W
Wesley De Neve
Researcher at Ghent University
Publications - 188
Citations - 2430
Wesley De Neve is an academic researcher from Ghent University. The author has contributed to research in topics: Scalable Video Coding & Bitstream. The author has an hindex of 22, co-authored 179 publications receiving 1941 citations. Previous affiliations of Wesley De Neve include KAIST & Information and Communications University.
Papers
More filters
Proceedings ArticleDOI
Using topic models for Twitter hashtag recommendation
TL;DR: This paper proposes a novel method for unsupervised and content-based hashtag recommendation for tweets that relies on Latent Dirichlet Allocation (LDA) to model the underlying topic assignment of language classified tweets.
Proceedings ArticleDOI
Multimedia Lab $@$ ACL WNUT NER Shared Task: Named Entity Recognition for Twitter Microposts using Distributed Word Representations
TL;DR: A semisupervised system that detects 10 types of named entities that achieved the fourth position in the final ranking, without using any kind of hand-crafted features such as lexical features or gazetteers.
Journal ArticleDOI
Indoor Person Identification Using a Low-Power FMCW Radar
Baptist Vandersmissen,Nicolas Knudde,Azarakhsh Jalalvand,Ivo Couckuyt,Andre Bourdoux,Wesley De Neve,Tom Dhaene +6 more
TL;DR: This paper investigates the use of micro-Doppler signatures retrieved from a low-power radar device to identify a set of persons based on their gait characteristics and proposes a robust feature learning approach based on deep convolutional neural networks.
Proceedings ArticleDOI
Hyperspectral Image Classification with Convolutional Neural Networks
TL;DR: A feature learning approach for hyperspectral image classification based on convolutional neural networks (CNNs) that is able to learn structured features, roughly resembling different spectral band-pass filters, directly from the hyperspectrals input data.
Journal ArticleDOI
SpliceRover: interpretable convolutional neural networks for improved splice site prediction
TL;DR: This paper presents SpliceRover, a predictive deep learning approach that outperforms the state‐of‐the‐art in splice site prediction, and introduces an approach to visualize the biologically relevant information learnt that is able to recover features known to be important for splicing site prediction.