{"id":"https://openalex.org/W1964073652","doi":"https://doi.org/10.1145/2647868.2654902","title":"Cross-modal Retrieval with Correspondence Autoencoder","display_name":"Cross-modal Retrieval with Correspondence Autoencoder","publication_year":2014,"publication_date":"2014-10-31","ids":{"openalex":"https://openalex.org/W1964073652","doi":"https://doi.org/10.1145/2647868.2654902","mag":"1964073652"},"language":"en","primary_location":{"id":"doi:10.1145/2647868.2654902","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2647868.2654902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Multimedia","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/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":true,"raw_author_name":"Fangxiang Feng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"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"],"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/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"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5013283012"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":28.1731,"has_fulltext":false,"cited_by_count":598,"citation_normalized_percentile":{"value":0.99761533,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7","last_page":"16"},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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":0.9987000226974487,"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":0.93555748462677},{"id":"https://openalex.org/keywords/canonical-correlation","display_name":"Canonical correlation","score":0.696068525314331},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6716344356536865},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6607709527015686},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.650733232498169},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6450462937355042},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5646560192108154},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5564520359039307},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5179395079612732},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.48546841740608215},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.43999993801116943},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.4397393763065338},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4333977699279785},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4030754864215851},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22451022267341614}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.93555748462677},{"id":"https://openalex.org/C153874254","wikidata":"https://www.wikidata.org/wiki/Q115542","display_name":"Canonical correlation","level":2,"score":0.696068525314331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6716344356536865},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6607709527015686},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.650733232498169},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6450462937355042},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5646560192108154},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5564520359039307},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5179395079612732},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.48546841740608215},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.43999993801116943},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.4397393763065338},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4333977699279785},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4030754864215851},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22451022267341614},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"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/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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2647868.2654902","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2647868.2654902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.44999998807907104}],"awards":[{"id":"https://openalex.org/G1321958002","display_name":null,"funder_award_id":"2012AA011103","funder_id":"https://openalex.org/F4320321540","funder_display_name":"Ministry of Science and Technology of the People's Republic of China"},{"id":"https://openalex.org/G249685275","display_name":null,"funder_award_id":"61273365","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321470","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59"},{"id":"https://openalex.org/F4320321540","display_name":"Ministry of Science and Technology of the People's Republic of China","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1566135517","https://openalex.org/W1880262756","https://openalex.org/W1897761818","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/W2148596671","https://openalex.org/W2164587673","https://openalex.org/W2187089797","https://openalex.org/W2251749059","https://openalex.org/W2294512729","https://openalex.org/W2557865186","https://openalex.org/W2950276680","https://openalex.org/W4231109964"],"related_works":["https://openalex.org/W2983142544","https://openalex.org/W2891059443","https://openalex.org/W4281663961","https://openalex.org/W3208888551","https://openalex.org/W4313561566","https://openalex.org/W3208386644","https://openalex.org/W4220682630","https://openalex.org/W3181622257","https://openalex.org/W4389832810","https://openalex.org/W3133533225"],"abstract_inverted_index":{"The":[0,35,155],"problem":[1],"of":[2,43,56,70,83,103,116],"cross-modal":[3,193],"retrieval,":[4],"e.g.,":[5],"using":[6],"a":[7,53,80],"text":[8],"query":[9],"to":[10,75,90,113,124,144],"search":[11],"for":[12,31,60],"images":[13],"and":[14,63,130,153,186],"vice-versa,":[15],"is":[16,28,37,73,122,142],"considered":[17],"in":[18,98],"this":[19,33],"paper.":[20],"A":[21,47,119],"novel":[22,48],"model":[23,36,78,89],"involving":[24],"correspondence":[25,147,174],"autoencoder":[26],"(Corr-AE)":[27],"proposed":[29,156],"here":[30,149],"solving":[32],"problem.":[34],"constructed":[38],"by":[39],"correlating":[40],"hidden":[41,68,92,108],"representations":[42,69,93,109],"two":[44,71,137,146,187],"uni-modal":[45],"autoencoders.":[46],"optimal":[49],"objective,":[50],"which":[51],"minimizes":[52],"linear":[54],"combination":[55],"representation":[57,104,127],"learning":[58,65,85,105,128,133],"errors":[59],"each":[61,117],"modality":[62],"correlation":[64,84,132,182],"error":[66,86,106,129],"between":[67],"modalities,":[72,100],"used":[74,123],"train":[76],"the":[77,88,126,131,172],"as":[79],"whole.":[81],"Minimization":[82],"forces":[87],"learn":[91],"with":[94],"only":[95],"common":[96],"information":[97],"different":[99,138],"while":[101],"minimization":[102],"makes":[107],"are":[110,158],"good":[111],"enough":[112],"reconstruct":[114],"input":[115],"modality.":[118],"parameter":[120],"$\\alpha$":[121],"balance":[125],"error.":[134],"Based":[135],"on":[136,160,192],"multi-modal":[139,189],"autoencoders,":[140],"Corr-AE":[141],"extended":[143],"other":[145],"models,":[148],"we":[150],"called":[151],"Corr-Cross-AE":[152],"Corr-Full-AE.":[154],"models":[157,185,191],"evaluated":[159],"three":[161,173,180],"publicly":[162],"available":[163],"data":[164],"sets":[165],"from":[166],"real":[167],"scenes.":[168],"We":[169],"demonstrate":[170],"that":[171],"autoencoders":[175],"perform":[176],"significantly":[177],"better":[178],"than":[179],"canonical":[181],"analysis":[183],"based":[184],"popular":[188],"deep":[190],"retrieval":[194],"tasks.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":34},{"year":2023,"cited_by_count":40},{"year":2022,"cited_by_count":62},{"year":2021,"cited_by_count":82},{"year":2020,"cited_by_count":81},{"year":2019,"cited_by_count":97},{"year":2018,"cited_by_count":71},{"year":2017,"cited_by_count":60},{"year":2016,"cited_by_count":35},{"year":2015,"cited_by_count":18},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}