from a 2D GIS layer (OpenStreetMap). The propos…
Context Aware Object Geotagging
Chao-Jung Liu, Matej Ulicny, Michael Manzke +1
Localization of street objects from images has gained a lot of attention in recent years. We propose an approach to improve asset geolocation from street view imagery by enhancing…
Sliced Distance for Colour Grading
Hana Alghamdi, Rozenn Dahyot
We propose a new method with distance that maps one -dimensional distribution to another, taking into account available information about correspondences. We sol…
Tensor Reordering for CNN Compression
Matej Ulicny, Vladimir A. Krylov, Rozenn Dahyot
We show how parameter redundancy in Convolutional Neural Network (CNN) filters can be effectively reduced by pruning in spectral domain. Specifically, the representation extracted…
Iterative Nadaraya-Watson Distribution Transfer for Colour Grading
Hana Alghamdi, Rozenn Dahyot
We propose a new method with Nadaraya-Watson that maps one N-dimensional distribution to another taking into account available information about correspondences. We extend the 2D/3…
Patch based Colour Transfer using SIFT Flow
Hana Alghamdi, Rozenn Dahyot
We propose a new colour transfer method with Optimal Transport (OT) to transfer the colour of a sourceimage to match the colour of a target image of the same scene that may exhibit…
Performance-Oriented Neural Architecture Search
Andrew Anderson, Jing Su, Rozenn Dahyot +1
Hardware-Software Co-Design is a highly successful strategy for improving performance of domain-specific computing systems. We argue for the application of the same methodology to…
Harmonic Convolutional Networks based on Discrete Cosine Transform
Matej Ulicny, Vladimir A. Krylov, Rozenn Dahyot
Convolutional neural networks (CNNs) learn filters in order to capture local correlation patterns in feature space. We propose to learn these filters as combinations of preset spec…
Entropic Regularisation of Robust Optimal Transport
Rozenn Dahyot, Hana Alghamdi, Mairead Grogan
Grogan et al [11,12] have recently proposed a solution to colour transfer by minimising the Euclidean distance L2 between two probability density functions capturing the colour dis…
Harmonic Networks with Limited Training Samples
Matej Ulicny, Vladimir A. Krylov, Rozenn Dahyot
Convolutional neural networks (CNNs) are very popular nowadays for image processing. CNNs allow one to learn optimal filters in a (mostly) supervised machine learning context. Howe…
Bonseyes AI Pipeline -- bringing AI to you. End-to-end integration of data, algorithms and deployment tools
Miguel de Prado, Jing Su, Rabia Saeed +9
Next generation of embedded Information and Communication Technology (ICT) systems are collaborative systems able to perform autonomous tasks. The remarkable expansion of the embed…
Harmonic Networks: Integrating Spectral Information into CNNs
Matej Ulicny, Vladimir A. Krylov, Rozenn Dahyot
Convolutional neural networks (CNNs) learn filters in order to capture local correlation patterns in feature space. In contrast, in this paper we propose harmonic blocks that produ…
Shape Registration with Directional Data
Mairéad Grogan, Rozenn Dahyot
We propose several cost functions for registration of shapes encoded with Euclidean and/or non-Euclidean information (unit vectors). Our framework is assessed for estimation of bot…
Automatic Discovery and Geotagging of Objects from Street View Imagery
Vladimir A. Krylov, Eamonn Kenny, Rozenn Dahyot
Many applications such as autonomous navigation, urban planning and asset monitoring, rely on the availability of accurate information about objects and their geolocations. In this…
Robust Registration of Gaussian Mixtures for Colour Transfer
Mairéad Grogan, Rozenn Dahyot
We present a flexible approach to colour transfer inspired by techniques recently proposed for shape registration. Colour distributions of the palette and target images are modelle…