{"id":"https://openalex.org/W2620341577","doi":"https://doi.org/10.1007/s13735-018-0151-5","title":"End-to-end cross-modality retrieval with CCA projections and pairwise ranking loss","display_name":"End-to-end cross-modality retrieval with CCA projections and pairwise ranking loss","publication_year":2018,"publication_date":"2018-03-07","ids":{"openalex":"https://openalex.org/W2620341577","doi":"https://doi.org/10.1007/s13735-018-0151-5","mag":"2620341577"},"language":"en","primary_location":{"id":"doi:10.1007/s13735-018-0151-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13735-018-0151-5","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs13735-018-0151-5.pdf","source":{"id":"https://openalex.org/S2496055428","display_name":"International Journal of Multimedia Information Retrieval","issn_l":"2192-6611","issn":["2192-6611","2192-662X"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Multimedia Information Retrieval","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007%2Fs13735-018-0151-5.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029203655","display_name":"Matthias Dorfer","orcid":"https://orcid.org/0000-0002-3806-5411"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Matthias Dorfer","raw_affiliation_strings":["Department of Computational Perception, Johannes Kepler University Linz, 4040, Linz, Austria"],"affiliations":[{"raw_affiliation_string":"Department of Computational Perception, Johannes Kepler University Linz, 4040, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101525853","display_name":"Jan Schl\u00fcter","orcid":"https://orcid.org/0000-0003-3862-6888"},"institutions":[{"id":"https://openalex.org/I161878677","display_name":"Austrian Research Institute for Artificial Intelligence","ror":"https://ror.org/04j47vk14","country_code":"AT","type":"facility","lineage":["https://openalex.org/I161878677","https://openalex.org/I4210107880"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Jan Schl\u00fcter","raw_affiliation_strings":["The Austrian Research Institute for Artificial Intelligence, 1010, Vienna, Austria"],"affiliations":[{"raw_affiliation_string":"The Austrian Research Institute for Artificial Intelligence, 1010, Vienna, Austria","institution_ids":["https://openalex.org/I161878677"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061500695","display_name":"Andreu Vall","orcid":"https://orcid.org/0000-0002-7331-7792"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Andreu Vall","raw_affiliation_strings":["Department of Computational Perception, Johannes Kepler University Linz, 4040, Linz, Austria"],"affiliations":[{"raw_affiliation_string":"Department of Computational Perception, Johannes Kepler University Linz, 4040, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047928537","display_name":"Filip Korzeniowski","orcid":"https://orcid.org/0000-0002-7287-8053"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Filip Korzeniowski","raw_affiliation_strings":["Department of Computational Perception, Johannes Kepler University Linz, 4040, Linz, Austria"],"affiliations":[{"raw_affiliation_string":"Department of Computational Perception, Johannes Kepler University Linz, 4040, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003768123","display_name":"Gerhard Widmer","orcid":"https://orcid.org/0000-0003-3531-1282"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]},{"id":"https://openalex.org/I161878677","display_name":"Austrian Research Institute for Artificial Intelligence","ror":"https://ror.org/04j47vk14","country_code":"AT","type":"facility","lineage":["https://openalex.org/I161878677","https://openalex.org/I4210107880"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Gerhard Widmer","raw_affiliation_strings":["Department of Computational Perception, Johannes Kepler University Linz, 4040, Linz, Austria","The Austrian Research Institute for Artificial Intelligence, 1010, Vienna, Austria"],"affiliations":[{"raw_affiliation_string":"Department of Computational Perception, Johannes Kepler University Linz, 4040, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]},{"raw_affiliation_string":"The Austrian Research Institute for Artificial Intelligence, 1010, Vienna, Austria","institution_ids":["https://openalex.org/I161878677"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5029203655"],"corresponding_institution_ids":["https://openalex.org/I121883995"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":3.4036,"has_fulltext":true,"cited_by_count":47,"citation_normalized_percentile":{"value":0.94547701,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"7","issue":"2","first_page":"117","last_page":"128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9995999932289124,"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":0.8424603343009949},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.770199716091156},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.7281208634376526},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6734035015106201},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6700845956802368},{"id":"https://openalex.org/keywords/canonical-correlation","display_name":"Canonical correlation","score":0.5939002633094788},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5359604358673096},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4793573021888733},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4126237630844116},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3459312915802002},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.20087501406669617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8424603343009949},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.770199716091156},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7281208634376526},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6734035015106201},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6700845956802368},{"id":"https://openalex.org/C153874254","wikidata":"https://www.wikidata.org/wiki/Q115542","display_name":"Canonical correlation","level":2,"score":0.5939002633094788},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5359604358673096},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4793573021888733},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4126237630844116},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3459312915802002},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20087501406669617}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s13735-018-0151-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13735-018-0151-5","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs13735-018-0151-5.pdf","source":{"id":"https://openalex.org/S2496055428","display_name":"International Journal of Multimedia Information Retrieval","issn_l":"2192-6611","issn":["2192-6611","2192-662X"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Multimedia Information Retrieval","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1705.06979","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1705.06979","pdf_url":"https://arxiv.org/pdf/1705.06979","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:epub.jku.at/:3406327","is_oa":true,"landing_page_url":"https://epub.jku.at/doi/10.1007/s13735-018-0151-5","pdf_url":null,"source":{"id":"https://openalex.org/S4306401788","display_name":"University Library Linz repository (Johannes Kepler Universitat Linz)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I121883995","host_organization_name":"Johannes Kepler University of Linz","host_organization_lineage":["https://openalex.org/I121883995"],"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":"Text"}],"best_oa_location":{"id":"doi:10.1007/s13735-018-0151-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13735-018-0151-5","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs13735-018-0151-5.pdf","source":{"id":"https://openalex.org/S2496055428","display_name":"International Journal of Multimedia Information Retrieval","issn_l":"2192-6611","issn":["2192-6611","2192-662X"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Multimedia Information Retrieval","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2620341577.pdf","grobid_xml":"https://content.openalex.org/works/W2620341577.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1523385540","https://openalex.org/W1527575280","https://openalex.org/W1562955078","https://openalex.org/W1600402929","https://openalex.org/W1686810756","https://openalex.org/W1799366690","https://openalex.org/W1819710477","https://openalex.org/W1836465849","https://openalex.org/W1905882502","https://openalex.org/W1924770834","https://openalex.org/W1949478088","https://openalex.org/W2100235303","https://openalex.org/W2108598243","https://openalex.org/W2112912048","https://openalex.org/W2131566584","https://openalex.org/W2138118304","https://openalex.org/W2149557440","https://openalex.org/W2153579005","https://openalex.org/W2159243025","https://openalex.org/W2176412452","https://openalex.org/W2271840356","https://openalex.org/W2276499310","https://openalex.org/W2384495648","https://openalex.org/W2533598788","https://openalex.org/W2579712972","https://openalex.org/W2949117887","https://openalex.org/W2963173190","https://openalex.org/W2963285578","https://openalex.org/W2963899908","https://openalex.org/W4234552385","https://openalex.org/W4247269759","https://openalex.org/W4285719527","https://openalex.org/W4294170691","https://openalex.org/W4296156497","https://openalex.org/W4297824567","https://openalex.org/W4299801216","https://openalex.org/W6605520847","https://openalex.org/W6653085483","https://openalex.org/W6829887170"],"related_works":["https://openalex.org/W2487162673","https://openalex.org/W1565185441","https://openalex.org/W2793211469","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W2011472225","https://openalex.org/W3000057026","https://openalex.org/W3048565508","https://openalex.org/W3163984363","https://openalex.org/W1968265719"],"abstract_inverted_index":{"Cross-modality":[0],"retrieval":[1,3,32,119],"encompasses":[2],"tasks":[4],"where":[5,44],"the":[6,15,41,86,105,112],"fetched":[7],"items":[8,45],"are":[9,49],"of":[10,40,108,114],"a":[11,23,36,59,134,143],"different":[12,122],"type":[13],"than":[14],"search":[16],"query,":[17],"e.g.,":[18],"retrieving":[19],"pictures":[20],"relevant":[21],"to":[22,30,83,91],"given":[24],"text":[25],"query.":[26],"The":[27],"state-of-the-art":[28],"approach":[29,116],"cross-modality":[31,118],"relies":[33],"on":[34,64,120],"learning":[35],"joint":[37],"embedding":[38,72,96],"space":[39,97],"two":[42],"modalities,":[43],"from":[46],"either":[47],"modality":[48],"retrieved":[50],"using":[51,137],"nearest-neighbor":[52],"search.":[53],"In":[54,81],"this":[55],"work,":[56],"we":[57],"introduce":[58],"neural":[60],"network":[61,136],"layer":[62,88],"based":[63],"canonical":[65],"correlation":[66],"analysis":[67],"(CCA)":[68],"that":[69,78],"learns":[70],"better":[71],"spaces":[73],"by":[74,142],"analytically":[75],"computing":[76],"projections":[77,107,140],"maximize":[79],"correlation.":[80],"contrast":[82],"previous":[84],"approaches,":[85],"CCA":[87,132],"allows":[89],"us":[90],"combine":[92],"existing":[93],"objectives":[94],"for":[95,117,156],"learning,":[98],"such":[99],"as":[100],"pairwise":[101,144],"ranking":[102,145],"losses,":[103],"with":[104],"optimal":[106],"CCA.":[109],"We":[110],"show":[111],"effectiveness":[113],"our":[115],"three":[121,158],"scenarios":[123],"(text-to-image,":[124],"audio-sheet-music":[125],"and":[126,133],"zero-shot":[127],"retrieval),":[128],"surpassing":[129],"both":[130],"Deep":[131],"multi-view":[135],"freely":[138],"learned":[139],"optimized":[141],"loss,":[146],"especially":[147],"when":[148],"little":[149],"training":[150],"data":[151],"is":[152,160],"available":[153],"(the":[154],"code":[155],"all":[157],"methods":[159],"released":[161],"at:":[162],"https://github.com/CPJKU/cca_layer":[163],").":[164]},"counts_by_year":[{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}