{"id":"https://openalex.org/W4304098678","doi":"https://doi.org/10.1145/3503161.3548172","title":"A Region-based Document VQA","display_name":"A Region-based Document VQA","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304098678","doi":"https://doi.org/10.1145/3503161.3548172"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548172","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548172","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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/A5101905905","display_name":"Xinya Wu","orcid":"https://orcid.org/0000-0002-4159-5894"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinya Wu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044238657","display_name":"Duo Zheng","orcid":"https://orcid.org/0000-0003-1180-6176"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Duo Zheng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100644563","display_name":"Ruonan Wang","orcid":"https://orcid.org/0000-0002-5066-6308"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruonan Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024455283","display_name":"Jiashen Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiashen Sun","raw_affiliation_strings":["Meituan Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074880771","display_name":"Minzhen Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minzhen Hu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013283012","display_name":"Fangxiang Feng","orcid":"https://orcid.org/0000-0002-4798-4233"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangxiang Feng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351304","display_name":"Xiaojie Wang","orcid":"https://orcid.org/0000-0003-0314-8951"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojie Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103801625","display_name":"Huixing Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huixing Jiang","raw_affiliation_strings":["Meituan Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan Group, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100346607","display_name":"Fan Yang","orcid":"https://orcid.org/0000-0002-1157-8719"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":["Meituan Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan Group, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101905905"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.2397,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.5837017,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4909","last_page":"4920"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9968000054359436,"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/T10028","display_name":"Topic Modeling","score":0.9957000017166138,"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/question-answering","display_name":"Question answering","score":0.8665543794631958},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8149526119232178},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7430533170700073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.611504077911377},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.533841073513031},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.42637503147125244},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4079291522502899},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34327852725982666},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3282591700553894}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8665543794631958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8149526119232178},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7430533170700073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.611504077911377},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.533841073513031},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.42637503147125244},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4079291522502899},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34327852725982666},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3282591700553894},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548172","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548172","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2560730294","https://openalex.org/W2561715562","https://openalex.org/W2745461083","https://openalex.org/W2747329762","https://openalex.org/W2781528640","https://openalex.org/W2963150162","https://openalex.org/W2963287297","https://openalex.org/W2963323070","https://openalex.org/W2963383024","https://openalex.org/W2963622213","https://openalex.org/W2963748441","https://openalex.org/W2979382951","https://openalex.org/W2988326850","https://openalex.org/W2998230451","https://openalex.org/W2998665041","https://openalex.org/W3006883036","https://openalex.org/W3034336960","https://openalex.org/W3104415840","https://openalex.org/W3173325518","https://openalex.org/W3175344799","https://openalex.org/W3176851559","https://openalex.org/W3180693748","https://openalex.org/W3198200341","https://openalex.org/W3202839357","https://openalex.org/W4226078866","https://openalex.org/W4226397046","https://openalex.org/W4238846128","https://openalex.org/W4240805545","https://openalex.org/W4249013746","https://openalex.org/W4313163001"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2115758952"],"abstract_inverted_index":{"Practical":[0],"Document":[1,59],"Visual":[2],"Question":[3],"Answering":[4],"(DocVQA)":[5],"needs":[6,47],"not":[7],"only":[8],"to":[9,111,137],"recognize":[10],"and":[11,105,119],"extract":[12],"the":[13,34,44,79,95,113,139,143,153],"document":[14],"contents,":[15],"but":[16],"also":[17,135],"reason":[18],"on":[19,30],"them":[20],"for":[21,67,77,163],"answering":[22],"questions.":[23],"However,":[24],"previous":[25],"DocVQA":[26,129,140,165],"data":[27],"mainly":[28],"focuses":[29],"in-line":[31],"questions,":[32],"where":[33,86],"answers":[35],"could":[36],"be":[37,161],"directly":[38],"extracted":[39],"after":[40],"locating":[41],"keywords":[42],"in":[43,142],"documents,":[45],"which":[46,62],"less":[48],"reasoning.":[49],"This":[50],"paper":[51],"therefore":[52],"builds":[53],"a":[54,72,83,87,128],"large-scale":[55],"dataset":[56],"named":[57],"Region-based":[58],"VQA":[60],"(RDVQA),":[61],"includes":[63],"more":[64,158],"practical":[65,164],"questions":[66],"DocVQA.":[68],"We":[69],"then":[70],"propose":[71],"novel":[73,98],"Reason-over-In-region-Question-answering":[74],"(ReIQ)":[75],"model":[76,151],"addressing":[78],"problems.":[80],"It":[81],"is":[82,92,134],"pre-training-based":[84],"model,":[85],"Spatial-Token":[88],"Pre-trained":[89],"Model":[90],"(STPM)":[91],"employed":[93],"as":[94,121,123,166],"backbone.":[96],"Two":[97],"pre-training":[99],"tasks,":[100],"Masked":[101],"Text":[102],"Box":[103],"Regression":[104],"Shuffled":[106],"Triplet":[107],"Reconstruction,":[108],"are":[109],"proposed":[110,136],"learn":[112],"entailment":[114],"relationship":[115],"between":[116],"text":[117],"blocks":[118],"tokens":[120],"well":[122],"contextual":[124],"information,":[125],"respectively.":[126],"Moreover,":[127],"State":[130],"Tracking":[131],"Module":[132],"(DocST)":[133],"track":[138],"state":[141],"fine-tuning":[144],"stage.":[145],"Experimental":[146],"results":[147],"show":[148],"that":[149],"our":[150],"improves":[152],"performance":[154],"onRDVQA":[155],"significantly,":[156],"although":[157],"work":[159],"should":[160],"done":[162],"shown":[167],"inRDVQA.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}