Événements du LITIS

Chargement Évènements

« Tous les Évènements

  • Cet évènement est passé

séminaire Deep Learning for Human Motion par Chrisitian Wolf

11/24/2016 @ 14:00 - 12/25/2016 @ 18:00

Le jeudi 24 novembre se tiendra à 14h un séminaire intitulé Deep Learning for Human Motion par Christian Wolf.

Titre : « Deep Learning for Human Motion » *
*
*
*Abstract :*
/We will first present a very brief introduction into common deep models for computer vision like convolutional neural networks and recurrent networks, and the main challenges of the field./

/The second part is devoted to develop learning methods advancing automatic analysis and interpreting of human motion from different perspectives and based on various sources of information, such as images, video, depth, mocap data, audio and inertial sensors. We propose several models and associated training algorithms for supervised classification and semi-supervised and weakly-supervised feature learning, as well as modelling of temporal dependencies, and show their efficiency on a set of fundamental tasks, including detection, classification, parameter estimation and user verification. /

/Advances in several applications will be shown, including (i) gesture spotting and recognition based on multi-scale and multi-modal deep learning from visual signals (such as video, depth and mocap data), where we will present a training strategy for learning cross-modality correlations while preserving uniqueness of each modality-specific representation; (ii) hand pose estimation through deep regression from depth images, based on semi-supervised and weakly-supervised learning; (iii) mobile biometrics, in particular the automatic authentification of smartphone users through deep learning from data acquired from inertiel sensors./

Détails

Début :
11/24/2016 @ 14:00
Fin :
12/25/2016 @ 18:00

Organisateur

Alain Rakotomamonjy
E-mail :
alain.rakoto@univ-rouen.fr

Lieu

voir avec Alain Rakotomamonjy
Publié dans
felis ut eget quis, felis nunc venenatis Curabitur vel, mattis