{"id":"https://openalex.org/W4389140516","doi":"https://doi.org/10.1145/3634918","title":"Graph Pooling Inference Network for Text-based VQA","display_name":"Graph Pooling Inference Network for Text-based VQA","publication_year":2023,"publication_date":"2023-11-29","ids":{"openalex":"https://openalex.org/W4389140516","doi":"https://doi.org/10.1145/3634918"},"language":"en","primary_location":{"id":"doi:10.1145/3634918","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3634918","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-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/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":["HeFei University of Technology, China"],"raw_orcid":"https://orcid.org/0009-0007-4215-5464","affiliations":[{"raw_affiliation_string":"HeFei University of Technology, 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":["HeFei University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0003-2594-254X","affiliations":[{"raw_affiliation_string":"HeFei University of Technology, 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":["University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0003-0201-1638","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008417257","display_name":"Jianfeng Dong","orcid":"https://orcid.org/0000-0001-5244-3274"},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Dong","raw_affiliation_strings":["Zhejiang Gongshang University, China"],"raw_orcid":"https://orcid.org/0000-0001-5244-3274","affiliations":[{"raw_affiliation_string":"Zhejiang Gongshang University, China","institution_ids":["https://openalex.org/I75059550"]}]},{"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":["HeFei University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-3094-7735","affiliations":[{"raw_affiliation_string":"HeFei University of Technology, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7585,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.85856317,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"20","issue":"4","first_page":"1","last_page":"21"},"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":0.9991999864578247,"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":0.996999979019165,"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":0.8330615162849426},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5781951546669006},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5538427829742432},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5149317383766174},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5011270046234131},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4661753177642822},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3920953869819641},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3874623775482178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8330615162849426},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5781951546669006},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5538427829742432},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5149317383766174},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5011270046234131},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4661753177642822},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3920953869819641},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3874623775482178}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3634918","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3634918","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"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/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/G6451131992","display_name":null,"funder_award_id":"62020106007, 62272144, U20A20183, 72188101, 62272435, and U22A2094","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7777819896","display_name":null,"funder_award_id":"-2022","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program 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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2053317383","https://openalex.org/W2108598243","https://openalex.org/W2253806798","https://openalex.org/W2277195237","https://openalex.org/W2493916176","https://openalex.org/W2558333741","https://openalex.org/W2560835477","https://openalex.org/W2615497679","https://openalex.org/W3106859150","https://openalex.org/W3127686331","https://openalex.org/W3130796238","https://openalex.org/W3165695488","https://openalex.org/W3215381707","https://openalex.org/W3216857888","https://openalex.org/W4205817612","https://openalex.org/W4224329610","https://openalex.org/W4238290165","https://openalex.org/W4293083879","https://openalex.org/W4295246343","https://openalex.org/W4312971273","https://openalex.org/W4312988011","https://openalex.org/W4362655662","https://openalex.org/W4378805076","https://openalex.org/W4382203033","https://openalex.org/W4385681696","https://openalex.org/W4386395578","https://openalex.org/W4386453561","https://openalex.org/W4387969035","https://openalex.org/W4388189392","https://openalex.org/W6778668228","https://openalex.org/W6790241037"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W147410782","https://openalex.org/W3022252430","https://openalex.org/W3103989898","https://openalex.org/W4287804464","https://openalex.org/W3211292372","https://openalex.org/W3015684221"],"abstract_inverted_index":{"Effectively":[0],"leveraging":[1],"objects":[2,97],"and":[3,38,40,54,83,98,130,153,179,191],"optical":[4],"character":[5],"recognition":[6],"(OCR)":[7],"tokens":[8,105],"to":[9,78,121,168],"reason":[10],"out":[11],"pivotal":[12],"scene":[13,137],"text":[14],"is":[15,72,89,140],"critical":[16],"for":[17,127],"the":[18,31,56,80,85,92,99,109,134,149,154,170,181],"challenging":[19],"Text-based":[20],"Visual":[21],"Question":[22],"Answering":[23],"(TextVQA)":[24],"task.":[25],"Graph-based":[26],"models":[27],"can":[28,174],"effectively":[29,175],"capture":[30,84],"semantic":[32],"relationship":[33],"among":[34],"visual":[35,52,81,166],"entities":[36,53,82],"(objects":[37],"tokens)":[39],"report":[41],"remarkable":[42],"performance":[43,199],"in":[44,108],"TextVQA.":[45],"However,":[46],"previous":[47],"efforts":[48],"usually":[49,106],"leverage":[50],"all":[51],"ignore":[55],"negative":[57],"effect":[58],"of":[59,95,101,136,183],"superfluous":[60],"entities.":[61],"This":[62],"article":[63],"presents":[64],"a":[65,141,160],"Graph":[66],"Pooling":[67],"Inference":[68],"Network":[69],"(GPIN),":[70],"which":[71],"an":[73,116],"evolutionary":[74],"graph":[75,128,144,152,157,161],"learning":[76],"method":[77],"purify":[79],"core":[86],"semantics.":[87],"It":[88,173],"observed":[90],"that":[91,146,163,195],"dense":[93],"distribution":[94],"reduplicative":[96],"crowd":[100],"semantically":[102,124,184],"dependent":[103],"OCR":[104],"co-exist":[107],"image.":[110],"Motivated":[111],"by":[112],"this,":[113],"GPIN":[114,139,196],"adopts":[115],"adaptive":[117],"node":[118],"dropping":[119],"strategy":[120],"dynamically":[122],"downscale":[123],"closed":[125],"nodes":[126],"evolution":[129],"update.":[131],"To":[132],"deepen":[133],"comprehension":[135],"text,":[138],"dual-path":[142],"hierarchical":[143],"architecture":[145],"progressively":[147],"aggregates":[148],"evolved":[150,155],"object":[151,177],"token":[156],"semantics":[158],"into":[159],"vector":[162],"serves":[164],"as":[165],"cues":[167],"facilitate":[169],"answer":[171],"reasoning.":[172],"eliminate":[176],"redundancy":[178],"enhance":[180],"association":[182],"continuous":[185],"tokens.":[186],"Experiments":[187],"conducted":[188],"on":[189],"TextVQA":[190],"ST-VQA":[192],"datasets":[193],"show":[194],"achieves":[197],"promising":[198],"compared":[200],"with":[201],"state-of-the-art":[202],"methods.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}