N
Noel E. O'Connor
Researcher at Dublin City University
Publications - 593
Citations - 11668
Noel E. O'Connor is an academic researcher from Dublin City University. The author has contributed to research in topics: Image processing & TRECVID. The author has an hindex of 46, co-authored 574 publications receiving 9699 citations. Previous affiliations of Noel E. O'Connor include Télécom ParisTech & Grenoble Institute of Technology.
Papers
More filters
Proceedings ArticleDOI
Shallow and Deep Convolutional Networks for Saliency Prediction
TL;DR: In this paper, the authors proposed a completely data-driven approach by training a convolutional neural network (convnet) for saliency prediction, where the learning process is formulated as a minimization of a loss function that measures the Euclidean distance of the predicted saliency map with the provided ground truth.
Proceedings Article
Unsupervised Label Noise Modeling and Loss Correction
TL;DR: A suitable two-component mixture model is suggested as an unsupervised generative model of sample loss values during training to allow online estimation of the probability that a sample is mislabelled and correct the loss by relying on the network prediction.
Journal Article
SalGAN: visual saliency prediction with generative adversarial networks
Junting Pan,Cristian Canton-Ferrer,Kevin McGuinness,Noel E. O'Connor,Jordi Torres,Elisa Sayrol,Xavier Giro-i-Nieto +6 more
TL;DR: This work introduces SalGAN, a deep convolutional neural network for visual saliency prediction trained with adversarial examples and shows how adversarial training allows reaching state-of-the-art performance across different metrics when combined with a widely-used loss function like BCE.
Journal ArticleDOI
A comparative evaluation of interactive segmentation algorithms
TL;DR: A comparative evaluation of four popular interactive segmentation algorithms using the well-known Jaccard index for measuring object accuracy and a new fuzzy metric, proposed in this paper, designed for measuring boundary accuracy, demonstrates the effectiveness of the suggested measures.
Journal ArticleDOI
A multiscale representation method for nonrigid shapes with a single closed contour
Tomasz Adamek,Noel E. O'Connor +1 more
TL;DR: The criteria that should be satisfied by a descriptor for nonrigid shapes with a single closed contour are discussed and a shape representation method that fulfills these criteria is proposed that is very efficient and invariant to several kinds of transformations.