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…
PhD student: Florent Meyer Supervisors: Bertrand Coüasnon, Yann Soullard and Guillaume Gravier Funding: CIFRE grant with ANTAI
Doctorant : Islam BARCHOUCH Encadrants :E. Anquetil (eric.anquetil@irisa.fr), Prof. à l’INSA de Rennes, Responsable de l’équipe IntuiDoc.N. Girard (nathalie.girard@irisa.fr), MC Univ. Rennes 1, équipe IntuiDoc. Lieu : laboratoire IRISA, IntuiDoc, Rennes Mots-clés : systèmes tutoriels intelligents, interprétation de documents manuscrits semi-structurés, tablettes orientées stylet, grammaires visuelles, croquis, Intelligence Artificielle, médecine, anatomie, pédagogie,…
