{"id":"https://openalex.org/W3017098848","doi":"https://doi.org/10.1109/tcyb.2020.2985716","title":"SMAN: Stacked Multimodal Attention Network for Cross-Modal Image\u2013Text Retrieval","display_name":"SMAN: Stacked Multimodal Attention Network for Cross-Modal Image\u2013Text Retrieval","publication_year":2020,"publication_date":"2020-05-04","ids":{"openalex":"https://openalex.org/W3017098848","doi":"https://doi.org/10.1109/tcyb.2020.2985716","mag":"3017098848","pmid":"https://pubmed.ncbi.nlm.nih.gov/32386178"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2020.2985716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2020.2985716","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5005367680","display_name":"Zhong Ji","orcid":"https://orcid.org/0000-0002-2197-3739"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhong Ji","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China","[School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China (e-mail:jizhong@tju.edu.cn)]"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"[School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China (e-mail:jizhong@tju.edu.cn)]","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102813363","display_name":"Haoran Wang","orcid":"https://orcid.org/0000-0002-6098-4772"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Wang","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China","[School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China (e-mail:haoranwang@tju.edu.cn)]"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"[School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China (e-mail:haoranwang@tju.edu.cn)]","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046605531","display_name":"Jungong Han","orcid":"https://orcid.org/0000-0003-4361-956X"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jungong Han","raw_affiliation_strings":["Data Science Group, University of Warwick, Coventry, U.K","[Data Science Group, University of Warwick, Coventry CV4 7AL, U.K..]"],"affiliations":[{"raw_affiliation_string":"Data Science Group, University of Warwick, Coventry, U.K","institution_ids":["https://openalex.org/I39555362"]},{"raw_affiliation_string":"[Data Science Group, University of Warwick, Coventry CV4 7AL, U.K..]","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086887025","display_name":"Yanwei Pang","orcid":"https://orcid.org/0000-0001-6670-3727"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwei Pang","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China","school of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"school of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005367680"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":3.2241,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.93359099,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"52","issue":"2","first_page":"1086","last_page":"1097"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9980000257492065,"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/modal","display_name":"Modal","score":0.6786098480224609},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5971873998641968},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5079758763313293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4432690441608429},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37322908639907837},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3368834853172302},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.327735960483551},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.11556699872016907}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6786098480224609},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5971873998641968},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5079758763313293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4432690441608429},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37322908639907837},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3368834853172302},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.327735960483551},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.11556699872016907},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1109/tcyb.2020.2985716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2020.2985716","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","raw_type":"journal-article"},{"id":"pmid:32386178","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32386178","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on cybernetics","raw_type":null},{"id":"pmh:oai:wrap.warwick.ac.uk:135302","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400665","display_name":"Warwick Research Archive Portal (University of Warwick)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39555362","host_organization_name":"University of Warwick","host_organization_lineage":["https://openalex.org/I39555362"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7799999713897705,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G11847706","display_name":null,"funder_award_id":"61632018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3635174350","display_name":null,"funder_award_id":"19JCYBJC16000","funder_id":"https://openalex.org/F4320323993","funder_display_name":"Natural Science Foundation of Tianjin City"},{"id":"https://openalex.org/G3732680637","display_name":null,"funder_award_id":"61771329","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/F4320323993","display_name":"Natural Science Foundation of Tianjin City","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1916445035","https://openalex.org/W1949478088","https://openalex.org/W1957706851","https://openalex.org/W2100235303","https://openalex.org/W2105482032","https://openalex.org/W2106277773","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2326180695","https://openalex.org/W2342543219","https://openalex.org/W2461972671","https://openalex.org/W2463955103","https://openalex.org/W2467139031","https://openalex.org/W2546696630","https://openalex.org/W2552579943","https://openalex.org/W2584535601","https://openalex.org/W2606473278","https://openalex.org/W2606965845","https://openalex.org/W2739181657","https://openalex.org/W2745461083","https://openalex.org/W2768454054","https://openalex.org/W2778100917","https://openalex.org/W2778940641","https://openalex.org/W2795832645","https://openalex.org/W2798280084","https://openalex.org/W2799150641","https://openalex.org/W2888166343","https://openalex.org/W2890732922","https://openalex.org/W2894786240","https://openalex.org/W2896798564","https://openalex.org/W2898403805","https://openalex.org/W2912738862","https://openalex.org/W2933775054","https://openalex.org/W2938728617","https://openalex.org/W2955058313","https://openalex.org/W2956018683","https://openalex.org/W2962851485","https://openalex.org/W2962964995","https://openalex.org/W2962965405","https://openalex.org/W2963000732","https://openalex.org/W2963389687","https://openalex.org/W2963467339","https://openalex.org/W2963882743","https://openalex.org/W2963954913","https://openalex.org/W2964120214","https://openalex.org/W2964130424","https://openalex.org/W2964167369","https://openalex.org/W2966226927","https://openalex.org/W2981586349","https://openalex.org/W2986510250","https://openalex.org/W2990571534","https://openalex.org/W6631516269","https://openalex.org/W6638742206","https://openalex.org/W6685183736","https://openalex.org/W6735377749","https://openalex.org/W6737778391","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W2714992399","https://openalex.org/W2383812217","https://openalex.org/W2326515389","https://openalex.org/W2491005386"],"abstract_inverted_index":{"This":[0],"article":[1],"focuses":[2],"on":[3,210],"tackling":[4],"the":[5,8,35,44,51,57,81,88,97,128,146,160,178,201],"task":[6],"of":[7,39,59,80,99,144,195,204],"cross-modal":[9,108,161],"image-text":[10],"retrieval":[11],"which":[12,156],"has":[13],"been":[14],"an":[15],"interdisciplinary":[16],"topic":[17],"in":[18,153,163],"both":[19],"computer":[20],"vision":[21],"and":[22,41,62,93,116,133],"natural":[23],"language":[24],"processing":[25],"communities.":[26],"Existing":[27],"global":[28],"representation":[29,46],"alignment-based":[30],"methods":[31],"fail":[32],"to":[33,86,121,158,184,191,199,223],"pinpoint":[34],"semantically":[36,147],"meaningful":[37,148],"portion":[38],"images":[40],"texts,":[42],"while":[43],"local":[45],"alignment":[47],"schemes":[48],"suffer":[49],"from":[50],"huge":[52],"computational":[53],"burden":[54],"for":[55,106],"aggregating":[56],"similarity":[58,162],"visual":[60,149],"fragments":[61,101],"textual":[63],"words":[64,152],"exhaustively.":[65],"In":[66],"this":[67],"article,":[68],"we":[69,111,141,169],"propose":[70],"a":[71,103,139,154,164,171],"stacked":[72,82],"multimodal":[73,83,117,182],"attention":[74,84,124],"network":[75],"(SMAN)":[76],"that":[77,127,176,215],"makes":[78],"use":[79,194],"mechanism":[85],"exploit":[87],"fine-grained":[89,129],"interdependencies":[90],"between":[91,131],"image":[92,132],"text,":[94],"thereby":[95],"mapping":[96],"aggregation":[98],"attentive":[100],"into":[102],"common":[104],"space":[105],"measuring":[107,159],"similarity.":[109],"Specifically,":[110],"sequentially":[112],"employ":[113],"intramodal":[114],"information":[115,118,198],"as":[119],"guidance":[120],"perform":[122],"multiple-step":[123],"reasoning":[125],"so":[126,188],"correlation":[130],"text":[134],"can":[135],"be":[136,185],"modeled.":[137],"As":[138],"consequence,":[140],"are":[142],"capable":[143],"discovering":[145],"regions":[150],"or":[151],"sentence":[155],"contributes":[157],"more":[165],"precise":[166],"manner.":[167],"Moreover,":[168],"present":[170],"novel":[172],"bidirectional":[173],"ranking":[174],"loss":[175],"enforces":[177],"distance":[179],"among":[180],"pairwise":[181,196,206],"instances":[183],"closer.":[186],"Doing":[187],"allows":[189],"us":[190],"make":[192],"full":[193],"supervised":[197],"preserve":[200],"manifold":[202],"structure":[203],"heterogeneous":[205],"data.":[207],"Extensive":[208],"experiments":[209],"two":[211],"benchmark":[212],"datasets":[213],"demonstrate":[214],"our":[216],"SMAN":[217],"consistently":[218],"yields":[219],"competitive":[220],"performance":[221],"compared":[222],"state-of-the-art":[224],"methods.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":9}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}
