Inferring visual semantic similarity with deep learning and Wikidata: Introducing imagesim-353?

Research output: Contribution to journalConference article – Annual report year: 2019Researchpeer-review

Documents

View graph of relations

Aiming at multi-modal knowledge representation we construct a dataset with pairs of digital photos of objects. We manually score image pairs for semantic object similarity. A pre-trained ImageNet- based deep neural network predicts the objects and we use the output to estimate the similarity between two images. With a linkage between the neural network and Wikidata, we augment the model and incorporate knowledge graph information into the similarity measure. We compare the machine-based predicted similarity with the human-based semantic similarity.

Original languageEnglish
JournalCEUR Workshop Proceedings
Volume2106
Pages (from-to)56-61
ISSN1613-0073
Publication statusPublished - 1 Jan 2018
Event1st Workshop on Deep Learning for Knowledge Graphs and Semantic Technologies, DL4KGS 2018 - Heraklion, Crete, Greece
Duration: 4 Jun 2018 → …

Conference

Conference1st Workshop on Deep Learning for Knowledge Graphs and Semantic Technologies, DL4KGS 2018
CountryGreece
CityHeraklion, Crete
Period04/06/2018 → …

ID: 189012963