{"id":"https://openalex.org/W4390100115","doi":"https://doi.org/10.1016/j.vrih.2023.06.003","title":"Adequate alignment and interaction for cross-modal retrieval","display_name":"Adequate alignment and interaction for cross-modal retrieval","publication_year":2023,"publication_date":"2023-12-01","ids":{"openalex":"https://openalex.org/W4390100115","doi":"https://doi.org/10.1016/j.vrih.2023.06.003"},"language":"en","primary_location":{"id":"doi:10.1016/j.vrih.2023.06.003","doi":"https://doi.org/10.1016/j.vrih.2023.06.003","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.vrih.2023.06.003","pdf_url":null,"source":{"id":"https://openalex.org/S4210224695","display_name":"Virtual Reality & Intelligent Hardware","issn_l":"2096-5796","issn":["2096-5796","2666-1209"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["ccf-c","cwts-core","doaj","norway-1","oarl","poland-20","russia-white-list-2"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Virtual Reality & Intelligent Hardware","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1016/j.vrih.2023.06.003","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"MingKang Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"MingKang Wang","raw_affiliation_strings":["School of Computer Science and Technology, Guangdong University of Technology, Guangzhou 510006, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Guangdong University of Technology, Guangzhou 510006, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048763159","display_name":"Min Meng","orcid":"https://orcid.org/0000-0002-5107-5585","observed_orcids":["https://orcid.org/0000-0002-5107-5585"]},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Meng","raw_affiliation_strings":["School of Computer Science and Technology, Guangdong University of Technology, Guangzhou 510006, China"],"raw_orcid":"https://orcid.org/0000-0002-5107-5585","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Guangdong University of Technology, Guangzhou 510006, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022643176","display_name":"Jigang Liu","orcid":"https://orcid.org/0000-0001-5778-895X","observed_orcids":["https://orcid.org/0000-0001-5778-895X"]},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jigang Liu","raw_affiliation_strings":["Ping An Life Insurance of China, Shenzhen 518033, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Life Insurance of China, Shenzhen 518033, China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060755096","display_name":"Jigang Wu","orcid":"https://orcid.org/0000-0002-6470-9794","observed_orcids":["https://orcid.org/0000-0002-6470-9794"]},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jigang Wu","raw_affiliation_strings":["School of Computer Science and Technology, Guangdong University of Technology, Guangzhou 510006, China"],"raw_orcid":"https://orcid.org/0000-0002-6470-9794","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Guangdong University of Technology, Guangzhou 510006, China","institution_ids":["https://openalex.org/I139024713"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5060755096"],"corresponding_institution_ids":["https://openalex.org/I139024713"],"apc_list":null,"apc_paid":null,"fwci":3.3891,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.94242712,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":"5","issue":"6","first_page":"509","last_page":"522"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9829000234603882,"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":0.9829000234603882,"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":0.013299999758601189,"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":0.0031999999191612005,"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/cross-modal-retrieval","display_name":"cross-modal retrieval","score":0.9990000128746033},{"id":"https://openalex.org/keywords/image-text-retrieval","display_name":"image-text retrieval","score":0.9589999914169312},{"id":"https://openalex.org/keywords/visual-semantic-embedding","display_name":"visual-semantic embedding","score":0.9430000185966492},{"id":"https://openalex.org/keywords/multimodal-fusion","display_name":"multimodal fusion","score":0.6159999966621399},{"id":"https://openalex.org/keywords/modality-alignment","display_name":"modality alignment","score":0.7519999742507935},{"id":"https://openalex.org/keywords/feature-aggregation","display_name":"feature aggregation","score":0.8489999771118164},{"id":"https://openalex.org/keywords/modality-gap","display_name":"modality gap","score":0.628000020980835},{"id":"https://openalex.org/keywords/encoder-decoder-architecture","display_name":"encoder-decoder architecture","score":0.40700000524520874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8447891473770142},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6286581158638},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6107881665229797},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6083641052246094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5728051662445068},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5328123569488525},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5019609928131104},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.4822472035884857},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4671420753002167},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46411898732185364},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.437024861574173},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.42991945147514343},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4226105213165283},{"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.vrih.2023.06.003","doi":"https://doi.org/10.1016/j.vrih.2023.06.003","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.vrih.2023.06.003","pdf_url":null,"source":{"id":"https://openalex.org/S4210224695","display_name":"Virtual Reality & Intelligent Hardware","issn_l":"2096-5796","issn":["2096-5796","2666-1209"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["ccf-c","cwts-core","doaj","norway-1","oarl","poland-20","russia-white-list-2"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Virtual Reality & Intelligent Hardware","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:40be65072287481280b2e73c7b9f6142","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/40be65072287481280b2e73c7b9f6142","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Virtual Reality & Intelligent Hardware, Vol 5, Iss 6, Pp 509-522 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1016/j.vrih.2023.06.003","doi":"https://doi.org/10.1016/j.vrih.2023.06.003","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.vrih.2023.06.003","pdf_url":null,"source":{"id":"https://openalex.org/S4210224695","display_name":"Virtual Reality & Intelligent Hardware","issn_l":"2096-5796","issn":["2096-5796","2666-1209"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["ccf-c","cwts-core","doaj","norway-1","oarl","poland-20","russia-white-list-2"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Virtual Reality & Intelligent Hardware","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1335214334","display_name":null,"funder_award_id":"62172109","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G558307529","display_name":"\u5206\u5e03\u5f0f\u8fb9\u7f18\u8bad\u7ec3\u52a8\u6001\u8ba1\u7b97\u73af\u5883\u4e0b\u670d\u52a1\u8d28\u91cf\u4fdd\u969c\u7814\u7a76","funder_award_id":"62072118","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6545273877","display_name":null,"funder_award_id":"2022A1515010322","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G663748654","display_name":null,"funder_award_id":"2021B15151 20010","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W93016980","https://openalex.org/W1527575280","https://openalex.org/W1583837637","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1957706851","https://openalex.org/W2123024445","https://openalex.org/W2185175083","https://openalex.org/W2277195237","https://openalex.org/W2289084343","https://openalex.org/W2571899125","https://openalex.org/W2626778328","https://openalex.org/W2765440071","https://openalex.org/W2774267535","https://openalex.org/W2887997457","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2913550731","https://openalex.org/W2936420065","https://openalex.org/W2956018683","https://openalex.org/W2962964995","https://openalex.org/W2963187862","https://openalex.org/W2963467339","https://openalex.org/W2964120214","https://openalex.org/W2965373594","https://openalex.org/W2968124245","https://openalex.org/W2970231061","https://openalex.org/W2971155163","https://openalex.org/W2971720279","https://openalex.org/W2975813532","https://openalex.org/W2981590713","https://openalex.org/W2982183006","https://openalex.org/W2988823324","https://openalex.org/W2991118492","https://openalex.org/W3001555892","https://openalex.org/W3005680577","https://openalex.org/W3014611590","https://openalex.org/W3035454331","https://openalex.org/W3035524453","https://openalex.org/W3035552787","https://openalex.org/W3043840704","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3094751268","https://openalex.org/W3102995547","https://openalex.org/W3108601100","https://openalex.org/W3110042533","https://openalex.org/W3126792443","https://openalex.org/W3139017368","https://openalex.org/W3170874841","https://openalex.org/W3175888430","https://openalex.org/W3184784418","https://openalex.org/W3211483028","https://openalex.org/W4200635843","https://openalex.org/W4239398860","https://openalex.org/W4249009392","https://openalex.org/W4255556797","https://openalex.org/W4283805294","https://openalex.org/W4285531802","https://openalex.org/W4286696412","https://openalex.org/W4293680532","https://openalex.org/W4297808394","https://openalex.org/W4301045096","https://openalex.org/W4312877428","https://openalex.org/W4385574227","https://openalex.org/W4386059972","https://openalex.org/W6763228578","https://openalex.org/W6798047393"],"related_works":["https://openalex.org/W4377236344","https://openalex.org/W2996478685","https://openalex.org/W2962529143","https://openalex.org/W4414605280","https://openalex.org/W4391425520","https://openalex.org/W7164814569","https://openalex.org/W4415754468","https://openalex.org/W4409311340","https://openalex.org/W2963467339","https://openalex.org/W7128386323"],"abstract_inverted_index":{"Cross-modal":[0],"retrieval":[1,14,38,129],"has":[2,32],"attracted":[3],"widespread":[4],"attention":[5],"in":[6,15],"many":[7],"cross-media":[8],"similarity":[9],"search":[10],"applications,":[11],"especially":[12],"image-text":[13,37],"the":[16,89,113,116,156,167,173],"fields":[17],"of":[18,92,115,169],"computer":[19],"vision":[20],"and":[21,27,57,79,111,136,148,163],"natural":[22],"language":[23],"processing.":[24],"Recently,":[25],"visual":[26],"semantic":[28],"embedding":[29],"(VSE)":[30],"learning":[31],"shown":[33],"promising":[34],"improvements":[35],"on":[36,150,160],"tasks.":[39],"Most":[40],"existing":[41,67,95],"VSE":[42],"models":[43,86],"employ":[44],"two":[45,72],"unrelated":[46],"encoders":[47],"to":[48,55,100,107,144],"extract":[49],"features,":[50],"then":[51],"use":[52],"complex":[53],"methods":[54],"contextualize":[56],"aggregate":[58],"those":[59],"features":[60,152],"into":[61],"holistic":[62],"embeddings.":[63],"Despite":[64],"recent":[65],"advances,":[66],"approaches":[68],"still":[69],"suffer":[70],"from":[71],"limitations:":[73],"1)":[74],"without":[75],"considering":[76],"intermediate":[77],"interaction":[78,149],"adequate":[80,146],"alignment":[81,134,147],"between":[82],"different":[83],"modalities,":[84],"these":[85,122],"cannot":[87],"guarantee":[88],"discriminative":[90],"ability":[91],"representations;":[93],"2)":[94],"feature":[96],"aggregators":[97],"are":[98],"susceptible":[99],"certain":[101],"noisy":[102],"regions,":[103],"which":[104,142],"may":[105],"lead":[106],"unreasonable":[108],"pooling":[109],"coefficients":[110],"affect":[112],"quality":[114],"final":[117],"aggregated":[118,151],"features.":[119],"To":[120],"address":[121],"challenges,":[123],"we":[124],"propose":[125],"a":[126,132,137],"novel":[127,138],"cross-modal":[128],"model":[130,171],"containing":[131],"well-designed":[133],"module":[135],"multimodal":[139],"fusion":[140],"encoder,":[141],"aims":[143],"learn":[145],"for":[153],"effectively":[154],"bridging":[155],"modality":[157],"gap.":[158],"Experiments":[159],"Microsoft":[161],"COCO":[162],"Flickr30k":[164],"datasets":[165],"demonstrates":[166],"superiority":[168],"our":[170],"over":[172],"state-of-the-art":[174],"methods.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":24},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-12-23T00:00:00"}