arXiv subjects

Adrien Deliège

Publications and source records attributed to Adrien Deliège.

21 records · Page 2Linked to original sources

arXiv2020

A Context-Aware Loss Function for Action Spotting in Soccer Videos

In video understanding, action spotting consists in temporally localizing human-induced events annotated with single timestamps. In this paper, we propose a novel loss function that specifically considers the temporal context naturally present around each action, rather than focusing on the single annotated frame to spot. We benchmark our loss on a large dataset of soccer videos, SoccerNet, and achieve an improvement of 12.8% over the baseline. We show the generalization capability of our loss for generic activity proposals and detection on ActivityNet, by spotting the beginning and the end of each activity. Furthermore, we provide an extended ablation study and display challenging cases for action spotting in soccer videos. Finally, we qualitatively illustrate how our loss induces a precise temporal understanding of actions and show how such semantic knowledge can be used for automatic highlights generation.

cs.CV↗

arXiv2018

HitNet: a neural network with capsules embedded in a Hit-or-Miss layer, extended with hybrid data augmentation and ghost capsules

Neural networks designed for the task of classification have become a commodity in recent years. Many works target the development of better networks, which results in a complexification of their architectures with more layers, multiple sub-networks, or even the combination of multiple classifiers. In this paper, we show how to redesign a simple network to reach excellent performances, which are better than the results reproduced with CapsNet on several datasets, by replacing a layer with a Hit-or-Miss layer. This layer contains activated vectors, called capsules, that we train to hit or miss a central capsule by tailoring a specific centripetal loss function. We also show how our network, named HitNet, is capable of synthesizing a representative sample of the images of a given class by including a reconstruction network. This possibility allows to develop a data augmentation step combining information from the data space and the feature space, resulting in a hybrid data augmentation process. In addition, we introduce the possibility for HitNet, to adopt an alternative to the true target when needed by using the new concept of ghost capsules, which is used here to detect potentially mislabeled images in the training data.

cs.CV↗

arXiv2014

Monofractal nature of air temperature signals reveals their climate variability

We use the discrete "wavelet transform microscope" to show that the surface air temperature signals of weather stations selected in Europe are monofractal. This study reveals that the information obtained in this way are richer than previous works studying long range correlations in meteorological stations. The approach presented here allows to bind the Hölder exponents with the climate variability. We also establish that such a link does not exist with methods previously carried out.

physics.data-an↗