{"id":"https://openalex.org/W2032001302","doi":"https://doi.org/10.1145/2808205","title":"Correspondence Autoencoders for Cross-Modal Retrieval","display_name":"Correspondence Autoencoders for Cross-Modal Retrieval","publication_year":2015,"publication_date":"2015-10-21","ids":{"openalex":"https://openalex.org/W2032001302","doi":"https://doi.org/10.1145/2808205","mag":"2032001302"},"language":"en","primary_location":{"id":"doi:10.1145/2808205","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2808205","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"letter","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/A5013283012","display_name":"Fangxiang Feng","orcid":"https://orcid.org/0000-0002-4798-4233"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangxiang Feng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351304","display_name":"Xiaojie Wang","orcid":"https://orcid.org/0000-0003-0314-8951"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojie Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068728736","display_name":"Ruifan Li","orcid":"https://orcid.org/0000-0002-3543-6272"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruifan Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101795236","display_name":"Ibrar Ahmad","orcid":"https://orcid.org/0000-0001-6206-3160"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I36001604","display_name":"University of Peshawar","ror":"https://ror.org/02t2qwf81","country_code":"PK","type":"education","lineage":["https://openalex.org/I36001604"]}],"countries":["CN","PK"],"is_corresponding":false,"raw_author_name":"Ibrar Ahmad","raw_affiliation_strings":["Beijing University of Posts and Telecommunications and University of Peshawar, Pakistan","Beijing University of Posts and Telecommunications and University of Peshawar, Pakistan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications and University of Peshawar, Pakistan","institution_ids":["https://openalex.org/I36001604"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications and University of Peshawar, Pakistan#TAB#","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":"1s","first_page":"1","last_page":"22"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9991999864578247,"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":0.9977999925613403,"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/autoencoder","display_name":"Autoencoder","score":0.8858102560043335},{"id":"https://openalex.org/keywords/canonical-correlation","display_name":"Canonical correlation","score":0.7324240207672119},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7222638726234436},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6803605556488037},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6635333299636841},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6398659348487854},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6386610269546509},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5436519980430603},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5193270444869995},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4804539084434509},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.48011136054992676},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4772893488407135},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.440742164850235},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.44035598635673523},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19304025173187256}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8858102560043335},{"id":"https://openalex.org/C153874254","wikidata":"https://www.wikidata.org/wiki/Q115542","display_name":"Canonical correlation","level":2,"score":0.7324240207672119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7222638726234436},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6803605556488037},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6635333299636841},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6398659348487854},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6386610269546509},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5436519980430603},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5193270444869995},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4804539084434509},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.48011136054992676},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4772893488407135},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.440742164850235},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.44035598635673523},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19304025173187256},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2808205","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2808205","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G249685275","display_name":"\u57fa\u4e8e\u513f\u7ae5\u8bed\u8a00\u4e60\u5f97\u673a\u5236\u7684\u8bed\u8a00\u63a5\u5730\u6280\u672f\u7814\u7a76","funder_award_id":"61273365","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4260822342","display_name":null,"funder_award_id":"2013RC0304","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1566135517","https://openalex.org/W1880262756","https://openalex.org/W1897761818","https://openalex.org/W1964073652","https://openalex.org/W2007972815","https://openalex.org/W2020842694","https://openalex.org/W2038770598","https://openalex.org/W2066941820","https://openalex.org/W2071709160","https://openalex.org/W2100002341","https://openalex.org/W2100235303","https://openalex.org/W2100495367","https://openalex.org/W2102765684","https://openalex.org/W2106277773","https://openalex.org/W2109506130","https://openalex.org/W2115752676","https://openalex.org/W2116064496","https://openalex.org/W2123024445","https://openalex.org/W2124914669","https://openalex.org/W2136922672","https://openalex.org/W2143017621","https://openalex.org/W2148596671","https://openalex.org/W2164587673","https://openalex.org/W2184188583","https://openalex.org/W2187089797","https://openalex.org/W2241862190","https://openalex.org/W2250742840","https://openalex.org/W2251749059","https://openalex.org/W2294512729","https://openalex.org/W2557865186","https://openalex.org/W2560674852","https://openalex.org/W2610593052","https://openalex.org/W2950276680","https://openalex.org/W3207342693","https://openalex.org/W4231109964","https://openalex.org/W4251372957"],"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":{"This":[0],"article":[1],"considers":[2],"the":[3,57,65,79,85,90,105,122,145,147],"problem":[4],"of":[5,42,45,56,72,117,125],"cross-modal":[6,228],"retrieval,":[7],"such":[8],"as":[9,81],"using":[10],"a":[11,43,53,82,136,189],"text":[12],"query":[13],"to":[14,77,92,114,144,150],"search":[15],"for":[16,30,61],"images":[17],"and":[18,64,131,221],"vice-versa.":[19],"Based":[20],"on":[21,197,227],"different":[22,101],"autoencoders,":[23],"several":[24],"novel":[25,48],"models":[26,35,148,162,179,194,220,226],"are":[27,36,153,195],"proposed":[28,193,208],"here":[29],"solving":[31],"this":[32],"problem.":[33],"These":[34],"constructed":[37],"by":[38,128],"correlating":[39],"hidden":[40,70,94,110],"representations":[41,71,95,111],"pair":[44],"autoencoders.":[46],"A":[47],"optimal":[49],"objective,":[50],"which":[51],"minimizes":[52],"linear":[54],"combination":[55],"representation":[58,106,129],"learning":[59,67,87,107,130],"errors":[60,126],"each":[62,118],"modality":[63],"correlation":[66,86,132,217],"error":[68,88,108],"between":[69],"two":[73,123,156,178,222],"modalities,":[74,102],"is":[75,163,180],"used":[76],"train":[78],"model":[80,91],"whole.":[83],"Minimizing":[84],"forces":[89],"learn":[93],"with":[96],"only":[97],"common":[98],"information":[99],"in":[100,139],"while":[103],"minimizing":[104],"makes":[109],"good":[112],"enough":[113],"reconstruct":[115,151],"inputs":[116],"modality.":[119,191],"To":[120],"balance":[121],"kind":[124],"induced":[127],"learning,":[133],"we":[134],"set":[135],"specific":[137],"parameter":[138],"our":[140,203,207],"models.":[141],"Furthermore,":[142],"according":[143],"modalities":[146],"attempt":[149],"they":[152],"divided":[154],"into":[155],"groups.":[157],"One":[158],"group":[159,176],"including":[160,177],"three":[161,198,215],"named":[164,181],"multimodal":[165,224],"reconstruction":[166,183],"correspondence":[167,184,209],"autoencoder":[168,185],"since":[169,186],"it":[170,187],"reconstructs":[171,188],"both":[172],"modalities.":[173],"The":[174,192],"other":[175],"unimodal":[182],"single":[190],"evaluated":[196],"publicly":[199],"available":[200],"datasets.":[201],"And":[202],"experiments":[204],"demonstrate":[205],"that":[206],"autoencoders":[210],"perform":[211],"significantly":[212],"better":[213],"than":[214],"canonical":[216],"analysis":[218],"based":[219],"popular":[223],"deep":[225],"retrieval":[229],"tasks.":[230]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}