{"id":"https://openalex.org/W4293518934","doi":"https://doi.org/10.1109/icme52920.2022.9859666","title":"Cross-Modal Attention Networks with Modality Disentanglement for Scene-Text VQA","display_name":"Cross-Modal Attention Networks with Modality Disentanglement for Scene-Text VQA","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4293518934","doi":"https://doi.org/10.1109/icme52920.2022.9859666"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859666","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5023449927","display_name":"Zeqin Fang","orcid":"https://orcid.org/0009-0004-3121-8050"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeqin Fang","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412815","display_name":"Lin Li","orcid":"https://orcid.org/0000-0001-7553-6916"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102947045","display_name":"Zhongwei Xie","orcid":"https://orcid.org/0000-0001-6346-0707"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongwei Xie","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062853168","display_name":"Jingling Yuan","orcid":"https://orcid.org/0000-0001-7924-8620"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingling Yuan","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I196699116"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9973000288009644,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9901999831199646,"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":0.8308315277099609},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6251187920570374},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.602948009967804},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5806532502174377},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5687212944030762},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5510179400444031},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.532925546169281},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4658421277999878},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.46221795678138733},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4505416452884674},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.421943724155426},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33809804916381836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8308315277099609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6251187920570374},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.602948009967804},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5806532502174377},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5687212944030762},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5510179400444031},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.532925546169281},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4658421277999878},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.46221795678138733},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4505416452884674},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.421943724155426},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33809804916381836},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme52920.2022.9859666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859666","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2597425697","https://openalex.org/W2745461083","https://openalex.org/W2954165458","https://openalex.org/W2963521239","https://openalex.org/W2963717374","https://openalex.org/W2964255219","https://openalex.org/W2965373594","https://openalex.org/W2966715458","https://openalex.org/W2979382951","https://openalex.org/W2988326850","https://openalex.org/W3004268082","https://openalex.org/W3034336960","https://openalex.org/W3034943799","https://openalex.org/W3035644209","https://openalex.org/W3043311956","https://openalex.org/W3215381707","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6752083267","https://openalex.org/W6765121158","https://openalex.org/W6766673545","https://openalex.org/W6766904570"],"related_works":["https://openalex.org/W2952745240","https://openalex.org/W2949074159","https://openalex.org/W4298715519","https://openalex.org/W2474574787","https://openalex.org/W3211385060","https://openalex.org/W2546190447","https://openalex.org/W2959445501","https://openalex.org/W4301143707","https://openalex.org/W4386094778","https://openalex.org/W2807776204"],"abstract_inverted_index":{"Understanding":[0],"the":[1,66,83,88,99,121],"texts":[2,12],"in":[3,159],"visual":[4,27,106,124],"scenes":[5,28],"is":[6,18,51,77,134],"essential":[7],"for":[8],"reasoning":[9],"tasks":[10],"when":[11],"carry":[13],"key":[14],"information.":[15],"Therefore,":[16],"it":[17],"a":[19,44,60,70,78,137,144],"common":[20],"way":[21],"to":[22,29,81,118,139],"learn":[23],"multi-modal":[24],"representation":[25,122],"from":[26],"support":[30],"Scene-Text":[31,57,146],"Visual":[32],"Question&Answering.":[33],"Different":[34],"modalities,":[35],"such":[36],"as":[37,59,136],"text":[38,75,126],"and":[39,73,107,125],"image,":[40],"are":[41,116],"embedded":[42],"into":[43,103],"joint":[45,67],"semantic":[46,79,85],"space":[47],"where":[48,65],"attention":[49,130],"mechanism":[50],"widely":[52],"applied.":[53],"This":[54],"paper":[55],"regards":[56],"VQA":[58,147],"kind":[61],"of":[62,123,161],"cross-modal":[63,113,129],"task":[64],"embedding":[68],"between":[69],"scene":[71,100],"image":[72],"its":[74],"answer":[76],"bridge":[80],"share":[82],"strong":[84],"clues":[86],"with":[87],"two":[89,104],"modalities.":[90],"To":[91],"this":[92],"end,":[93],"our":[94,153],"proposed":[95,154],"framework":[96,155],"firstly":[97],"divides":[98],"recognition":[101],"features":[102,115,127],"types:":[105],"textual":[108],"features.":[109],"And":[110],"then":[111],"external":[112],"pre-trained":[114],"introduced":[117],"simultaneously":[119],"guide":[120],"through":[128],"net-works.":[131],"Finally,":[132],"Transformer":[133],"applied":[135],"decoder":[138],"output":[140],"answers.":[141],"Conducted":[142],"on":[143],"public":[145],"dataset,":[148],"experimental":[149],"results":[150],"show":[151],"that":[152],"out-performs":[156],"existing":[157],"approaches":[158],"terms":[160],"accuracy.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}