Ph-D of Florent Imbert

Defended on November 22th 2024 Design of a deep neural network architecture dedicated to handwriting synthesis from kinematic sensors of a digital pen This thesis focuses on a digital pen equipped with kinematic sensors, and its aim is to reconstruct the in-line trace of handwriting. We introduce a new processing…

Read

Ph-D of Killian Barrere

Defended on Decembre 20th 2023 Architectures de Transformer légères pour la reconnaissance de textes manuscrits anciens Transformer architectures deliver low error rates but are challenging to train due to limited annotated data in handwritten text recognition. We propose lightweight Transformer architectures to adapt to the limited amounts of annotated handwritten…

Read

Self-adaptive handwriting recognition using self-supervised learning

The aim of this thesis will be to look at self-supervised learning in order to take advantage of unsu-pervised examples for handwriting recognition. In recent years, a great deal of work has focused onself-supervised approaches for network pre-training. Starting with a pretext task that does not requiremanual annotation, the model…

Read

INTUINOTE: AN INTEGRATED DIGITAL SOLUTION TO ENCOURAGE ACTIVE LEARNING

AMI “Digital demonstrators in higher education” / AIR project- Increasing Interaction in Rennes IntuiNOTE is an integrated digital solution for higher education that encourages active learning in synchronous mode using a variety of features: handwritten annotations, quizzes allowing rich questions/answers that can be handwritten (diagrams, equations, etc.) or shared whiteboards…

Read

PhD offer (Sept. 2024): Semi-supervised learning of an intelligent tutorial system for e-education through the production of drawings/sketches

Supervisors: E. Anquetil (eric.anquetil@irisa.fr ), Professor at INSA Rennes, Shadoc team. N. Girard (nathalie.girard@irisa.fr), Lecturer at the University of Rennes, Shadoc team. Location: IRISA laboratory, Shadoc, Rennes Keywords: Intelligent Tutorial Systems, Artificial Intelligence, interpretation of semi-structured handwritten documents, two-dimensional visual grammars, sketching, pedagogy, e-education, pen- based tablets The Shadoc (formerly…

Read

Ph-D of William Mocaer

Defended on Decembre 15th 2023 Réseaux de Neurones à Convolution Spatio-Temporelle pour l’Analyse et la Reconnaissance Précoce d’Actions et de Gestes Sujet Ce travail de recherche se concentre sur la reconnaissance précoce de gestes dans le domaine de l’interaction homme-machine. Il s’inscrit dans le cadre d’une collaboration entre deux équipes…

Read

Ph-D of Martin Dornier

Defended December 14th 2023 Apprentissage par transfert pour l’analyse faciale avec des données annotées limitées et incohérentes Sujet L’apprentissage profond s’est grandement développé ces dernières années. Cependant, beaucoup des méthodes existantes reposent toujours sur l’apprentissage supervisé qui requiert des données annotées. Or, obtenir ce type de données peut se révéler…

Read

Ph-D of Arnaud Lods

Defended September 12 2023 Analyse en-ligne d’opérations arithmétiques manuscrites posées pour l’aide à l’apprentissage sur tablette numérique Abstract Cette thèse s’inscrit dans la continuité du LabCom «Script&Labs » qui porte sur l’apport de l’IA pour l’apprentissage numérique. Nous traitons la problématique de l’analyse d’opérations arithmétiques posées manuscrites réalisées sur tablette…

Read

IRISA-KIHT-S and KIHT-public Datasets

IRISA-KIHT-S and KIHT-public Datasets Contact: Florent IMBERT (florent.imbert@irisa.fr), Eric ANQUETIL (eric.anquetil@irisa.fr) Partner: STABILO, IRISA (IntuiDoc/SHADoc Team), KIT , Learn&Go, Funding : ANR Startdate: 01.10.2021 Enddate: 31.12.2024 Links SHADoc team ex Intuidoc team Project webpage   Download the IRISA-KIHT-S Dataset   Download the KIHT-public Dataset   Digital devices can help pupils…

Read