{"id":"https://openalex.org/W4386453561","doi":"https://doi.org/10.1109/tip.2023.3310332","title":"Exploring Sparse Spatial Relation in Graph Inference for Text-Based VQA","display_name":"Exploring Sparse Spatial Relation in Graph Inference for Text-Based VQA","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386453561","doi":"https://doi.org/10.1109/tip.2023.3310332","pmid":"https://pubmed.ncbi.nlm.nih.gov/37669188"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2023.3310332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3310332","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":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.09147","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100782531","display_name":"Sheng Zhou","orcid":"https://orcid.org/0009-0007-4215-5464"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Zhou","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0007-4215-5464","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059530979","display_name":"Dan Guo","orcid":"https://orcid.org/0000-0003-2594-254X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Guo","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-2594-254X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019391894","display_name":"Jia Li","orcid":"https://orcid.org/0000-0001-9446-249X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Li","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-9446-249X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034737032","display_name":"Xun Yang","orcid":"https://orcid.org/0000-0003-0201-1638"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Yang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-0201-1638","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100377147","display_name":"Meng Wang","orcid":"https://orcid.org/0000-0002-3094-7735"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3094-7735","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7654,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.92426343,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"5060","last_page":"5074"},"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/T10028","display_name":"Topic Modeling","score":0.998199999332428,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9955000281333923,"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":0.690555214881897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6336418390274048},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6039372682571411},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5700036287307739},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5556827187538147},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5280904173851013},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4763886332511902},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.45415157079696655},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.4532913863658905},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.44448143243789673},{"id":"https://openalex.org/keywords/dense-graph","display_name":"Dense graph","score":0.43524599075317383},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4146175980567932},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.26956626772880554},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.20079970359802246},{"id":"https://openalex.org/keywords/line-graph","display_name":"Line graph","score":0.17644351720809937}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.690555214881897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6336418390274048},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6039372682571411},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5700036287307739},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5556827187538147},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5280904173851013},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4763886332511902},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.45415157079696655},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.4532913863658905},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.44448143243789673},{"id":"https://openalex.org/C13251829","wikidata":"https://www.wikidata.org/wiki/Q3085841","display_name":"Dense graph","level":5,"score":0.43524599075317383},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4146175980567932},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26956626772880554},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.20079970359802246},{"id":"https://openalex.org/C203776342","wikidata":"https://www.wikidata.org/wiki/Q1378376","display_name":"Line graph","level":3,"score":0.17644351720809937},{"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/C102192266","wikidata":"https://www.wikidata.org/wiki/Q4545823","display_name":"1-planar graph","level":4,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tip.2023.3310332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3310332","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:37669188","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37669188","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},{"id":"pmh:oai:arXiv.org:2310.09147","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.09147","pdf_url":"https://arxiv.org/pdf/2310.09147","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.09147","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.09147","pdf_url":"https://arxiv.org/pdf/2310.09147","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1040185051","display_name":null,"funder_award_id":"62272435","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3326758564","display_name":null,"funder_award_id":"62202139","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G405190135","display_name":null,"funder_award_id":"U22A2094","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4862433228","display_name":null,"funder_award_id":"62272144","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5038960961","display_name":null,"funder_award_id":"U20A20183","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5586136776","display_name":null,"funder_award_id":"2022YFB4500600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6151690139","display_name":null,"funder_award_id":"62020106007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8480155402","display_name":null,"funder_award_id":"72188101","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"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4386453561.pdf"},"referenced_works_count":72,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1647671624","https://openalex.org/W2008806374","https://openalex.org/W2012689760","https://openalex.org/W2031489346","https://openalex.org/W2053317383","https://openalex.org/W2108598243","https://openalex.org/W2144554289","https://openalex.org/W2277195237","https://openalex.org/W2493916176","https://openalex.org/W2788334925","https://openalex.org/W2809273748","https://openalex.org/W2884093133","https://openalex.org/W2890531016","https://openalex.org/W2896457183","https://openalex.org/W2962766617","https://openalex.org/W2963420691","https://openalex.org/W2963518342","https://openalex.org/W2963622213","https://openalex.org/W2965512000","https://openalex.org/W2965778995","https://openalex.org/W2979382951","https://openalex.org/W2982021328","https://openalex.org/W2988326850","https://openalex.org/W2997531716","https://openalex.org/W2997747012","https://openalex.org/W3004082545","https://openalex.org/W3004349648","https://openalex.org/W3004846386","https://openalex.org/W3006154882","https://openalex.org/W3034336960","https://openalex.org/W3034479628","https://openalex.org/W3034787499","https://openalex.org/W3034943799","https://openalex.org/W3035454069","https://openalex.org/W3035520037","https://openalex.org/W3035644209","https://openalex.org/W3039115681","https://openalex.org/W3093272873","https://openalex.org/W3093385053","https://openalex.org/W3094071022","https://openalex.org/W3097712622","https://openalex.org/W3101411491","https://openalex.org/W3106859150","https://openalex.org/W3108319047","https://openalex.org/W3110661548","https://openalex.org/W3115287481","https://openalex.org/W3122622502","https://openalex.org/W3175445769","https://openalex.org/W3177430964","https://openalex.org/W3181159501","https://openalex.org/W3181186176","https://openalex.org/W3185066916","https://openalex.org/W3205050305","https://openalex.org/W3205209899","https://openalex.org/W3215381707","https://openalex.org/W3215633354","https://openalex.org/W4224242030","https://openalex.org/W4283029876","https://openalex.org/W4287555689","https://openalex.org/W4289542422","https://openalex.org/W4293528858","https://openalex.org/W4295246343","https://openalex.org/W4297733535","https://openalex.org/W4385245566","https://openalex.org/W6636915900","https://openalex.org/W6691603626","https://openalex.org/W6739901393","https://openalex.org/W6753027577","https://openalex.org/W6755207826","https://openalex.org/W6765121158","https://openalex.org/W6784368356"],"related_works":["https://openalex.org/W4214591816","https://openalex.org/W4389471147","https://openalex.org/W3042849301","https://openalex.org/W4312650216","https://openalex.org/W4221155265","https://openalex.org/W3109142545","https://openalex.org/W4385571298","https://openalex.org/W4377372012","https://openalex.org/W2590022237","https://openalex.org/W4390195594"],"abstract_inverted_index":{"Text-based":[0],"visual":[1,32,38,114,184],"question":[2],"answering":[3],"(TextVQA)":[4],"faces":[5],"the":[6,55,90,102,134,205,209,217,245],"significant":[7],"challenge":[8],"of":[9,20,104,112,123,247],"avoiding":[10],"redundant":[11,140],"relational":[12],"inference.":[13],"To":[14],"be":[15,58,110],"specific,":[16],"a":[17,51,144,152,198],"large":[18],"number":[19],"detected":[21,60,88],"objects":[22,63,76,106],"and":[23,100,107,175,192,214,222,230],"optical":[24],"character":[25],"recognition":[26],"(OCR)":[27],"tokens":[28,87,108],"result":[29],"in":[30,54,89,208,216],"rich":[31],"relationships.":[33,195],"Existing":[34],"works":[35],"take":[36],"all":[37,122],"relationships":[39,185],"into":[40],"account":[41],"for":[42,79,97,116,125,164,177,186],"answer":[43,80,98,126],"prediction.":[44],"However,":[45],"there":[46],"are":[47,77],"three":[48,183],"observations:":[49],"(1)":[50],"single":[52],"subject":[53],"images":[56],"can":[57],"easily":[59],"as":[61],"multiple":[62],"with":[64],"distinct":[65],"bounding":[66],"boxes":[67],"(considered":[68],"repetitive":[69,75],"objects).":[70],"The":[71],"associations":[72],"between":[73],"these":[74],"superfluous":[78],"reasoning;":[81,99],"(2)":[82],"two":[83],"spatially":[84,153,178],"distant":[85],"OCR":[86],"image":[91],"frequently":[92],"have":[93],"weak":[94],"semantic":[95],"dependencies":[96],"(3)":[101],"co-existence":[103],"nearby":[105],"may":[109],"indicative":[111],"important":[113,136],"cues":[115],"predicting":[117],"answers.":[118],"Rather":[119],"than":[120],"utilizing":[121],"them":[124],"prediction,":[127],"we":[128,167],"make":[129],"an":[130],"effort":[131],"to":[132,158],"identify":[133],"most":[135],"connections":[137],"or":[138],"eliminate":[139],"ones.":[141],"We":[142,181],"propose":[143],"sparse":[145,212,220,224],"spatial":[146,162,169],"graph":[147,187,200,221],"network":[148],"(SSGN)":[149],"that":[150,203,234],"introduces":[151],"aware":[154,179],"relation":[155,165],"pruning":[156],"technique":[157],"this":[159],"task.":[160],"As":[161],"factors":[163],"measurement,":[166],"employ":[168],"distance,":[170],"geometric":[171],"dimension,":[172],"overlap":[173],"area,":[174],"DIoU":[176],"pruning.":[180],"consider":[182],"learning:":[188],"object-object,":[189],"OCR-OCR":[190],"tokens,":[191],"object-OCR":[193],"token":[194],"SSGN":[196,235],"is":[197],"progressive":[199],"learning":[201],"architecture":[202],"verifies":[204],"pivotal":[206],"relations":[207],"correlated":[210],"object-token":[211],"graph,":[213],"then":[215],"respective":[218],"object-based":[219],"token-based":[223],"graph.":[225],"Experiment":[226],"results":[227,242],"on":[228],"TextVQA":[229],"ST-VQA":[231],"datasets":[232],"demonstrate":[233,244],"achieves":[236],"promising":[237],"performances.":[238],"And":[239],"some":[240],"visualization":[241],"further":[243],"interpretability":[246],"our":[248],"method.":[249]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}