{"id":"https://openalex.org/W4386116948","doi":"https://doi.org/10.1109/tip.2023.3306910","title":"DisAVR: Disentangled Adaptive Visual Reasoning Network for Diagram Question Answering","display_name":"DisAVR: Disentangled Adaptive Visual Reasoning Network for Diagram Question Answering","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386116948","doi":"https://doi.org/10.1109/tip.2023.3306910","pmid":"https://pubmed.ncbi.nlm.nih.gov/37616140"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2023.3306910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3306910","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","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/A5101851808","display_name":"Yaxian Wang","orcid":"https://orcid.org/0000-0003-3193-3658"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yaxian Wang","raw_affiliation_strings":["National Engineering Laboratory for Big Data Analytics, School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data Analytics, School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070094915","display_name":"Bifan Wei","orcid":"https://orcid.org/0000-0002-9732-3011"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bifan Wei","raw_affiliation_strings":["National Engineering Laboratory for Big Data Analytics, School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data Analytics, School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361891","display_name":"Jun Liu","orcid":"https://orcid.org/0000-0002-6004-0675"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Liu","raw_affiliation_strings":["National Engineering Laboratory for Big Data Analytics, School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data Analytics, School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100384144","display_name":"Lingling Zhang","orcid":"https://orcid.org/0000-0001-8136-8795"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingling Zhang","raw_affiliation_strings":["Key Laboratory of Intelligent Networks and Network Security, Xi’an Jiaotong University, Ministry of Education, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Networks and Network Security, Xi’an Jiaotong University, Ministry of Education, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089522107","display_name":"Jiaxin Wang","orcid":"https://orcid.org/0000-0003-1629-654X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxin Wang","raw_affiliation_strings":["Key Laboratory of Intelligent Networks and Network Security, Xi’an Jiaotong University, Ministry of Education, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Networks and Network Security, Xi’an Jiaotong University, Ministry of Education, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115694806","display_name":"Qianying Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianying Wang","raw_affiliation_strings":["Lenovo Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Lenovo Research, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101851808"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.6018,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.69247568,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"32","issue":null,"first_page":"4812","last_page":"4827"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9886999726295471,"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":0.7504348754882812},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6154178977012634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5243000388145447},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5214492678642273},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5060340762138367},{"id":"https://openalex.org/keywords/reasoning-system","display_name":"Reasoning system","score":0.5040918588638306},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4967937767505646},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48783400654792786},{"id":"https://openalex.org/keywords/semantic-reasoner","display_name":"Semantic reasoner","score":0.4686557352542877},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4344805181026459},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.41131868958473206},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.14671018719673157},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1426541805267334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7504348754882812},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6154178977012634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5243000388145447},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5214492678642273},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5060340762138367},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.5040918588638306},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4967937767505646},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48783400654792786},{"id":"https://openalex.org/C9616225","wikidata":"https://www.wikidata.org/wiki/Q3929429","display_name":"Semantic reasoner","level":2,"score":0.4686557352542877},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4344805181026459},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.41131868958473206},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.14671018719673157},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1426541805267334},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2023.3306910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3306910","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:37616140","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37616140","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 image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2369050462","display_name":null,"funder_award_id":"2022YFC3303600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3914048027","display_name":null,"funder_award_id":"2023-JC-YB-593","funder_id":"https://openalex.org/F4320336567","funder_display_name":"Natural Science Basic Research Program of Shaanxi Province"},{"id":"https://openalex.org/G6387986177","display_name":null,"funder_award_id":"61721002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8928869386","display_name":null,"funder_award_id":"xhj032021013-02","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320316084","display_name":"China Computer Federation","ror":"https://ror.org/015xj5w40"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320336567","display_name":"Natural Science Basic Research Program of Shaanxi Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1933349210","https://openalex.org/W2064675550","https://openalex.org/W2133564696","https://openalex.org/W2194775991","https://openalex.org/W2250564385","https://openalex.org/W2307512708","https://openalex.org/W2547875792","https://openalex.org/W2561715562","https://openalex.org/W2745461083","https://openalex.org/W2766732270","https://openalex.org/W2779827764","https://openalex.org/W2786273134","https://openalex.org/W2808877322","https://openalex.org/W2883104598","https://openalex.org/W2891021031","https://openalex.org/W2908510526","https://openalex.org/W2908633661","https://openalex.org/W2962763265","https://openalex.org/W2962779575","https://openalex.org/W2962959437","https://openalex.org/W2963150162","https://openalex.org/W2963163009","https://openalex.org/W2963224792","https://openalex.org/W2963446712","https://openalex.org/W2963521239","https://openalex.org/W2964118342","https://openalex.org/W2965336788","https://openalex.org/W2965373594","https://openalex.org/W2966369713","https://openalex.org/W2966683369","https://openalex.org/W2998631105","https://openalex.org/W3009518609","https://openalex.org/W3028907449","https://openalex.org/W3034513622","https://openalex.org/W3106278732","https://openalex.org/W3176186248","https://openalex.org/W3176371077","https://openalex.org/W3200998783","https://openalex.org/W3206987730","https://openalex.org/W4220983034","https://openalex.org/W4282936652","https://openalex.org/W4285255856","https://openalex.org/W4285265382","https://openalex.org/W4293584584","https://openalex.org/W4299522971","https://openalex.org/W4312645695","https://openalex.org/W4313013044","https://openalex.org/W6637373629","https://openalex.org/W6679434410","https://openalex.org/W6729448088","https://openalex.org/W6745915114","https://openalex.org/W6750227808","https://openalex.org/W6752083267","https://openalex.org/W6754944153","https://openalex.org/W6757812085","https://openalex.org/W6757817989","https://openalex.org/W6766673545"],"related_works":["https://openalex.org/W16767636","https://openalex.org/W2158601124","https://openalex.org/W20175516","https://openalex.org/W1945364905","https://openalex.org/W4301852704","https://openalex.org/W2068634534","https://openalex.org/W82332555","https://openalex.org/W2011316522","https://openalex.org/W2472715646","https://openalex.org/W2101990186"],"abstract_inverted_index":{"Diagram":[0],"Question":[1],"Answering":[2],"(DQA)":[3],"aims":[4],"to":[5,45,66,90,123,163,185,223],"correctly":[6],"answer":[7],"questions":[8,56],"about":[9,57],"given":[10],"diagrams,":[11],"which":[12],"demands":[13],"an":[14,217],"interplay":[15],"of":[16,27,37,95,152,243],"good":[17],"diagram":[18,127,210],"understanding":[19],"and":[20,69,97,110,134,159,205],"effective":[21],"reasoning.":[22,98,113,167],"However,":[23],"the":[24,93,115,142,147,169,175,209,212,241],"same":[25],"appearance":[26],"objects":[28],"in":[29,197,208],"diagrams":[30,47,58],"can":[31],"express":[32],"different":[33,60],"semantics.":[34],"This":[35],"kind":[36],"visual":[38,182],"semantic":[39,160,204],"ambiguity":[40],"problem":[41],"makes":[42],"it":[43,62],"challenging":[44],"represent":[46],"sufficiently":[48],"for":[49,86,230],"better":[50],"understanding.":[51],"Moreover,":[52,216],"since":[53],"there":[54],"are":[55],"from":[59],"perspectives,":[61],"is":[63,121,221],"also":[64],"crucial":[65],"perform":[67],"flexible":[68],"adaptive":[70,112,171,218],"reasoning":[71,172,177,183,228],"on":[72,236],"content-rich":[73],"diagrams.":[74],"In":[75],"this":[76],"paper,":[77],"we":[78],"propose":[79],"a":[80,187],"Disentangled":[81],"Adaptive":[82],"Visual":[83],"Reasoning":[84],"Network":[85],"DQA,":[87],"named":[88],"DisAVR,":[89],"jointly":[91],"optimize":[92],"dual-process":[94],"representation":[96,128],"DisAVR":[99],"mainly":[100],"comprises":[101],"three":[102,150,181,195,237],"modules:":[103],"improved":[104,116],"region":[105,117,139],"feature":[106,118],"learning,":[107],"question":[108,143,148,153,214],"parsing,":[109],"disentangled":[111,170],"Specifically,":[114],"learning":[119],"module":[120,145,173],"designed":[122,222],"first":[124],"learn":[125],"robust":[126],"by":[129,179],"integrating":[130],"detail-aware":[131],"patch":[132],"features":[133,137],"semantically-explicit":[135],"text":[136],"with":[138],"features.":[140],"Subsequently,":[141],"parsing":[144],"decomposes":[146,174],"into":[149],"types":[151],"guidance":[154,162],"including":[155],"region,":[156],"spatial":[157,206],"relation":[158,161],"dynamically":[164],"guide":[165],"subsequent":[166],"Next,":[168],"whole":[176],"process":[178],"employing":[180],"cells":[184,196],"construct":[186],"soft":[188],"fully-connected":[189],"multi-layer":[190],"stacked":[191],"routing":[192,219],"space.":[193],"These":[194],"each":[198],"layer":[199],"reason":[200],"over":[201],"object":[202],"regions,":[203],"relations":[207],"under":[211],"corresponding":[213],"guidance.":[215],"mechanism":[220],"flexibly":[224],"explore":[225],"more":[226],"optimal":[227],"paths":[229],"specific":[231],"diagram-question":[232],"pairs.":[233],"Extensive":[234],"experiments":[235],"DQA":[238],"datasets":[239],"demonstrate":[240],"superiority":[242],"our":[244],"DisAVR.":[245]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}