{"id":"https://openalex.org/W4225774139","doi":"https://doi.org/10.1109/tnnls.2022.3168431","title":"Keyword-Based Diverse Image Retrieval With Variational Multiple Instance Graph","display_name":"Keyword-Based Diverse Image Retrieval With Variational Multiple Instance Graph","publication_year":2022,"publication_date":"2022-04-28","ids":{"openalex":"https://openalex.org/W4225774139","doi":"https://doi.org/10.1109/tnnls.2022.3168431"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2022.3168431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3168431","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","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/A5017828551","display_name":"Yawen Zeng","orcid":"https://orcid.org/0000-0003-1908-1157"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yawen Zeng","raw_affiliation_strings":["Department of WeChat, Tencent Inc., Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of WeChat, Tencent Inc., Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100319145","display_name":"Yiru Wang","orcid":"https://orcid.org/0009-0006-2193-6686"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiru Wang","raw_affiliation_strings":["Department of WeChat, Tencent Inc., Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of WeChat, Tencent Inc., Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053595500","display_name":"Dongliang Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongliang Liao","raw_affiliation_strings":["Department of WeChat, Tencent Inc., Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of WeChat, Tencent Inc., Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003577897","display_name":"Gongfu Li","orcid":"https://orcid.org/0000-0003-0655-5317"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gongfu Li","raw_affiliation_strings":["Department of WeChat, Tencent Inc., Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of WeChat, Tencent Inc., Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100643508","display_name":"Weijie Huang","orcid":"https://orcid.org/0009-0003-6017-0474"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijie Huang","raw_affiliation_strings":["Department of WeChat, Tencent Inc., Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of WeChat, Tencent Inc., Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038610034","display_name":"Jin Xu","orcid":"https://orcid.org/0000-0001-6738-9979"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Xu","raw_affiliation_strings":["School of Future Technology, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Future Technology, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078164599","display_name":"Da Cao","orcid":"https://orcid.org/0000-0002-2611-2559"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Da Cao","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069857153","display_name":"Hong Man","orcid":"https://orcid.org/0000-0002-8892-3066"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong Man","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Stevens Institute of Technology, Hoboken, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Stevens Institute of Technology, Hoboken, NJ, USA","institution_ids":["https://openalex.org/I108468826"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5017828551"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":1.5291,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.83609533,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"34","issue":"12","first_page":"10528","last_page":"10537"},"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":0.9979000091552734,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9965999722480774,"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":0.7995805144309998},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.6422572135925293},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6325843334197998},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6258041858673096},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.48789119720458984},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4809124171733856},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4752742350101471},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4150833785533905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3706057071685791},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.29200148582458496},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2813190221786499},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.19776973128318787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7995805144309998},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6422572135925293},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6325843334197998},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6258041858673096},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.48789119720458984},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4809124171733856},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4752742350101471},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4150833785533905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3706057071685791},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.29200148582458496},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2813190221786499},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.19776973128318787},{"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tnnls.2022.3168431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3168431","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1596649971","https://openalex.org/W1975692209","https://openalex.org/W2088884958","https://openalex.org/W2106277773","https://openalex.org/W2112037975","https://openalex.org/W2131744502","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2295691670","https://openalex.org/W2295853834","https://openalex.org/W2398606097","https://openalex.org/W2408636378","https://openalex.org/W2527238922","https://openalex.org/W2594785588","https://openalex.org/W2606965845","https://openalex.org/W2742000522","https://openalex.org/W2765440071","https://openalex.org/W2771110965","https://openalex.org/W2773442144","https://openalex.org/W2903664715","https://openalex.org/W2946298263","https://openalex.org/W2954793896","https://openalex.org/W2955894817","https://openalex.org/W2956018683","https://openalex.org/W2963340196","https://openalex.org/W2963389687","https://openalex.org/W2967957126","https://openalex.org/W2981951787","https://openalex.org/W2997297138","https://openalex.org/W3016451726","https://openalex.org/W3017267450","https://openalex.org/W3017313555","https://openalex.org/W3035256320","https://openalex.org/W3035454331","https://openalex.org/W3046554305","https://openalex.org/W3048886518","https://openalex.org/W3093002089","https://openalex.org/W3093206850","https://openalex.org/W3093493377","https://openalex.org/W3155865710","https://openalex.org/W3176471072","https://openalex.org/W3176913643","https://openalex.org/W3177445943","https://openalex.org/W3179442710","https://openalex.org/W3206019042","https://openalex.org/W4212848270","https://openalex.org/W4294558607","https://openalex.org/W4385245566","https://openalex.org/W4400433329","https://openalex.org/W6679775712","https://openalex.org/W6696999132","https://openalex.org/W6697201839","https://openalex.org/W6713922003","https://openalex.org/W6738964360","https://openalex.org/W6739901393","https://openalex.org/W6746086056","https://openalex.org/W6746825264","https://openalex.org/W6870024233"],"related_works":["https://openalex.org/W2393699422","https://openalex.org/W2168037874","https://openalex.org/W2387268739","https://openalex.org/W4250138412","https://openalex.org/W2135728080","https://openalex.org/W2379546782","https://openalex.org/W2534443799","https://openalex.org/W2148968119","https://openalex.org/W2391460410","https://openalex.org/W1658719554"],"abstract_inverted_index":{"The":[0],"task":[1,111],"of":[2,77,140,148,201],"cross-modal":[3,47,78,179],"image":[4,48,150],"retrieval":[5,34,49,66,110,207],"has":[6],"recently":[7],"attracted":[8],"considerable":[9],"research":[10],"attention.":[11],"In":[12],"real-world":[13,194],"scenarios,":[14],"keyword-based":[15],"queries":[16],"issued":[17],"by":[18,155],"users":[19],"are":[20,153,184],"usually":[21],"short":[22],"and":[23,108,151,162,177,209],"have":[24,196],"broad":[25],"semantics.":[26,180],"Therefore,":[27],"semantic":[28,61,99,137,160,210],"diversity":[29],"is":[30,101,112,131,171],"as":[31,33,114],"important":[32],"accuracy":[35,72,208],"in":[36,59,95,157,205],"such":[37],"user-oriented":[38],"services,":[39],"which":[40,96],"improves":[41],"user":[42],"experience.":[43],"However,":[44],"most":[45],"typical":[46],"methods":[50],"based":[51],"on":[52,192],"single":[53],"point":[54],"query":[55,106,152],"embedding":[56],"inevitably":[57],"result":[58],"low":[60,71],"diversity,":[62],"while":[63],"existing":[64],"diverse":[65,105,122],"approaches":[67],"frequently":[68],"lead":[69],"to":[70,74,103,120,133,173],"due":[73],"a":[75,97,115,127,142],"lack":[76],"understanding.":[79],"To":[80],"address":[81],"this":[82],"challenge,":[83],"we":[84],"introduce":[85],"an":[86,168],"end-to-end":[87],"solution":[88,204],"termed":[89],"variational":[90,129],"multiple":[91,116,146,188],"instance":[92,117,169],"graph":[93,170],"(VMIG),":[94],"continuous":[98,136,159],"space":[100,138,161],"learned":[102],"capture":[104],"semantics,":[107],"the":[109,135,149,158,199],"formulated":[113],"learning":[118,141],"problems":[119],"connect":[121],"features":[123],"across":[124],"modalities.":[125],"Specifically,":[126],"query-guided":[128],"autoencoder":[130],"employed":[132],"model":[134],"instead":[139],"single-point":[143],"embedding.":[144],"Afterward,":[145],"instances":[147,176],"obtained":[154],"sampling":[156],"applying":[163],"multihead":[164],"attention,":[165],"respectively.":[166],"Thereafter,":[167],"constructed":[172],"remove":[174],"noisy":[175],"align":[178],"Finally,":[181],"heterogeneous":[182],"modalities":[183],"robustly":[185],"fused":[186],"under":[187],"losses.":[189],"Extensive":[190],"experiments":[191],"two":[193],"datasets":[195],"well":[197],"verified":[198],"effectiveness":[200],"our":[202],"proposed":[203],"both":[206],"diversity.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":8}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}