News
Countless columns
You can also set the number of columns per row and much more from the theme settings.
Responsive Design
~ Font Fiesta ~
Layouts and Templates
Socials Galore
HTML5 + CSS3
Séminaire: Structure pour modéliser l’activité, Nicolas Bloyet
Démo: outil d’annotation de vidéos, Cédric Fayet
Talk: Analyse sémantique en Frames, Gabriel Marzinotto
Talk: Encore des mots, toujours des mots : de la détection de dates d’évènements aux paroles de chansons, Rémi Kessler
Talk : Apprentissage incrémental de modèles de domaine par interaction dialogique, Vincent Letard
Best paper award at TALN 2017
Désolé, cet article est seulement disponible en English. The paper of Raheel Qader, Gwénolé Lecorvé, Damien Lolive, and Pascale Sébillot on speech disfluencies got rewarded by the Best Paper Award at the conference TALN 2017, held in Orléans (France) in June. The paper can be accessed here: https://hal.inria.fr/hal-01532031/file/disfluency-generation.pdf.
Séminaire au vert : 8-9 juin
Programme Orateur invité : Laurent Amsaleg (IRISA/CNRS, team LinkMedia, « Indexation multidimensionnelle et recherches par similarité : grande échelle, vitesse, qualité ». Orateurs : Pamela Carreno, Antoine Perquin, Raheel Qader, Aghilas Sini, Cédric Fayet, Rémy Kessler, Ahmad Alaa Eddine, Stefania Pecòre. Démo : Claude Simon, Damien Lolive.
Dana Kulic Seminar, Motion analysis and segmentation, April the 28th.
Désolé, cet article est seulement disponible en English. Dana’s work, as lead of the Adaptive Systems Laboratory at the University of Waterloo, CA, has focused on the analysis of human movement in a variety of applications, including human-robot interaction, rehabilitation and sports training, and interactive architectural and sculptural installations.
PhD defense : Marc Dupont: Glove-based gesture recognition for real-time outdoors robot control, 28th March, 2017.
Désolé, cet article est seulement disponible en English. Although gesture recognition has been studied for several decades, much research stays in the realm of indoors laboratory experiments. In this thesis, we address the problem of designing a truly usable, real- world gesture recognition system, focusing mainly on the real-time control…
PhD defense : Raheel Qader: Pronunciation and disfluency modeling for expressive speech synthesis, 31st March, 2017.
Désolé, cet article est seulement disponible en English. In this thesis, we address the problem of expressivity in Text-To-Speech (TTS) by incorporating two phenomena with a high impact on speech: pronunciation variants and speech disfluencies. In the first part of this thesis, we present a pronunciation variant generation method which…