{"id":"https://openalex.org/W2808336545","doi":"https://doi.org/10.1145/3206025.3206033","title":"Modal-adversarial Semantic Learning Network for Extendable Cross-modal Retrieval","display_name":"Modal-adversarial Semantic Learning Network for Extendable Cross-modal Retrieval","publication_year":2018,"publication_date":"2018-06-05","ids":{"openalex":"https://openalex.org/W2808336545","doi":"https://doi.org/10.1145/3206025.3206033","mag":"2808336545"},"language":"en","primary_location":{"id":"doi:10.1145/3206025.3206033","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3206025.3206033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009074046","display_name":"Xing Xu","orcid":"https://orcid.org/0000-0001-5685-3123"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xing Xu","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036987388","display_name":"Jingkuan Song","orcid":"https://orcid.org/0000-0002-2549-8322"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingkuan Song","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019035804","display_name":"Huimin Lu","orcid":"https://orcid.org/0000-0001-9794-3221"},"institutions":[{"id":"https://openalex.org/I207014233","display_name":"Kyushu Institute of Technology","ror":"https://ror.org/02278tr80","country_code":"JP","type":"education","lineage":["https://openalex.org/I207014233"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Huimin Lu","raw_affiliation_strings":["Kyushu Institute of Technology, Kitakyushu, Japan"],"affiliations":[{"raw_affiliation_string":"Kyushu Institute of Technology, Kitakyushu, Japan","institution_ids":["https://openalex.org/I207014233"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074492050","display_name":"Fumin Shen","orcid":"https://orcid.org/0000-0001-7303-3231"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fumin Shen","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078170935","display_name":"Zi Huang","orcid":"https://orcid.org/0000-0002-9738-4949"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zi Huang","raw_affiliation_strings":["University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5009074046"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":3.5086,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.94794159,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"46","last_page":"54"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9966999888420105,"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":0.7929982542991638},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5857052803039551},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5831493139266968},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5267170071601868},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47939014434814453},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.42070114612579346},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.412921279668808},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3969985842704773},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3708782494068146},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32943493127822876}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7929982542991638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5857052803039551},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5831493139266968},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5267170071601868},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47939014434814453},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.42070114612579346},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.412921279668808},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3969985842704773},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3708782494068146},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32943493127822876},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3206025.3206033","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3206025.3206033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:espace.library.uq.edu.au:UQ:48cb5f4","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402388","display_name":"Queensland's institutional digital repository (The University of Queensland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165143802","host_organization_name":"The University of Queensland","host_organization_lineage":["https://openalex.org/I165143802"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1523385540","https://openalex.org/W1686810756","https://openalex.org/W1883346539","https://openalex.org/W1949478088","https://openalex.org/W1964073652","https://openalex.org/W2053667957","https://openalex.org/W2059003682","https://openalex.org/W2070753207","https://openalex.org/W2099471712","https://openalex.org/W2100235303","https://openalex.org/W2106277773","https://openalex.org/W2119775030","https://openalex.org/W2138118304","https://openalex.org/W2139172286","https://openalex.org/W2164530430","https://openalex.org/W2184188583","https://openalex.org/W2211092169","https://openalex.org/W2250539671","https://openalex.org/W2282231212","https://openalex.org/W2326180695","https://openalex.org/W2463762378","https://openalex.org/W2525270349","https://openalex.org/W2552383788","https://openalex.org/W2557865186","https://openalex.org/W2574447816","https://openalex.org/W2584893896","https://openalex.org/W2591669147","https://openalex.org/W2604579046","https://openalex.org/W2605649771","https://openalex.org/W2620971895","https://openalex.org/W2739103128","https://openalex.org/W2747647654","https://openalex.org/W2747853580","https://openalex.org/W2752930373","https://openalex.org/W2765440071","https://openalex.org/W2766910785","https://openalex.org/W2788585680","https://openalex.org/W2795389793","https://openalex.org/W2950700180","https://openalex.org/W2963281729","https://openalex.org/W2963389687","https://openalex.org/W2963826681","https://openalex.org/W2964216321"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4224009465","https://openalex.org/W2357241418","https://openalex.org/W4286629047","https://openalex.org/W4301143707","https://openalex.org/W3087493185","https://openalex.org/W3038842520","https://openalex.org/W4206762304","https://openalex.org/W3158586592"],"abstract_inverted_index":{"Cross-modal":[0],"retrieval,":[1],"e.g.,":[2],"using":[3],"an":[4,220],"image":[5],"query":[6],"to":[7,19,68,101,149,205,211,230,245],"search":[8],"related":[9],"text":[10],"and":[11,56,96,132,170,241,261,266],"vice-versa,":[12],"has":[13],"become":[14],"a":[15,42,47,65,119,140],"highlighted":[16],"research":[17],"topic,":[18],"provide":[20],"flexible":[21],"retrieval":[22,35,112,126,269],"experience":[23],"across":[24],"multi-modal":[25,256],"data.":[26],"Existing":[27],"approaches":[28],"usually":[29],"consider":[30,118],"the":[31,62,80,83,90,94,103,109,151,161,177,188,197,213,216,232,237,242,248],"so-called":[32],"non-extendable":[33,265],"cross-modal":[34,70,111,125,168,178,233,268],"task.":[36,113,159,270],"In":[37,114],"this":[38,115,157],"task,":[39],"they":[40],"learn":[41],"common":[43,59,217,239],"latent":[44],"subspace":[45,240],"from":[46,215],"source":[48,95,131],"set":[49,67,85,98,134],"containing":[50],"labeled":[51],"instances":[52,63,81,91,129,246],"of":[53,82,92,106,123,153,167,190],"image-text":[54],"pairs":[55],"then":[57],"generate":[58],"representation":[60,204,218],"for":[61,208],"in":[64,108,130,196,236,247],"target":[66,84,97,133,249],"perform":[69],"matching.":[71],"However,":[72],"these":[73],"method":[74],"may":[75],"not":[76],"generalize":[77],"well":[78],"when":[79],"contains":[86],"unseen":[87],"classes":[88,107],"since":[89],"both":[93,264],"are":[99,227],"assumed":[100],"share":[102],"same":[104],"range":[105],"non-extensive":[110],"paper,":[116],"we":[117],"more":[120],"practical":[121,158],"issue":[122],"extendable":[124,267],"task":[127],"where":[128],"have":[135],"disjoint":[136],"classes.":[137],"We":[138],"propose":[139],"novel":[141],"framework,":[142],"termed":[143],"Modal-adversarial":[144],"Semantic":[145],"Learning":[146],"Network":[147],"(MASLN),":[148],"tackle":[150],"limitation":[152],"existing":[154],"methods":[155],"on":[156,253,263],"Specifically,":[160],"proposed":[162],"MASLN":[163],"consists":[164],"two":[165,225],"subnetworks":[166,226],"reconstruction":[169,198],"modal-adversarial":[171],"semantic":[172,203,234],"learning.":[173],"The":[174,200,224],"former":[175],"minimizes":[176],"distribution":[179],"discrepancy":[180],"by":[181],"reconstructing":[182],"each":[183],"modality":[184],"data":[185],"mutually,":[186],"with":[187],"guidelines":[189],"class":[191],"embeddings":[192],"as":[193],"side":[194],"information":[195],"procedure.":[199],"latter":[201],"generates":[202],"be":[206],"indiscriminative":[207],"modalities,":[209],"while":[210],"distinguish":[212],"modalities":[214],"via":[219],"adversarial":[221],"learning":[222],"mechanism.":[223],"jointly":[228],"trained":[229],"enhance":[231],"consistency":[235],"learned":[238],"knowledge":[243],"transfer":[244],"set.":[250],"Comprehensive":[251],"experiment":[252],"three":[254],"widely-used":[255],"datasets":[257],"show":[258],"its":[259],"effectiveness":[260],"robustness":[262]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":12}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}