{"id":"https://openalex.org/W4401750957","doi":"https://doi.org/10.1109/isbi56570.2024.10635693","title":"Dual Representation Learning From Fetal Ultrasound Video and Sonographer Audio","display_name":"Dual Representation Learning From Fetal Ultrasound Video and Sonographer Audio","publication_year":2024,"publication_date":"2024-05-27","ids":{"openalex":"https://openalex.org/W4401750957","doi":"https://doi.org/10.1109/isbi56570.2024.10635693","pmid":"https://pubmed.ncbi.nlm.nih.gov/40438701"},"language":"en","primary_location":{"id":"doi:10.1109/isbi56570.2024.10635693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isbi56570.2024.10635693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Biomedical Imaging (ISBI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC7616753/pdf/EMS199595.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015592249","display_name":"Mourad Gridach","orcid":"https://orcid.org/0000-0002-7998-0448"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mourad Gridach","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066105306","display_name":"Mohammad Alsharid","orcid":"https://orcid.org/0000-0002-2271-0578"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mohammad Alsharid","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017599481","display_name":"Jianbo Jiao","orcid":"https://orcid.org/0000-0003-0833-5115"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianbo Jiao","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076657548","display_name":"Lior Drukker","orcid":"https://orcid.org/0000-0002-5588-1410"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lior Drukker","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039160245","display_name":"Aris T. Papageorghiou","orcid":"https://orcid.org/0000-0001-8143-2232"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Aris T. Papageorghiou","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077728082","display_name":"J. Alison Noble","orcid":"https://orcid.org/0000-0002-3060-3772"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"J. Alison Noble","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6109,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.73397147,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"2024","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9822999835014343,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9822999835014343,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10860","display_name":"Speech and Audio Processing","score":0.974399983882904,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9671000242233276,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/sonographer","display_name":"Sonographer","score":0.9730314016342163},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6700921654701233},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5212412476539612},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4854443669319153},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4728204011917114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4573897123336792},{"id":"https://openalex.org/keywords/ultrasound","display_name":"Ultrasound","score":0.4493121802806854},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42491084337234497},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3328476846218109},{"id":"https://openalex.org/keywords/radiology","display_name":"Radiology","score":0.15291163325309753},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.13576245307922363}],"concepts":[{"id":"https://openalex.org/C2778941581","wikidata":"https://www.wikidata.org/wiki/Q11251722","display_name":"Sonographer","level":3,"score":0.9730314016342163},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6700921654701233},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5212412476539612},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4854443669319153},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4728204011917114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4573897123336792},{"id":"https://openalex.org/C143753070","wikidata":"https://www.wikidata.org/wiki/Q162564","display_name":"Ultrasound","level":2,"score":0.4493121802806854},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42491084337234497},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3328476846218109},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.15291163325309753},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.13576245307922363},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/isbi56570.2024.10635693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isbi56570.2024.10635693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Biomedical Imaging (ISBI)","raw_type":"proceedings-article"},{"id":"pmid:40438701","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40438701","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. IEEE International Symposium on Biomedical Imaging","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:7616753","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7616753","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC7616753/pdf/EMS199595.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc IEEE Int Symp Biomed Imaging","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:7616753","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7616753","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC7616753/pdf/EMS199595.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc IEEE Int Symp Biomed Imaging","raw_type":"Text"},"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[{"id":"https://openalex.org/G4530138162","display_name":null,"funder_award_id":"EP/MO13774/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320319990","display_name":"National Institute for Health and Care Research","ror":"https://ror.org/0187kwz08"},{"id":"https://openalex.org/F4320320006","display_name":"Royal Society","ror":"https://ror.org/03wnrjx87"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320336045","display_name":"NIHR Oxford Biomedical Research Centre","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401750957.pdf"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2326925005","https://openalex.org/W2890952074","https://openalex.org/W2963503775","https://openalex.org/W3094123278","https://openalex.org/W3180638445","https://openalex.org/W6747225742","https://openalex.org/W6774314701"],"related_works":["https://openalex.org/W3047805102","https://openalex.org/W2526371571","https://openalex.org/W4307493836","https://openalex.org/W2160946342","https://openalex.org/W2064512321","https://openalex.org/W2005024658","https://openalex.org/W2174001346","https://openalex.org/W4241217511","https://openalex.org/W2556291463","https://openalex.org/W3028729327"],"abstract_inverted_index":{"This":[0],"paper":[1],"tackles":[2],"the":[3,20,37,42,46,73,81,114,153,156,164],"challenging":[4],"problem":[5],"of":[6,60,66,96,142,155],"real-world":[7],"data":[8],"self-supervised":[9],"representation":[10,87],"learning":[11,61,88],"from":[12,89],"two":[13,97,124,131],"modalities:":[14],"fetal":[15],"ultrasound":[16],"(US)":[17],"video":[18,48,78,91,143],"and":[19,45,69,80,92,102,120,140],"corresponding":[21],"speech":[22,44,158],"acquired":[23],"when":[24],"a":[25,28,56,107],"sonographer":[26,148],"performs":[27],"pregnancy":[29],"scan.":[30],"We":[31,54,84],"propose":[32],"to":[33,150],"transfer":[34],"knowledge":[35],"between":[36,75],"different":[38,132],"modalities,":[39],"even":[40],"though":[41],"sonographer's":[43,82,157],"US":[47,77,90],"may":[49],"not":[50],"be":[51],"semantically":[52],"correlated.":[53],"design":[55],"network":[57],"architecture":[58,116],"capable":[59],"useful":[62],"representations":[63,119],"such":[64],"as":[65,147],"anatomical":[67],"features":[68],"structures":[70],"while":[71],"recognising":[72],"correlation":[74],"an":[76,160],"scan":[79],"speech.":[83],"introduce":[85],"dual":[86],"audio,":[93],"which":[94,136],"consists":[95],"concepts:":[98],"Multi-Modal":[99,103],"Contrastive":[100],"Learning":[101],"Similarity":[104],"Learning,":[105],"in":[106,138,163],"latent":[108],"feature":[109],"space.":[110],"Experiments":[111],"show":[112,151],"that":[113,152],"proposed":[115],"learns":[117],"powerful":[118],"transfers":[121],"well":[122,146],"for":[123,134],"downstream":[125],"tasks.":[126],"Furthermore,":[127],"we":[128],"experiment":[129],"with":[130],"datasets":[133],"pretraining":[135],"differ":[137],"size":[139],"length":[141],"clips":[144],"(as":[145],"speech)":[149],"quality":[154],"plays":[159],"important":[161],"role":[162],"final":[165],"performance.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}