{"id":"https://openalex.org/W4200219557","doi":"https://doi.org/10.1109/cisp-bmei53629.2021.9624447","title":"Visual Question Answering Based on Position Alignment","display_name":"Visual Question Answering Based on Position Alignment","publication_year":2021,"publication_date":"2021-10-23","ids":{"openalex":"https://openalex.org/W4200219557","doi":"https://doi.org/10.1109/cisp-bmei53629.2021.9624447"},"language":"en","primary_location":{"id":"doi:10.1109/cisp-bmei53629.2021.9624447","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cisp-bmei53629.2021.9624447","pdf_url":null,"source":{"id":"https://openalex.org/S4363605805","display_name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","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":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","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/A5079161242","display_name":"Qihao Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165726","display_name":"Shanghai Municipal Education Commission","ror":"https://ror.org/05tewj457","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210165456","https://openalex.org/I4210165726"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qihao Xia","raw_affiliation_strings":["Engineering Center of SHMEC for Space Information and GNSS, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Center of SHMEC for Space Information and GNSS, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210165726","https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084234940","display_name":"Chao Yu","orcid":"https://orcid.org/0000-0002-5604-0373"},"institutions":[{"id":"https://openalex.org/I4210165726","display_name":"Shanghai Municipal Education Commission","ror":"https://ror.org/05tewj457","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210165456","https://openalex.org/I4210165726"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Yu","raw_affiliation_strings":["Engineering Center of SHMEC for Space Information and GNSS, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Center of SHMEC for Space Information and GNSS, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210165726","https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057711372","display_name":"P Peng","orcid":"https://orcid.org/0000-0002-3921-6218"},"institutions":[{"id":"https://openalex.org/I4210165726","display_name":"Shanghai Municipal Education Commission","ror":"https://ror.org/05tewj457","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210165456","https://openalex.org/I4210165726"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pingping Peng","raw_affiliation_strings":["Engineering Center of SHMEC for Space Information and GNSS, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Center of SHMEC for Space Information and GNSS, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210165726","https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018925091","display_name":"Henghao Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165726","display_name":"Shanghai Municipal Education Commission","ror":"https://ror.org/05tewj457","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210165456","https://openalex.org/I4210165726"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Henghao Gu","raw_affiliation_strings":["Engineering Center of SHMEC for Space Information and GNSS, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Center of SHMEC for Space Information and GNSS, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210165726","https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032764435","display_name":"Zhengqi Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165726","display_name":"Shanghai Municipal Education Commission","ror":"https://ror.org/05tewj457","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210165456","https://openalex.org/I4210165726"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqi Zheng","raw_affiliation_strings":["Engineering Center of SHMEC for Space Information and GNSS, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Center of SHMEC for Space Information and GNSS, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210165726","https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056251077","display_name":"Kun Zhao","orcid":"https://orcid.org/0000-0002-8381-3714"},"institutions":[{"id":"https://openalex.org/I4210165726","display_name":"Shanghai Municipal Education Commission","ror":"https://ror.org/05tewj457","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210165456","https://openalex.org/I4210165726"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Zhao","raw_affiliation_strings":["Engineering Center of SHMEC for Space Information and GNSS, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Center of SHMEC for Space Information and GNSS, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210165726","https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.17511977,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.996399998664856,"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":0.9962000250816345,"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":0.7385327816009521},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6365278959274292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6274150013923645},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6177090406417847},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5949452519416809},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5919148921966553},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5808513164520264},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5570394992828369},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5015075206756592},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4988524913787842},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.462049663066864},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4081355333328247},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3995363712310791},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07890638709068298}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7385327816009521},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6365278959274292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6274150013923645},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6177090406417847},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5949452519416809},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5919148921966553},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5808513164520264},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5570394992828369},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5015075206756592},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4988524913787842},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.462049663066864},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4081355333328247},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3995363712310791},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07890638709068298},{"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/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cisp-bmei53629.2021.9624447","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cisp-bmei53629.2021.9624447","pdf_url":null,"source":{"id":"https://openalex.org/S4363605805","display_name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","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":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G5977199651","display_name":"\u5ba4\u5185\u9006\u5b9a\u4f4d\u7406\u8bba\u673a\u5236\u7814\u7a76","funder_award_id":"61771197","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1665214252","https://openalex.org/W1933349210","https://openalex.org/W2095705004","https://openalex.org/W2105880865","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2302255633","https://openalex.org/W2560730294","https://openalex.org/W2741964042","https://openalex.org/W2745461083","https://openalex.org/W2787119853","https://openalex.org/W2808877322","https://openalex.org/W2917061951","https://openalex.org/W2949197413","https://openalex.org/W2963066927","https://openalex.org/W2963150162","https://openalex.org/W2963383024","https://openalex.org/W2963521239","https://openalex.org/W2963925437","https://openalex.org/W2964067226","https://openalex.org/W2964345214","https://openalex.org/W2998631105","https://openalex.org/W3195541832","https://openalex.org/W4299522971","https://openalex.org/W4385245566","https://openalex.org/W6618372016","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6637242042","https://openalex.org/W6675992320","https://openalex.org/W6683258052","https://openalex.org/W6694395031","https://openalex.org/W6698183232","https://openalex.org/W6728881024","https://openalex.org/W6742036546","https://openalex.org/W6743068658","https://openalex.org/W6748581942","https://openalex.org/W6752083267","https://openalex.org/W6757067213"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W4288102755","https://openalex.org/W2104753665","https://openalex.org/W2358868262"],"abstract_inverted_index":{"The":[0,53,64,178],"alignment":[1,45],"of":[2,9,137,157],"information":[3,107,136],"from":[4,120],"images":[5],"and":[6,68,86,93,99,110,142,204],"questions":[7],"is":[8,23,30,56,182,209],"great":[10],"significance":[11],"in":[12,21,61,108,140,155,171,211],"the":[13,26,31,36,57,88,96,105,117,134,150,158,162,168,175,185,191],"visual":[14,199],"question":[15,27,80,92,126,200],"answering":[16,201],"task.":[17],"Whether":[18],"an":[19],"object":[20,139],"image":[22,84,109,141,172],"related":[24,169],"to":[25,47,82,127,148,173,184,189],"or":[28],"not":[29],"basic":[32],"judgement":[33],"relied":[34],"on":[35,198],"feature":[37,186],"alignment.":[38,63,213],"Many":[39],"previous":[40],"works":[41],"have":[42],"proposed":[43],"different":[44],"methods":[46],"build":[48],"better":[49],"cross":[50],"modality":[51],"interaction.":[52],"attention":[54,76,89,118,146,163,180,187],"mechanism":[55],"most":[58],"used":[59],"method":[60,197,208],"making":[62],"classical":[65],"bottom":[66,97],"up":[67,98],"top":[69,74,100],"down":[70,75,101],"model":[71,102,165],"builds":[72],"a":[73,121,144],"distribution":[77,119,147,164,181,188],"by":[78],"concatenating":[79],"features":[81,85],"each":[83,138],"calculates":[87],"weights":[90],"between":[91,152],"image.":[94],"However,":[95],"didn't":[103],"consider":[104],"positional":[106,129,135],"question.":[111,160,177],"In":[112],"this":[113],"paper,":[114],"we":[115],"revisit":[116],"position":[122,145,170,179],"perspective":[123],"which":[124],"aligns":[125],"object's":[128],"information.":[130],"We":[131,194],"first":[132],"embed":[133],"calculate":[143],"indicate":[149],"relevance":[151],"objects'":[153],"positions":[154],"context":[156],"current":[159],"Through":[161],"can":[166],"select":[167],"answer":[174],"given":[176],"concatenated":[183],"get":[190],"final":[192],"distribution.":[193],"evaluate":[195],"our":[196,207],"(VQA2.0)":[202],"dataset,":[203],"show":[205],"that":[206],"effective":[210],"multimodal":[212]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
