Please use this identifier to cite or link to this item:
Type of publication: Straipsnis Clarivate Analytics Web of Science ar/ir Scopus / Article in Clarivate Analytics Web of Science or / and Scopus (S1)
Field of Science: Informatika / Computer science (N009)
Author(s): Lüddecke, Timo;Agostini, Alejandro;Fauth, Michael;Wörgötter, Florentin;Tamošiūnaitė, Minija
Title: Distributional semantics of objects in visual scenes in comparison to text
Is part of: Artificial intelligence: an international journal. Amsterdam : Elsevier B.V, 2019, vol. 274
Extent: p. 44-65
Date: 2019
Keywords: Computer Science;Object semantics;Semantics;Distributional hypothesis
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
Affiliation(s): Informatikos fakultetas
Taikomosios informatikos katedra
Vytauto Didžiojo universitetas
Appears in Collections:Universiteto mokslo publikacijos / University Research Publications

Files in This Item:
marc.xml8.4 kBXMLView/Open

MARC21 XML metadata

Show full item record

Page view(s)

checked on Aug 17, 2019

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.