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

Finn Årup Nielsen, Lars Kai Hansen

AbstractAiming 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.
Keywordsdeep learning, knowledge graph, Wikidata, semantic similarity, visual similarity, visual semantic similarity
TypeConference paper [With referee]
ConferenceDL4KGS
Year2018    Month April
PublisherDepartment of Applied Mathmatics and Computer Science, Technical University of Denmark
AddressBuilding 321, DK-2800 Kgs. Lyngby
Electronic version(s)[pdf]
BibTeX data [bibtex]
IMM Group(s)Intelligent Signal Processing


Back  ::  IMM Publications