{"id":"https://openalex.org/W4409539127","doi":"https://doi.org/10.1145/3729242","title":"Cascade Transformer for Hierarchical Semantic Reasoning in Text-Based Visual Question Answering","display_name":"Cascade Transformer for Hierarchical Semantic Reasoning in Text-Based Visual Question Answering","publication_year":2025,"publication_date":"2025-04-17","ids":{"openalex":"https://openalex.org/W4409539127","doi":"https://doi.org/10.1145/3729242"},"language":"en","primary_location":{"id":"doi:10.1145/3729242","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3729242","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"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 Intelligent Systems and Technology","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/A5086470221","display_name":"Yuan Gao","orcid":"https://orcid.org/0000-0003-4096-9134"},"institutions":[{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]},{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]},{"id":"https://openalex.org/I4210091712","display_name":"Zhengzhou University of Science and Technology","ror":"https://ror.org/00b3j7936","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210091712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Gao","raw_affiliation_strings":["School of Computer Science and Technology, Hainan University, Haikou, China and School of Computer Science and Artificial Intelligence, Zhengzhou University, Zhengzhou, China","Hainan University, China and Zhengzhou University, China"],"raw_orcid":"https://orcid.org/0000-0003-4096-9134","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hainan University, Haikou, China and School of Computer Science and Artificial Intelligence, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I20942203","https://openalex.org/I4210091712"]},{"raw_affiliation_string":"Hainan University, China and Zhengzhou University, China","institution_ids":["https://openalex.org/I20942203","https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071522874","display_name":"Dezhen Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dezhen Feng","raw_affiliation_strings":["School of Computer Science and Technology, Hainan University, Haikou, China","Hainan University, China"],"raw_orcid":"https://orcid.org/0009-0006-7432-8115","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hainan University, Haikou, China","institution_ids":["https://openalex.org/I20942203"]},{"raw_affiliation_string":"Hainan University, China","institution_ids":["https://openalex.org/I20942203"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049154222","display_name":"Laurence T. Yang","orcid":"https://orcid.org/0000-0002-7986-4244"},"institutions":[{"id":"https://openalex.org/I197191942","display_name":"St. Francis Xavier University","ror":"https://ror.org/01wcaxs37","country_code":"CA","type":"education","lineage":["https://openalex.org/I197191942"]},{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CA","CN"],"is_corresponding":false,"raw_author_name":"Laurence T. Yang","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Zhengzhou University, Zhengzhou, China and School of Computer Science and Technology, St Francis Xavier University, Antigonish, Nova Scotia, Canada","Zhengzhou University, China and St. Francis Xavier University, Canada"],"raw_orcid":"https://orcid.org/0000-0002-7986-4244","affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Zhengzhou University, Zhengzhou, China and School of Computer Science and Technology, St Francis Xavier University, Antigonish, Nova Scotia, Canada","institution_ids":["https://openalex.org/I197191942"]},{"raw_affiliation_string":"Zhengzhou University, China and St. Francis Xavier University, Canada","institution_ids":["https://openalex.org/I197191942","https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100309994","display_name":"Jing Yang","orcid":"https://orcid.org/0009-0000-4682-4839"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Yang","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Zhengzhou University, Zhengzhou, China","Zhengzhou University, China"],"raw_orcid":"https://orcid.org/0009-0000-4682-4839","affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]},{"raw_affiliation_string":"Zhengzhou University, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027538242","display_name":"Xiaowen Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowen Jiang","raw_affiliation_strings":["School of Computer Science and Technology, Hainan University, Haikou, China","Hainan University, China"],"raw_orcid":"https://orcid.org/0009-0006-9773-1265","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hainan University, Haikou, China","institution_ids":["https://openalex.org/I20942203"]},{"raw_affiliation_string":"Hainan University, China","institution_ids":["https://openalex.org/I20942203"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113978259","display_name":"Jieming Yang","orcid":"https://orcid.org/0000-0001-9584-2160"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jieming Yang","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Zhengzhou University, Zhengzhou, China","Zhengzhou University, China"],"raw_orcid":"https://orcid.org/0000-0001-9584-2160","affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]},{"raw_affiliation_string":"Zhengzhou University, China","institution_ids":["https://openalex.org/I38877650"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05411249,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"3","first_page":"1","last_page":"23"},"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":0.9973999857902527,"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":0.9966999888420105,"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":0.8936195373535156},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.8893633484840393},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7427325248718262},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.6707224249839783},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.623034656047821},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.574460506439209},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4544007480144501}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8936195373535156},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8893633484840393},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7427325248718262},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.6707224249839783},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.623034656047821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.574460506439209},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4544007480144501},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3729242","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3729242","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"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 Intelligent Systems and Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G214697123","display_name":null,"funder_award_id":"62302130","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2053317383","https://openalex.org/W2493916176","https://openalex.org/W2750779823","https://openalex.org/W2970231061","https://openalex.org/W2979382951","https://openalex.org/W3004268082","https://openalex.org/W3034837210","https://openalex.org/W3093385053","https://openalex.org/W3094071022","https://openalex.org/W3110661548","https://openalex.org/W3115287481","https://openalex.org/W3168597991","https://openalex.org/W3182937942","https://openalex.org/W3193396141","https://openalex.org/W3206082179","https://openalex.org/W3215381707","https://openalex.org/W3215633354","https://openalex.org/W3216857888","https://openalex.org/W4231258501","https://openalex.org/W4284685252","https://openalex.org/W4304142414","https://openalex.org/W4317677707","https://openalex.org/W4375802461","https://openalex.org/W4378805076","https://openalex.org/W4382203033","https://openalex.org/W4387968123","https://openalex.org/W4388016610","https://openalex.org/W4389140516","https://openalex.org/W4390241396","https://openalex.org/W4390873421","https://openalex.org/W4392488475","https://openalex.org/W4392523432","https://openalex.org/W4393033612","https://openalex.org/W4393148632","https://openalex.org/W4393160568","https://openalex.org/W4393206886","https://openalex.org/W4393405364","https://openalex.org/W4400524868","https://openalex.org/W4400624587","https://openalex.org/W4401595348","https://openalex.org/W4402671723","https://openalex.org/W4402715923","https://openalex.org/W4402754145","https://openalex.org/W4403540486","https://openalex.org/W4403791793","https://openalex.org/W4405416283","https://openalex.org/W4406308627"],"related_works":["https://openalex.org/W2153719181","https://openalex.org/W1971748923","https://openalex.org/W1566155057","https://openalex.org/W2060986072","https://openalex.org/W2052574922","https://openalex.org/W64588465","https://openalex.org/W4381058564","https://openalex.org/W3003945460","https://openalex.org/W2964413124","https://openalex.org/W4288267738"],"abstract_inverted_index":{"Text-based":[0],"visual":[1,35,49,66,88,93,126],"question":[2,44,101],"answering":[3],"(TextVQA)":[4],"aims":[5],"to":[6,39,124,133,190],"answer":[7],"questions":[8],"by":[9,157],"understanding":[10],"scene":[11,52],"text":[12],"in":[13],"images.":[14],"However,":[15],"many":[16],"current":[17],"methods":[18],"overly":[19],"depend":[20],"on":[21,61,78,174],"the":[22,32,43,46,56,63,79,92,100,106,114,141,146,154,175,183,191],"accuracy":[23],"of":[24,34,65,99,185],"Optical":[25],"Character":[26],"Recognition":[27],"(OCR)":[28],"systems,":[29],"while":[30],"overlooking":[31],"significance":[33],"objects.":[36],"They":[37],"tend":[38],"perform":[40],"poorly":[41],"when":[42],"involves":[45],"relationships":[47],"between":[48],"objects":[50,67,127],"and":[51,68,87,162,178],"text.":[53],"To":[54],"address":[55],"above":[57],"issues,":[58],"we":[59,138,151],"focus":[60],"raising":[62],"status":[64],"innovatively":[69],"propose":[70],"a":[71],"hierarchical":[72],"semantic":[73,89,97],"reasoning":[74,86],"network":[75],"(CT-HSR)":[76],"based":[77],"cascade":[80],"transformer":[81,116],"architecture,":[82],"achieving":[83],"fine-grained":[84],"cross-modal":[85,107,142],"enhancement.":[90],"Specifically,":[91],"representations":[94],"containing":[95],"rich":[96],"information":[98],"modality":[102,119],"are":[103,129],"obtained":[104],"through":[105,145,166],"transformer-based":[108],"vision-language":[109],"pre-training":[110,160],"model":[111,188],"firstly.":[112],"Then,":[113],"uni-modal":[115],"for":[117],"unified":[118],"encoding":[120],"module":[121],"is":[122],"utilized":[123],"capture":[125],"that":[128],"more":[130],"semantically":[131],"related":[132],"OCR":[134],"texts.":[135],"In":[136],"addition,":[137],"further":[139],"alleviate":[140],"noise":[143],"interference":[144],"feature":[147],"filtering":[148],"strategy.":[149],"Finally,":[150],"better":[152],"align":[153],"three":[155],"modalities":[156],"introducing":[158],"TextVQA":[159],"tasks":[161],"generate":[163],"prediction":[164,169],"answers":[165],"multi-step":[167],"iterative":[168],"during":[170],"fine-tuning.":[171],"Extensive":[172],"experiments":[173],"TextVQA,":[176],"ST-VQA,":[177],"OCR-VQA":[179],"datasets":[180],"have":[181],"demonstrated":[182],"effectiveness":[184],"our":[186],"proposed":[187],"compared":[189],"state-of-the-art":[192],"methods.":[193],"The":[194],"code":[195],"will":[196],"be":[197],"released":[198],"at":[199],"https://github.com/FTFWO/CT-HSR":[200],".":[201]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
