{"id":"https://openalex.org/W3026614632","doi":"https://doi.org/10.1109/access.2020.2995815","title":"Enhancing Cross-Modal Retrieval Based on Modality-Specific and Embedding Spaces","display_name":"Enhancing Cross-Modal Retrieval Based on Modality-Specific and Embedding Spaces","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3026614632","doi":"https://doi.org/10.1109/access.2020.2995815","mag":"3026614632"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.2995815","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2995815","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09097176.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09097176.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071840670","display_name":"Rintaro Yanagi","orcid":"https://orcid.org/0000-0003-0110-7208"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rintaro Yanagi","raw_affiliation_strings":["Graduate School of Information Science and Technology, Hokkaido University, Sapporo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-0110-7208","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, Hokkaido University, Sapporo, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002757875","display_name":"Ren Togo","orcid":"https://orcid.org/0000-0002-4474-3995"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ren Togo","raw_affiliation_strings":["Education and Research Center for Mathematical and Data Science, Hokkaido University, Sapporo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4474-3995","affiliations":[{"raw_affiliation_string":"Education and Research Center for Mathematical and Data Science, Hokkaido University, Sapporo, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009032240","display_name":"Takahiro Ogawa","orcid":"https://orcid.org/0000-0001-5332-8112"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Ogawa","raw_affiliation_strings":["Faculty of Information Science and Technology, Division of Media and Network Technologies, Hokkaido University, Sapporo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-5332-8112","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Division of Media and Network Technologies, Hokkaido University, Sapporo, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"last","author":{"id":null,"display_name":"Miki Haseyama","orcid":"https://orcid.org/0000-0003-1496-1761"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Miki Haseyama","raw_affiliation_strings":["Faculty of Information Science and Technology, Division of Media and Network Technologies, Hokkaido University, Sapporo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1496-1761","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Division of Media and Network Technologies, Hokkaido University, Sapporo, Japan","institution_ids":["https://openalex.org/I205349734"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205349734"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.15,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.80648409,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"8","issue":null,"first_page":"96777","last_page":"96786"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994000196456909,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9965000152587891,"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/computer-science","display_name":"Computer science","score":0.8186116218566895},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7978607416152954},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7528167963027954},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6861035227775574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6293835639953613},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5479152798652649},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5238694548606873},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.5207828879356384},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4996755123138428},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47136130928993225},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4341168701648712},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42053964734077454},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40186065435409546},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36580508947372437},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.36222267150878906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8186116218566895},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7978607416152954},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7528167963027954},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6861035227775574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6293835639953613},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5479152798652649},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5238694548606873},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.5207828879356384},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4996755123138428},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47136130928993225},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4341168701648712},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42053964734077454},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40186065435409546},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36580508947372437},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36222267150878906},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/access.2020.2995815","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2995815","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09097176.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:885ff79c906440b4b9c9a58ceb9383a4","is_oa":true,"landing_page_url":"https://doaj.org/article/885ff79c906440b4b9c9a58ceb9383a4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 96777-96786 (2020)","raw_type":"article"},{"id":"pmh:oai:eprints.lib.hokudai.ac.jp:2115/78959","is_oa":true,"landing_page_url":"http://hdl.handle.net/2115/78959","pdf_url":null,"source":{"id":"https://openalex.org/S4306400549","display_name":"Hokkaido University Collection of Scholarly and Academic Papers (Hokkaido University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205349734","host_organization_name":"Hokkaido University","host_organization_lineage":["https://openalex.org/I205349734"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},{"id":"pmh:oai:irdb.nii.ac.jp:01364:0007191930","is_oa":true,"landing_page_url":"https://hdl.handle.net/2115/78959","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access","raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.2995815","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2995815","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09097176.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.75,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4515739553","display_name":"Super-MultiModal Human Analysis Platform for Next Generation of Advanced Retrieval","funder_award_id":"17H01744","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3026614632.pdf","grobid_xml":"https://content.openalex.org/works/W3026614632.grobid-xml"},"referenced_works_count":72,"referenced_works":["https://openalex.org/W92662927","https://openalex.org/W1123427201","https://openalex.org/W1514535095","https://openalex.org/W1527575280","https://openalex.org/W1686810756","https://openalex.org/W1773149199","https://openalex.org/W1778065289","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1916445035","https://openalex.org/W1924770834","https://openalex.org/W1949478088","https://openalex.org/W1964073652","https://openalex.org/W2006031689","https://openalex.org/W2019863495","https://openalex.org/W2039297031","https://openalex.org/W2046589280","https://openalex.org/W2064675550","https://openalex.org/W2099471712","https://openalex.org/W2112912048","https://openalex.org/W2159128662","https://openalex.org/W2405756170","https://openalex.org/W2476034201","https://openalex.org/W2499468060","https://openalex.org/W2530372461","https://openalex.org/W2552579943","https://openalex.org/W2598991778","https://openalex.org/W2605035112","https://openalex.org/W2606473278","https://openalex.org/W2774267535","https://openalex.org/W2778100917","https://openalex.org/W2883311563","https://openalex.org/W2894786240","https://openalex.org/W2902617128","https://openalex.org/W2949999304","https://openalex.org/W2956018683","https://openalex.org/W2962845008","https://openalex.org/W2963040148","https://openalex.org/W2963413689","https://openalex.org/W2963435050","https://openalex.org/W2963446712","https://openalex.org/W2963467339","https://openalex.org/W2963499204","https://openalex.org/W2963899908","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W2964120214","https://openalex.org/W2966792645","https://openalex.org/W2970641574","https://openalex.org/W2979747405","https://openalex.org/W2982260276","https://openalex.org/W2983141445","https://openalex.org/W2990571534","https://openalex.org/W3029678209","https://openalex.org/W4299801216","https://openalex.org/W4300838842","https://openalex.org/W4308831279","https://openalex.org/W4320013936","https://openalex.org/W6630875275","https://openalex.org/W6631516269","https://openalex.org/W6637373629","https://openalex.org/W6639102338","https://openalex.org/W6640212811","https://openalex.org/W6676647902","https://openalex.org/W6685183736","https://openalex.org/W6713645886","https://openalex.org/W6721087566","https://openalex.org/W6728889164","https://openalex.org/W6747225742","https://openalex.org/W6754723634","https://openalex.org/W6756444276"],"related_works":["https://openalex.org/W2952745240","https://openalex.org/W2949074159","https://openalex.org/W4301143707","https://openalex.org/W4298715519","https://openalex.org/W2474574787","https://openalex.org/W3211385060","https://openalex.org/W2159851394","https://openalex.org/W3150772620","https://openalex.org/W3201919367","https://openalex.org/W4287330208"],"abstract_inverted_index":{"A":[0],"new":[1],"approach":[2,132],"that":[3,75,129,139],"drastically":[4],"improves":[5],"cross-modal":[6],"retrieval":[7,29,49,109],"performance":[8,135],"in":[9,23,81,101],"vision":[10,106],"and":[11,18,27,45,63,88,107,123,142],"language":[12,19,28,108],"(hereinafter":[13],"referred":[14],"to":[15,38,66,145],"as":[16,35],"\u201cvision":[17],"retrieval\u201d)":[20],"is":[21],"proposed":[22,112,131],"this":[24,91],"paper.":[25],"Vision":[26],"takes":[30],"data":[31,41],"of":[32,42,54,61,83,98,116,136],"one":[33],"modality":[34],"a":[36,67,102,146],"query":[37],"retrieve":[39],"relevant":[40],"another":[43],"modality,":[44],"it":[46],"enables":[47],"flexible":[48],"across":[50],"different":[51],"modalities.":[52],"Most":[53],"the":[55,76,130,134],"existing":[56,137],"methods":[57,138],"learn":[58],"optimal":[59],"embeddings":[60],"visual":[62,141],"lingual":[64,143],"information":[65,85,144],"single":[68,147],"common":[69,148],"representation":[70,99,119,149],"space.":[71,150],"However,":[72],"we":[73,93],"argue":[74],"forced":[77],"embedding":[78],"optimization":[79],"results":[80,127],"loss":[82],"key":[84],"for":[86],"sentences":[87],"images.":[89],"In":[90],"paper,":[92],"propose":[94],"an":[95],"effective":[96],"utilization":[97],"spaces":[100,120],"simple":[103],"but":[104],"robust":[105],"method.":[110],"The":[111],"method":[113],"makes":[114],"use":[115],"multiple":[117],"individual":[118],"through":[121],"text-to-image":[122],"image-to-text":[124],"models.":[125],"Experimental":[126],"showed":[128],"enhances":[133],"embed":[140]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}