The Role of Graduality for Referring Expression Generation in Visual Scenes - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

The Role of Graduality for Referring Expression Generation in Visual Scenes

Résumé

Referring Expression Generation (reg) algorithms, a core component of systems that generate text from non-linguistic data, seek to identify domain objects using natural language descriptions. While reg has often been applied to visual domains, very few approaches deal with the problem of fuzziness and gradation. This paper discusses these problems and how they can be accommodated to achieve a more realistic view of the task of referring to objects in visual scenes.
Fichier principal
Vignette du fichier
jointipmu2016.pdf (381.55 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01334785 , version 1 (21-06-2016)

Identifiants

Citer

Albert Gatt, Nicolás Marín, François Portet, Daniel Sánchez. The Role of Graduality for Referring Expression Generation in Visual Scenes. Information Processing and Management of Uncertainty in Knowledge-Based Systems, Jun 2016, Eindhoven, Netherlands. pp.191--203, ⟨10.1007/978-3-319-40596-4_17⟩. ⟨hal-01334785⟩
148 Consultations
142 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More