{"id":"https://openalex.org/W3140270772","doi":"https://doi.org/10.1016/j.patcog.2021.107983","title":"Integrating information theory and adversarial learning for cross-modal retrieval","display_name":"Integrating information theory and adversarial learning for cross-modal retrieval","publication_year":2021,"publication_date":"2021-04-08","ids":{"openalex":"https://openalex.org/W3140270772","doi":"https://doi.org/10.1016/j.patcog.2021.107983","mag":"3140270772"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patcog.2021.107983","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.patcog.2021.107983","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100344333","display_name":"Wei Chen","orcid":"https://orcid.org/0000-0001-7875-4548"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Wei Chen","raw_affiliation_strings":["LIACS, Leiden University, Leiden, 2333 CA, The Netherlands"],"affiliations":[{"raw_affiliation_string":"LIACS, Leiden University, Leiden, 2333 CA, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004895426","display_name":"Yu Liu","orcid":"https://orcid.org/0000-0002-2067-9175"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Yu Liu","raw_affiliation_strings":["ESAT-PSI, KU Leuven, Heverlee-Leuven, 3001, Belgium"],"affiliations":[{"raw_affiliation_string":"ESAT-PSI, KU Leuven, Heverlee-Leuven, 3001, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047471651","display_name":"Erwin M. Bakker","orcid":"https://orcid.org/0000-0002-2624-5271"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Erwin M. Bakker","raw_affiliation_strings":["LIACS, Leiden University, Leiden, 2333 CA, The Netherlands"],"affiliations":[{"raw_affiliation_string":"LIACS, Leiden University, Leiden, 2333 CA, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107877141","display_name":"Michael S. Lew","orcid":null},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Michael S. Lew","raw_affiliation_strings":["LIACS, Leiden University, Leiden, 2333 CA, The Netherlands"],"affiliations":[{"raw_affiliation_string":"LIACS, Leiden University, Leiden, 2333 CA, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5107877141"],"corresponding_institution_ids":["https://openalex.org/I121797337"],"apc_list":{"value":2710,"currency":"USD","value_usd":2710,"provenance":"doaj"},"apc_paid":{"value":2710,"currency":"USD","value_usd":2710,"provenance":"doaj"},"fwci":2.245,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":23,"citation_normalized_percentile":{"value":0.999939,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":95},"biblio":{"volume":"117","issue":null,"first_page":"107983","last_page":"107983"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997,"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":0.9997,"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":0.9997,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9975,"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/discriminator","display_name":"Discriminator","score":0.8655672},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.5293829},{"id":"https://openalex.org/keywords/information-theory","display_name":"Information Theory","score":0.51691365},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.41239497}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.8655672},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.66917586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6268668},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.568661},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.53690195},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.53446585},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.5293829},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5257833},{"id":"https://openalex.org/C52622258","wikidata":"https://www.wikidata.org/wiki/Q131222","display_name":"Information theory","level":2,"score":0.51691365},{"id":"https://openalex.org/C106752470","wikidata":"https://www.wikidata.org/wiki/Q1364826","display_name":"Joint entropy","level":3,"score":0.44601563},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.41239497},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40655595},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.23905867},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23512933},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12438822},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patcog.2021.107983","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://hdl.handle.net/1887/3163550","pdf_url":"https://scholarlypublications.universiteitleiden.nl/access/item%3A3163551/view","source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":["Royal Netherlands Academy of Arts and Sciences"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2104.04991","pdf_url":"https://arxiv.org/pdf/2104.04991","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patcog.2021.107983","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.74}],"grants":[{"funder":"https://openalex.org/F4320320929","funder_display_name":"Universiteit Leiden","award_id":"201703170183"},{"funder":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council","award_id":"201703170183"}],"datasets":[],"versions":[],"referenced_works_count":44,"referenced_works":["https://openalex.org/W1510632636","https://openalex.org/W1566256432","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1957706851","https://openalex.org/W1995875735","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2284126738","https://openalex.org/W2335024046","https://openalex.org/W2476034201","https://openalex.org/W2546696630","https://openalex.org/W2552579943","https://openalex.org/W2592388817","https://openalex.org/W2612445135","https://openalex.org/W2619383789","https://openalex.org/W2626967530","https://openalex.org/W2743355020","https://openalex.org/W2765440071","https://openalex.org/W2778100917","https://openalex.org/W2883311563","https://openalex.org/W2885709146","https://openalex.org/W2894786240","https://openalex.org/W2900564790","https://openalex.org/W2942614241","https://openalex.org/W2955736964","https://openalex.org/W2962529143","https://openalex.org/W2962706528","https://openalex.org/W2963073217","https://openalex.org/W2963389687","https://openalex.org/W2963499204","https://openalex.org/W2963826681","https://openalex.org/W2966783477","https://openalex.org/W2985951359","https://openalex.org/W3011997138","https://openalex.org/W3015686580","https://openalex.org/W3029678209","https://openalex.org/W3030772386","https://openalex.org/W3038590649","https://openalex.org/W3047647477","https://openalex.org/W3102887392","https://openalex.org/W4297775537","https://openalex.org/W4300560153","https://openalex.org/W68733909"],"related_works":["https://openalex.org/W4383822431","https://openalex.org/W4225940264","https://openalex.org/W3212925274","https://openalex.org/W3134129340","https://openalex.org/W3124771927","https://openalex.org/W2920676536","https://openalex.org/W2509725027","https://openalex.org/W2163103544","https://openalex.org/W2036846997","https://openalex.org/W1479897377"],"abstract_inverted_index":{"Accurately":[0],"matching":[1],"visual":[2],"and":[3,26,36,49,69,113,159,169],"textual":[4],"data":[5,199],"in":[6,13,174],"cross-modal":[7,135],"retrieval":[8],"has":[9],"been":[10],"widely":[11],"studied":[12],"the":[14,23,27,42,67,91,94,117,131,144,153,167,175,192,198,215,218],"multimedia":[15],"community.":[16],"To":[17,151],"address":[18],"these":[19],"challenges":[20],"posited":[21],"by":[22,119,197],"heterogeneity":[24,43],"gap":[25],"semantic":[28,154],"gap,":[29,44,155],"we":[30,45],"propose":[31],"integrating":[32],"Shannon":[33,86],"information":[34,50,87,123,127],"theory":[35],"adversarial":[37],"learning.":[38],"In":[39],"terms":[40],"of":[41,93,134,217],"integrate":[46],"modality":[47,58,95],"classification":[48,96],"entropy":[51,128],"maximization":[52],"adversarially.":[53],"For":[54],"this":[55],"purpose,":[56],"a":[57,61,103,109,139,179],"classifier":[59,195],"(as":[60,102],"discriminator)":[62],"is":[63,188],"built":[64],"to":[65,73,84,115,165,190,213],"distinguish":[66],"text":[68],"image":[70],"modalities":[71,149],"according":[72],"their":[74],"different":[75],"statistical":[76],"properties.":[77],"This":[78],"discriminator":[79,118,145],"uses":[80],"its":[81,121],"output":[82,122],"probabilities":[83],"compute":[85],"entropy,":[88],"which":[89],"measures":[90],"uncertainty":[92],"it":[97],"performs.":[98],"Moreover,":[99],"feature":[100],"encoders":[101],"generator)":[104],"project":[105],"uni-modal":[106],"features":[107,173],"into":[108],"commonly":[110],"shared":[111,176],"space":[112],"attempt":[114],"fool":[116],"maximizing":[120,126],"entropy.":[124],"Thus,":[125],"gradually":[129],"reduces":[130],"distribution":[132],"discrepancy":[133],"features,":[136],"thereby":[137],"achieving":[138],"domain":[140],"confusion":[141],"state":[142],"where":[143],"cannot":[146],"classify":[147],"two":[148],"confidently.":[150],"reduce":[152],"Kullback-Leibler":[156],"(KL)":[157],"divergence":[158],"bi-directional":[160],"triplet":[161],"loss":[162],"are":[163,211],"used":[164,189],"associate":[166],"intra-":[168],"inter-modality":[170],"similarity":[171],"between":[172],"space.":[177],"Furthermore,":[178],"regularization":[180],"term":[181],"based":[182],"on":[183,208],"KL-divergence":[184],"with":[185,204],"temperature":[186],"scaling":[187],"calibrate":[191],"biased":[193],"label":[194],"caused":[196],"imbalance":[200],"issue.":[201],"Extensive":[202],"experiments":[203],"four":[205,209],"deep":[206],"models":[207],"benchmarks":[210],"conducted":[212],"demonstrate":[214],"effectiveness":[216],"proposed":[219],"approach.":[220]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3140270772","counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":1}],"updated_date":"2025-01-08T11:43:00.544296","created_date":"2021-04-13"}