{"id":"https://openalex.org/W2803042791","doi":"https://doi.org/10.1109/access.2018.2844789","title":"Cross-Modal Multistep Fusion Network With Co-Attention for Visual Question Answering","display_name":"Cross-Modal Multistep Fusion Network With Co-Attention for Visual Question Answering","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2803042791","doi":"https://doi.org/10.1109/access.2018.2844789","mag":"2803042791"},"language":"en","primary_location":{"id":"doi:10.1109/access.2018.2844789","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2844789","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2018.2844789","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028043255","display_name":"Mingrui Lao","orcid":"https://orcid.org/0000-0001-8413-7220"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingrui Lao","raw_affiliation_strings":["College of Systems Engineering, National University of Defense Technology, Changsha, China","College of systems engineering, National University of Defense Technology, Changsha, China#TAB#"],"affiliations":[{"raw_affiliation_string":"College of Systems Engineering, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of systems engineering, National University of Defense Technology, Changsha, China#TAB#","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079425523","display_name":"Yanming Guo","orcid":"https://orcid.org/0000-0001-9184-5313"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanming Guo","raw_affiliation_strings":["College of Systems Engineering, National University of Defense Technology, Changsha, China","College of systems engineering, National University of Defense Technology, Changsha, China#TAB#"],"affiliations":[{"raw_affiliation_string":"College of Systems Engineering, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of systems engineering, National University of Defense Technology, Changsha, China#TAB#","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460848","display_name":"Hui Wang","orcid":"https://orcid.org/0000-0002-8745-4042"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Wang","raw_affiliation_strings":["College of Systems Engineering, National University of Defense Technology, Changsha, China","College of systems engineering, National University of Defense Technology, Changsha, China#TAB#"],"affiliations":[{"raw_affiliation_string":"College of Systems Engineering, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of systems engineering, National University of Defense Technology, Changsha, China#TAB#","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103053572","display_name":"Xin Zhang","orcid":"https://orcid.org/0000-0002-4679-4809"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Zhang","raw_affiliation_strings":["College of Systems Engineering, National University of Defense Technology, Changsha, China","College of systems engineering, National University of Defense Technology, Changsha, China#TAB#"],"affiliations":[{"raw_affiliation_string":"College of Systems Engineering, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of systems engineering, National University of Defense Technology, Changsha, China#TAB#","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5028043255"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.3828,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.86017905,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"6","issue":null,"first_page":"31516","last_page":"31524"},"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":0.9986000061035156,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7880226373672485},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7652527689933777},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6573543548583984},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6323373317718506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5865494608879089},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5403035879135132},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5372893810272217},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5280792713165283},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5229407548904419},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47096139192581177},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.45269542932510376},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43229416012763977},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3298197388648987},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32591456174850464},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10195603966712952}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7880226373672485},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7652527689933777},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6573543548583984},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6323373317718506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5865494608879089},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5403035879135132},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5372893810272217},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5280792713165283},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5229407548904419},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47096139192581177},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.45269542932510376},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43229416012763977},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3298197388648987},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32591456174850464},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10195603966712952},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2018.2844789","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2844789","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:68a4250cb548493499c191b340e86d02","is_oa":true,"landing_page_url":"https://doaj.org/article/68a4250cb548493499c191b340e86d02","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 6, Pp 31516-31524 (2018)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2018.2844789","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2844789","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4409688979","display_name":null,"funder_award_id":"61105124","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5315980042","display_name":null,"funder_award_id":"71331008","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":62,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1963882359","https://openalex.org/W2068462894","https://openalex.org/W2117539524","https://openalex.org/W2142192571","https://openalex.org/W2171361956","https://openalex.org/W2176950688","https://openalex.org/W2190656909","https://openalex.org/W2194775991","https://openalex.org/W2216949779","https://openalex.org/W2250539671","https://openalex.org/W2297405797","https://openalex.org/W2326180695","https://openalex.org/W2340874616","https://openalex.org/W2402268235","https://openalex.org/W2463565445","https://openalex.org/W2463955103","https://openalex.org/W2470673105","https://openalex.org/W2520774990","https://openalex.org/W2532034655","https://openalex.org/W2546696630","https://openalex.org/W2563399268","https://openalex.org/W2575842049","https://openalex.org/W2580662672","https://openalex.org/W2613718673","https://openalex.org/W2731821979","https://openalex.org/W2745461083","https://openalex.org/W2767794011","https://openalex.org/W2778100917","https://openalex.org/W2791521493","https://openalex.org/W2919115771","https://openalex.org/W2962891704","https://openalex.org/W2962933067","https://openalex.org/W2963108253","https://openalex.org/W2963143606","https://openalex.org/W2963150162","https://openalex.org/W2963191264","https://openalex.org/W2963383024","https://openalex.org/W2963398599","https://openalex.org/W2963403868","https://openalex.org/W2963608065","https://openalex.org/W2963656855","https://openalex.org/W2963717374","https://openalex.org/W2963900105","https://openalex.org/W2963917086","https://openalex.org/W2963954913","https://openalex.org/W2964118342","https://openalex.org/W2964138017","https://openalex.org/W2964331270","https://openalex.org/W6607333740","https://openalex.org/W6676165494","https://openalex.org/W6676719534","https://openalex.org/W6685230081","https://openalex.org/W6713098461","https://openalex.org/W6715144786","https://openalex.org/W6719057275","https://openalex.org/W6728881024","https://openalex.org/W6729399837","https://openalex.org/W6731895421","https://openalex.org/W6742999658"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2115758952","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W4212839359"],"abstract_inverted_index":{"Visual":[0],"question":[1,71,78],"answering":[2],"(VQA)":[3],"is":[4],"receiving":[5],"increasing":[6],"attention":[7,62],"from":[8],"researchers":[9],"in":[10,25,53,137],"both":[11],"the":[12,26,60,66,69,84,123,127,132,138,144,154,157],"computer":[13],"vision":[14],"and":[15,31,49,98],"natural":[16],"language":[17],"processing":[18],"fields.":[19],"There":[20],"are":[21],"two":[22,103,113],"key":[23],"components":[24],"VQA":[27],"task:":[28],"feature":[29,35,118],"extraction":[30],"multi-modal":[32,85],"fusion.":[33],"For":[34,83],"extraction,":[36],"we":[37,87,130],"introduce":[38],"a":[39,54,89],"novel":[40],"co-attention":[41],"scheme":[42],"by":[43],"combining":[44],"Sentence-guide":[45],"Word":[46],"Attention":[47,52],"(SWA)":[48],"Question-guide":[50],"Image":[51],"unified":[55],"framework.":[56],"To":[57,121],"be":[58],"specific,":[59],"textual":[61],"SWA":[63],"relies":[64],"on":[65,108],"semantics":[67],"of":[68,76,126,156],"whole":[70],"sentence":[72],"to":[73,94],"calculate":[74],"contributions":[75],"different":[77],"words":[79],"for":[80,102,134],"text":[81],"representation.":[82],"fusion,":[86],"propose":[88],"\u201cCross-modal":[90],"Multistep":[91],"Fusion":[92],"(CMF)\u201dnetwork":[93],"generate":[95],"multistep":[96],"features":[97],"achieve":[99,148],"multiple":[100],"interactions":[101,111],"modalities,":[104],"rather":[105],"than":[106,153],"focusing":[107],"modeling":[109],"complex":[110],"between":[112],"modals":[114],"like":[115],"most":[116],"current":[117],"fusion":[119],"methods.":[120],"avoid":[122],"linear":[124],"increase":[125],"computational":[128],"cost,":[129],"share":[131],"parameters":[133],"each":[135],"step":[136],"CMF.":[139],"Extensive":[140],"experiments":[141],"demonstrate":[142],"that":[143],"proposed":[145],"method":[146],"can":[147],"competitive":[149],"or":[150],"better":[151],"performance":[152],"state":[155],"art.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}