J
Jonathon S. Hare
Researcher at University of Southampton
Publications - 129
Citations - 3542
Jonathon S. Hare is an academic researcher from University of Southampton. The author has contributed to research in topics: Image retrieval & Visual Word. The author has an hindex of 26, co-authored 129 publications receiving 2692 citations.
Papers
More filters
Journal ArticleDOI
An object-based convolutional neural network (OCNN) for urban land use classification
TL;DR: The proposed OCNN framework is the first object-based convolutional neural network framework to effectively and efficiently address the complicated problem of urban land use classification from VFSR images, and was tested on aerial photography of two large urban scenes in Southampton and Manchester.
Journal ArticleDOI
Joint deep learning for land cover and land use classification
TL;DR: A set of novel deep learning methods are developed for LC and LU image classification based on the deep convolutional neural networks (CNN) as an example, which achieved by far the highest classification accuracy for both LC andLU, up to around 90% accuracy, about 5% higher than the existingDeep learning methods, and 10% greater than traditional pixel-based and object-based approaches.
Journal ArticleDOI
A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification
TL;DR: The proposed ensemble classifier MLP-CNN harvests the complementary results acquired from the CNN based on deep spatial feature representation and from the MLP based on spectral discrimination, paving the way to effectively address the complicated problem of VFSR image classification.
Proceedings Article
T-REx: A large scale alignment of natural language with knowledge base triples
Hady Elsahar,Pavlos Vougiouklis,Arslen Remaci,Christophe Gravier,Jonathon S. Hare,Frédérique Laforest,Elena Simperl +6 more
TL;DR: T-REx, a dataset of large scale alignments between Wikipedia abstracts and Wikidata triples, is presented, which is two orders of magnitude larger than the largest available alignments dataset and covers 2.5 times more predicates.
Proceedings ArticleDOI
Analyzing and predicting sentiment of images on the social web
TL;DR: This large-scale empirical study on a set of over half a million Flickr images shows a considerable correlation between sentiment and visual features, and promising results towards estimating the polarity of sentiment in images.