The Role of Graduality for Referring Expression Generation in Visual Scenes

Abstract : 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.
Liste complète des métadonnées

Cited literature [48 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01334785
Contributor : François Portet <>
Submitted on : Tuesday, June 21, 2016 - 1:30:54 PM
Last modification on : Monday, February 11, 2019 - 4:36:02 PM

File

jointipmu2016.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

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⟩

Share

Metrics

Record views

263

Files downloads

108