{"id":"https://openalex.org/W2796315435","doi":"https://doi.org/10.1007/s11263-019-01205-0","title":"Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input","display_name":"Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input","publication_year":2019,"publication_date":"2019-08-05","ids":{"openalex":"https://openalex.org/W2796315435","doi":"https://doi.org/10.1007/s11263-019-01205-0","mag":"2796315435"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-019-01205-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11263-019-01205-0","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/1721.1/123476","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004717608","display_name":"David Harwath","orcid":"https://orcid.org/0000-0003-0206-0253"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"David Harwath","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0206-0253","affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020406406","display_name":"Adri\u00e0 Recasens","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adri\u00e0 Recasens","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019293578","display_name":"D\u00eddac Sur\u00eds","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D\u00eddac Sur\u00eds","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008420109","display_name":"Galen Chuang","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Galen Chuang","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085020955","display_name":"Antonio Torralba","orcid":"https://orcid.org/0000-0003-4915-0256"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonio Torralba","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5004717608"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":null,"fwci":5.9225,"has_fulltext":false,"cited_by_count":68,"citation_normalized_percentile":{"value":0.96949682,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"128","issue":"3","first_page":"620","last_page":"641"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8509058952331543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6574192047119141},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5332880616188049},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5320326685905457},{"id":"https://openalex.org/keywords/associative-property","display_name":"Associative property","score":0.48418381810188293},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.46813759207725525},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46274545788764954},{"id":"https://openalex.org/keywords/visual-objects","display_name":"Visual Objects","score":0.4603578448295593},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4581001102924347},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43352049589157104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8509058952331543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6574192047119141},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5332880616188049},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5320326685905457},{"id":"https://openalex.org/C159423971","wikidata":"https://www.wikidata.org/wiki/Q177251","display_name":"Associative property","level":2,"score":0.48418381810188293},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.46813759207725525},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46274545788764954},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.4603578448295593},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4581001102924347},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43352049589157104},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s11263-019-01205-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11263-019-01205-0","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/123476","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/123476","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv","raw_type":"http://purl.org/eprint/type/ConferencePaper"},{"id":"pmh:oai:dspace.mit.edu:1721.1/131515","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/131515","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Springer US","raw_type":"Article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/131515.2","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/131515.2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Springer US","raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/123476","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/123476","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv","raw_type":"http://purl.org/eprint/type/ConferencePaper"},"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320315934","display_name":"Toyota Research Institute","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":87,"referenced_works":["https://openalex.org/W30845872","https://openalex.org/W343636949","https://openalex.org/W1488163396","https://openalex.org/W1514535095","https://openalex.org/W1545920196","https://openalex.org/W1586079445","https://openalex.org/W1686810756","https://openalex.org/W1796128977","https://openalex.org/W1836465849","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1919709169","https://openalex.org/W1931639407","https://openalex.org/W1933349210","https://openalex.org/W2057007397","https://openalex.org/W2095897464","https://openalex.org/W2100768664","https://openalex.org/W2102605133","https://openalex.org/W2107917162","https://openalex.org/W2112301665","https://openalex.org/W2112796928","https://openalex.org/W2114347655","https://openalex.org/W2117539524","https://openalex.org/W2123081785","https://openalex.org/W2127589108","https://openalex.org/W2132921748","https://openalex.org/W2133324800","https://openalex.org/W2134670479","https://openalex.org/W2142192571","https://openalex.org/W2151498684","https://openalex.org/W2154093685","https://openalex.org/W2163605009","https://openalex.org/W2167828171","https://openalex.org/W2179022885","https://openalex.org/W2295107390","https://openalex.org/W2295297373","https://openalex.org/W2346626577","https://openalex.org/W2347098582","https://openalex.org/W2404799143","https://openalex.org/W2468716020","https://openalex.org/W2483390977","https://openalex.org/W2511428026","https://openalex.org/W2531381952","https://openalex.org/W2544224704","https://openalex.org/W2556930864","https://openalex.org/W2558809543","https://openalex.org/W2586148577","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2625455707","https://openalex.org/W2728551486","https://openalex.org/W2737258237","https://openalex.org/W2758849341","https://openalex.org/W2767754137","https://openalex.org/W2774267535","https://openalex.org/W2949117887","https://openalex.org/W2949218037","https://openalex.org/W2949999304","https://openalex.org/W2950187998","https://openalex.org/W2950761309","https://openalex.org/W2950926078","https://openalex.org/W2951505120","https://openalex.org/W2951619830","https://openalex.org/W2951638509","https://openalex.org/W2952122856","https://openalex.org/W2952246170","https://openalex.org/W2953276893","https://openalex.org/W2962753610","https://openalex.org/W2963037989","https://openalex.org/W2963758027","https://openalex.org/W2963902314","https://openalex.org/W2963996492","https://openalex.org/W2964001192","https://openalex.org/W2964345931","https://openalex.org/W3099142230","https://openalex.org/W3105148948","https://openalex.org/W4231029117","https://openalex.org/W4232426322","https://openalex.org/W4235505822","https://openalex.org/W4237938692","https://openalex.org/W6632527360","https://openalex.org/W6634232107","https://openalex.org/W6639102338","https://openalex.org/W6639927594","https://openalex.org/W6684512847","https://openalex.org/W6687483927","https://openalex.org/W6713645886"],"related_works":["https://openalex.org/W1492794944","https://openalex.org/W169603398","https://openalex.org/W1965669125","https://openalex.org/W2913274341","https://openalex.org/W2049033869","https://openalex.org/W4375958012","https://openalex.org/W2910844563","https://openalex.org/W2059672880","https://openalex.org/W2064852296","https://openalex.org/W2020360005"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":12},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}