Show simple item record

dc.contributor.authorBernardi, Raffaella
dc.contributor.authorCakıcı, Ruket
dc.contributor.authorElliott, Desmond
dc.contributor.authorErdem, Aykut
dc.contributor.authorErdem, Erkut
dc.contributor.authorIkizler-Cinbis, Nazli
dc.contributor.authorKeller, Frank
dc.contributor.authorMuscat, Adrian
dc.contributor.authorPlank, Barbara
dc.date.accessioned2019-12-13T06:51:43Z
dc.date.available2019-12-13T06:51:43Z
dc.date.issued2016
dc.identifier.issn1076-9757
dc.identifier.urihttps://doi.org/10.1613/jair.4900
dc.identifier.urihttp://hdl.handle.net/11655/18667
dc.description.abstractAutomatic description generation from natural images is a challenging problem that has recently received a large amount of interest from the computer vision and natural language processing communities. In this survey, we classify the existing approaches based on how they conceptualize this problem, viz., models that cast description as either generation problem or as a retrieval problem over a visual or multimodal representational space. We provide a detailed review of existing models, highlighting their advantages and disadvantages. Moreover, we give an overview of the benchmark image datasets and the evaluation measures that have been developed to assess the quality of machine-generated image descriptions. Finally we extrapolate future directions in the area of automatic image description generation.
dc.language.isoen
dc.publisherAi Access Foundation
dc.relation.isversionof10.1613/jair.4900
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectComputer Science
dc.titleAutomatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures
dc.typeinfo:eu-repo/semantics/article
dc.typeinfo:eu-repo/semantics/publishedVersion
dc.relation.journalJournal Of Artificial Intelligence Research
dc.contributor.departmentBilgisayar Mühendisliği
dc.identifier.volume55
dc.identifier.startpage409
dc.identifier.endpage442
dc.indexingWoS


Files in this item

This item appears in the following Collection(s)

Show simple item record