{"id":"https://openalex.org/W2962529143","doi":"https://doi.org/10.1145/3314577","title":"Cross-Modality Retrieval by Joint Correlation Learning","display_name":"Cross-Modality Retrieval by Joint Correlation Learning","publication_year":2019,"publication_date":"2019-04-30","ids":{"openalex":"https://openalex.org/W2962529143","doi":"https://doi.org/10.1145/3314577","mag":"2962529143"},"language":"en","primary_location":{"id":"doi:10.1145/3314577","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3314577","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":"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/A5051448188","display_name":"Shuo Wang","orcid":"https://orcid.org/0000-0001-6599-3638"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuo Wang","raw_affiliation_strings":["School of Computer Science and Information Engineering, School of Artificial Intelligence, Hefei University of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, School of Artificial Intelligence, Hefei University of Technology, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059530979","display_name":"Dan Guo","orcid":"https://orcid.org/0000-0003-2594-254X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Guo","raw_affiliation_strings":["School of Computer Science and Information Engineering, School of Artificial Intelligence, Hefei University of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, School of Artificial Intelligence, Hefei University of Technology, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100696102","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0003-0748-3669"},"institutions":[{"id":"https://openalex.org/I43922553","display_name":"Wuhan University of Science and Technology","ror":"https://ror.org/00e4hrk88","country_code":"CN","type":"education","lineage":["https://openalex.org/I43922553"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xu","raw_affiliation_strings":["College of Computer Science 8 Technology, Wuhan University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science 8 Technology, Wuhan University of Science and Technology, China","institution_ids":["https://openalex.org/I43922553"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100448036","display_name":"Zhuo Li","orcid":"https://orcid.org/0000-0002-9937-2669"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhuo","raw_affiliation_strings":["Signal 8 Information Processing Laboratory, Beijing University of Technology, China"],"affiliations":[{"raw_affiliation_string":"Signal 8 Information Processing Laboratory, Beijing University of Technology, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100377147","display_name":"Meng Wang","orcid":"https://orcid.org/0000-0002-3094-7735"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["School of Computer Science and Information Engineering, School of Artificial Intelligence, Hefei University of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, School of Artificial Intelligence, Hefei University of Technology, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5051448188"],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":1.4171,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.8538432,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"15","issue":"2s","first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9995999932289124,"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":0.9940999746322632,"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":0.8219560384750366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6064304113388062},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5442344546318054},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.517473042011261},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.48201289772987366},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4803708493709564},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4793192148208618},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45702311396598816},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.44113689661026},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37433695793151855}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8219560384750366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6064304113388062},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5442344546318054},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.517473042011261},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.48201289772987366},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4803708493709564},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4793192148208618},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45702311396598816},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.44113689661026},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37433695793151855},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3314577","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3314577","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5899999737739563}],"awards":[{"id":"https://openalex.org/G6255571428","display_name":null,"funder_award_id":"61725203, 61732008, 61876058","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W205822829","https://openalex.org/W310972808","https://openalex.org/W1527575280","https://openalex.org/W1546503963","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1916445035","https://openalex.org/W1931639407","https://openalex.org/W1931795219","https://openalex.org/W1949478088","https://openalex.org/W1957706851","https://openalex.org/W1964073652","https://openalex.org/W1977177161","https://openalex.org/W1985690171","https://openalex.org/W2012689760","https://openalex.org/W2037722773","https://openalex.org/W2042708146","https://openalex.org/W2096733369","https://openalex.org/W2097117768","https://openalex.org/W2106277773","https://openalex.org/W2124386111","https://openalex.org/W2129156852","https://openalex.org/W2161969291","https://openalex.org/W2163605009","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2210322478","https://openalex.org/W2284126738","https://openalex.org/W2287451110","https://openalex.org/W2293546405","https://openalex.org/W2340690086","https://openalex.org/W2346425926","https://openalex.org/W2465870074","https://openalex.org/W2526428212","https://openalex.org/W2552579943","https://openalex.org/W2685669664","https://openalex.org/W2744926832","https://openalex.org/W2766623491","https://openalex.org/W2778940641","https://openalex.org/W2896487916","https://openalex.org/W2949117887","https://openalex.org/W2949967295","https://openalex.org/W2950133940","https://openalex.org/W2962706528","https://openalex.org/W2962714319","https://openalex.org/W2962835968","https://openalex.org/W2963051286","https://openalex.org/W2963389687","https://openalex.org/W2964138343","https://openalex.org/W3000226596","https://openalex.org/W3099206234"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2081900870","https://openalex.org/W2530972254","https://openalex.org/W3111219495","https://openalex.org/W2374013449","https://openalex.org/W2181948922","https://openalex.org/W2375873920","https://openalex.org/W73545470","https://openalex.org/W2384362569","https://openalex.org/W4283320496"],"abstract_inverted_index":{"As":[0],"an":[1,58],"indispensable":[2],"process":[3],"of":[4,15,71,110,117,165],"cross-media":[5],"analyzing,":[6],"comprehending":[7],"heterogeneous":[8],"data":[9],"faces":[10],"challenges":[11],"in":[12,43,158],"the":[13,26,30,41,64,69,83,97,100,103,107,113,121,131,136,159,163,166,174],"fields":[14],"visual":[16,20,65,111],"question":[17],"answering":[18],"(VQA),":[19],"captioning,":[21],"and":[22,74,99,120,127,145,182],"cross-modality":[23,44],"retrieval.":[24],"Bridging":[25],"semantic":[27],"gap":[28],"between":[29,125],"two":[31],"modalities":[32],"is":[33,60,79],"still":[34],"difficult.":[35],"In":[36,130],"this":[37],"article,":[38],"to":[39,62,81,94,152,173],"address":[40],"problem":[42],"retrieval,":[45],"we":[46,88,134],"propose":[47],"a":[48,75,90,141],"cross-modal":[49],"learning":[50],"model":[51,82],"with":[52],"joint":[53,91,137],"correlative":[54],"calculation":[55],"learning.":[56],"First,":[57],"auto-encoder":[59],"used":[61],"embed":[63],"features":[66,85],"by":[67],"minimizing":[68],"error":[70],"feature":[72],"reconstruction":[73,108],"multi-layer":[76],"perceptron":[77],"(MLP)":[78],"utilized":[80],"textual":[84],"embedding.":[86],"Then":[87],"design":[89],"loss":[92,109,116,124,138],"function":[93],"optimize":[95,135],"both":[96],"intra-":[98],"inter-correlations":[101],"among":[102],"image-sentence":[104],"pairs,":[105],"i.e.,":[106,179],"features,":[112],"relevant":[114],"similarity":[115],"paired":[118,150],"samples,":[119],"triplet":[122],"relation":[123],"positive":[126],"negative":[128],"examples.":[129],"proposed":[132,167],"method,":[133],"based":[139],"on":[140,176],"batch":[142],"score":[143],"matrix":[144],"utilize":[146],"all":[147],"mutual":[148],"mismatched":[149],"samples":[151],"enhance":[153],"its":[154],"performance.":[155],"Our":[156],"experiments":[157],"retrieval":[160],"tasks":[161],"demonstrate":[162],"effectiveness":[164],"method.":[168],"It":[169],"achieves":[170],"comparable":[171],"performance":[172],"state-of-the-art":[175],"three":[177],"benchmarks,":[178],"Flickr8k,":[180],"Flickr30k,":[181],"MS-COCO.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2019-07-23T00:00:00"}