Lüddecke, Timo

[["dc.bibliographiccitation.firstpage","44"],["dc.bibliographiccitation.journal","Artificial Intelligence"],["dc.bibliographiccitation.lastpage","65"],["dc.bibliographiccitation.volume","274"],["dc.contributor.author","Lüddecke, Timo"],["dc.contributor.author","Agostini, Alejandro"],["dc.contributor.author","Fauth, Michael"],["dc.contributor.author","Tamosiunaite, Minija"],["dc.contributor.author","Wörgötter, Florentin"],["dc.date.accessioned","2019-07-15T08:04:50Z"],["dc.date.available","2019-07-15T08:04:50Z"],["dc.date.issued","2019"],["dc.description.abstract","The distributional hypothesis states that the meaning of a concept is defined through the contexts it occurs in. In practice, often word co-occurrence and proximity are analyzed in text corpora for a given word to obtain a real-valued semantic word vector, which is taken to (at least partially) encode the meaning of this word. Here we transfer this idea from text to images, where pre-assigned labels of other objects or activations of convolutional neural networks serve as context. We propose a simple algorithm that extracts and processes object contexts from an image database and yields semantic vectors for objects. We show empirically that these representations exhibit on par performance with state-of-the-art distributional models over a set of conventional objects. For this we employ well-known word benchmarks in addition to a newly proposed object-centric benchmark."],["dc.identifier.doi","10.1016/j.artint.2018.12.009"],["dc.identifier.purl","https://resolver.sub.uni-goettingen.de/purl?gs-1/16274"],["dc.identifier.uri","https://resolver.sub.uni-goettingen.de/purl?gro-2/61490"],["dc.language.iso","en"],["dc.notes.intern","Merged from goescholar"],["dc.notes.status","final"],["dc.relation","info:eu-repo/grantAgreement/EC/H2020/731761/EU//IMAGINE"],["dc.relation.issn","0004-3702"],["dc.relation.orgunit","Fakultät für Physik"],["dc.rights","CC BY-NC-ND 4.0"],["dc.rights.uri","https://creativecommons.org/licenses/by-nc-nd/4.0/"],["dc.title","Distributional semantics of objects in visual scenes in comparison to text"],["dc.type","journal_article"],["dc.type.internalPublication","yes"],["dc.type.version","published_version"],["dspace.entity.type","Publication"]]