{"data":{"id":"10.6084/m9.figshare.1277822","type":"dois","attributes":{"doi":"10.6084/m9.figshare.1277822","prefix":"10.6084","suffix":"m9.figshare.1277822","identifiers":[],"alternateIdentifiers":[],"creators":[{"name":"Synnaeve, Gabriel","nameType":"Personal","givenName":"Gabriel","familyName":"Synnaeve","affiliation":[],"nameIdentifiers":[]},{"name":"Verteegh, Maarten","nameType":"Personal","givenName":"Maarten","familyName":"Verteegh","affiliation":[],"nameIdentifiers":[]},{"name":"Dupoux, Emmanuel","nameType":"Personal","givenName":"Emmanuel","familyName":"Dupoux","affiliation":[],"nameIdentifiers":[]}],"titles":[{"title":"Learning Words from Images and Speech"}],"publisher":"figshare","container":{},"publicationYear":2014,"subjects":[{"subject":"Artificial Intelligence and Image Processing"},{"subject":"FOS: Computer and information sciences","schemeUri":"http://www.oecd.org/science/inno/38235147.pdf","subjectScheme":"Fields of Science and Technology (FOS)"},{"subject":"FOS: Computer and information sciences","subjectScheme":"Fields of Science and Technology (FOS)"}],"contributors":[],"dates":[{"date":"2014-12-23","dateType":"Created"},{"date":"2014-12-23","dateType":"Updated"},{"date":"2014","dateType":"Issued"}],"language":null,"types":{"ris":"DATA","bibtex":"misc","citeproc":"dataset","schemaOrg":"Dataset","resourceType":"Dataset","resourceTypeGeneral":"Dataset"},"relatedIdentifiers":[],"relatedItems":[],"sizes":["838738 Bytes"],"formats":[],"version":null,"rightsList":[{"rights":"Creative Commons Attribution 4.0 International","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"cc-by-4.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"This paper explores the possibility to learn a semantically-relevant lexicon from images and speech only. For this, we train a multi-modal neural network working both on image fragments and on speech features, by learning an embedding in which images and content words that co-occur together are close. Making no assumption on the acoustic model, this paper shows promising results on how multi-modality could help word learning.","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"xml":"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","url":"https://figshare.com/articles/dataset/Learning_Words_from_Images_and_Speech/1277822","contentUrl":null,"metadataVersion":1,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":0,"viewsOverTime":[],"downloadCount":0,"downloadsOverTime":[],"referenceCount":0,"citationCount":0,"citationsOverTime":[],"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2014-12-23T19:02:20.000Z","registered":"2014-12-23T19:02:22.000Z","published":"2014","updated":"2020-09-04T19:49:30.000Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}},"provider":{"data":{"id":"otjm","type":"providers"}},"media":{"data":{"id":"10.6084/m9.figshare.1277822","type":"media"}},"references":{"data":[]},"citations":{"data":[]},"parts":{"data":[]},"partOf":{"data":[]},"versions":{"data":[]},"versionOf":{"data":[]}}}}