{"id":"https://openalex.org/W2059003682","doi":"https://doi.org/10.1145/2733373.2806346","title":"Semi-supervised Coupled Dictionary Learning for Cross-modal Retrieval in Internet Images and Texts","display_name":"Semi-supervised Coupled Dictionary Learning for Cross-modal Retrieval in Internet Images and Texts","publication_year":2015,"publication_date":"2015-10-13","ids":{"openalex":"https://openalex.org/W2059003682","doi":"https://doi.org/10.1145/2733373.2806346","mag":"2059003682"},"language":"en","primary_location":{"id":"doi:10.1145/2733373.2806346","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2733373.2806346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xing Xu","raw_affiliation_strings":["Kyushu University, Fukuoka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyushu University, Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"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, CA, China","University of Electronic Science and Technology of China, Chengdu, CA, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, CA, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, CA, China#TAB#","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046057343","display_name":"Atsushi Shimada","orcid":"https://orcid.org/0000-0002-3635-9336"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Shimada","raw_affiliation_strings":["Kyushu University, Fukuoka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyushu University, Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111450732","display_name":"Rin-ichiro Taniguchi","orcid":null},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rin-ichiro Taniguchi","raw_affiliation_strings":["Kyushu University, Fukuoka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyushu University, Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073058503","display_name":"Li He","orcid":"https://orcid.org/0000-0002-6681-0933"},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]},{"id":"https://openalex.org/I4210087596","display_name":"Qualcomm (United States)","ror":"https://ror.org/002zrf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087596"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Li He","raw_affiliation_strings":["Qualcomm Research and Development Center, San Diego, CA, USA","Qualcomm Research and Development Center, San Diego, CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm Research and Development Center, San Diego, CA, USA","institution_ids":["https://openalex.org/I4210087596"]},{"raw_affiliation_string":"Qualcomm Research and Development Center, San Diego, CA, USA#TAB#","institution_ids":["https://openalex.org/I19268510"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"847","last_page":"850"},"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":0.9979000091552734,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.992900013923645,"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/computer-science","display_name":"Computer science","score":0.7583900690078735},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.7545143961906433},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.627571702003479},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5436122417449951},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5382959246635437},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5193130373954773},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5023155212402344},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.49799299240112305},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.49324101209640503},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.48474976420402527},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.47756701707839966},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4470856785774231},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4252413511276245},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4054795503616333},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.39730706810951233},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36615538597106934},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17831581830978394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7583900690078735},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.7545143961906433},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.627571702003479},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5436122417449951},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5382959246635437},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5193130373954773},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5023155212402344},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.49799299240112305},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.49324101209640503},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.48474976420402527},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.47756701707839966},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4470856785774231},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4252413511276245},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4054795503616333},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.39730706810951233},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36615538597106934},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17831581830978394},{"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2733373.2806346","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2733373.2806346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W154472438","https://openalex.org/W1994179401","https://openalex.org/W2022398331","https://openalex.org/W2041259983","https://openalex.org/W2070753207","https://openalex.org/W2087501015","https://openalex.org/W2100235303","https://openalex.org/W2106277773","https://openalex.org/W2136995369","https://openalex.org/W2164530430","https://openalex.org/W2998641113"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Nowadays":[0],"massive":[1],"amount":[2],"of":[3,16,34,125,158,192,227],"images":[4,35],"and":[5,24,36,69,113,178,221],"texts":[6],"has":[7],"been":[8],"emerging":[9],"on":[10,175,209,231],"the":[11,14,29,32,38,72,78,92,101,107,116,122,138,189,225,228,232],"Internet,":[12],"arousing":[13],"demand":[15],"effective":[17,89],"cross-modal":[18,52,153,206,233],"retrieval":[19,154,234],"such":[20],"as":[21],"text-to-image":[22],"search":[23],"image-to-text":[25],"search.":[26],"To":[27],"eliminate":[28],"heterogeneity":[30],"between":[31,94,110],"modalities":[33,96,112,173,194],"texts,":[37],"existing":[39],"subspace":[40,49,90,117,198],"learning":[41,87,118,164],"methods":[42,59,85],"try":[43],"to":[44,136,166,187,204],"learn":[45],"a":[46,149,160,182,196,210],"common":[47,197],"latent":[48],"under":[50],"which":[51],"matching":[53],"can":[54,105],"be":[55],"performed.":[56],"However,":[57],"these":[58,84],"usually":[60],"require":[61],"fully":[62,219],"paired":[63,79,177,220],"samples":[64,127],"(images":[65,128],"with":[66,77,217],"corresponding":[67],"texts)":[68,130],"also":[70],"ignore":[71],"class":[73,102,201],"label":[74,103,202],"information":[75,104,135,203],"along":[76],"samples.":[80],"This":[81],"may":[82,131],"inhibit":[83],"from":[86,140],"an":[88],"since":[91],"correlations":[93],"two":[95],"are":[97],"implicitly":[98],"incorporated.":[99],"Indeed,":[100],"reduce":[106],"semantic":[108],"gap":[109],"different":[111,172,193],"explicitly":[114],"guide":[115],"procedure.":[119],"In":[120],"addition,":[121],"large":[123,211],"quantities":[124],"unpaired":[126,179,222],"or":[129],"provide":[132],"useful":[133],"side":[134],"enrich":[137],"representations":[139,170,191],"learned":[141],"subspace.":[142],"Thus,":[143],"in":[144],"this":[145],"paper":[146],"we":[147],"propose":[148],"novel":[150],"model":[151,230],"for":[152,171],"problem.":[155],"It":[156],"consists":[157],"1)":[159],"semi-supervised":[161],"coupled":[162,183],"dictionary":[163],"step":[165,186],"generate":[167],"homogeneously":[168],"sparse":[169,190],"based":[174],"both":[176,218],"samples;":[180],"2)":[181],"feature":[184],"mapping":[185],"project":[188],"into":[195],"defined":[199],"by":[200],"perform":[205],"matching.":[207],"Experiments":[208],"scale":[212],"web":[213],"image":[214],"dataset":[215],"MIRFlickr-1M":[216],"settings":[223],"show":[224],"effectiveness":[226],"proposed":[229],"task.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}