{"id":"https://openalex.org/W4392902806","doi":"https://doi.org/10.1109/icassp48485.2024.10445873","title":"Segment then Match: Find the Carrier before Reasoning in Scene-Text VQA","display_name":"Segment then Match: Find the Carrier before Reasoning in Scene-Text VQA","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902806","doi":"https://doi.org/10.1109/icassp48485.2024.10445873"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5085542141","display_name":"Chengyang Fang","orcid":"https://orcid.org/0000-0002-3583-9119"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengyang Fang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering","Institute of Information Engineering, Chinese Academy of Sciences","School of Cyber Security, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034640518","display_name":"Liang Li","orcid":"https://orcid.org/0000-0001-8437-4824"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Li","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering","Institute of Information Engineering, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102978348","display_name":"Jiapeng Liu","orcid":"https://orcid.org/0009-0002-0249-908X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiapeng Liu","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering","Institute of Information Engineering, Chinese Academy of Sciences","School of Cyber Security, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339915","display_name":"Bing Li","orcid":"https://orcid.org/0000-0002-1251-4346"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Li","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering","Institute of Information Engineering, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101153367","display_name":"HU Da-yong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dayong Hu","raw_affiliation_strings":["Heilongjiang Network Space Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Heilongjiang Network Space Research Center","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101021225","display_name":"Can Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Can Ma","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering","Institute of Information Engineering, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2629,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46225998,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"8130","last_page":"8134"},"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":0.9991000294685364,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9915000200271606,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8138623237609863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6953097581863403},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6423967480659485},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6250501871109009},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5610400438308716},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5425769090652466},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5378557443618774},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5148324370384216},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5014684200286865},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49122685194015503},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.454124391078949},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4411129057407379},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4222072958946228},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4157556891441345},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08214795589447021}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8138623237609863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6953097581863403},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6423967480659485},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6250501871109009},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5610400438308716},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5425769090652466},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5378557443618774},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5148324370384216},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5014684200286865},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49122685194015503},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.454124391078949},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4411129057407379},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4222072958946228},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4157556891441345},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08214795589447021},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2008806374","https://openalex.org/W2012689760","https://openalex.org/W2058556535","https://openalex.org/W2108598243","https://openalex.org/W2144554289","https://openalex.org/W2277195237","https://openalex.org/W2979382951","https://openalex.org/W2988326850","https://openalex.org/W3034336960","https://openalex.org/W3035644209","https://openalex.org/W3093385053","https://openalex.org/W3115287481","https://openalex.org/W3179897446","https://openalex.org/W3181159501","https://openalex.org/W3205050305","https://openalex.org/W3215381707","https://openalex.org/W3215633354","https://openalex.org/W4221165960","https://openalex.org/W4288083516","https://openalex.org/W4295246343","https://openalex.org/W4304142414","https://openalex.org/W4312263373","https://openalex.org/W4382203033","https://openalex.org/W4388189392","https://openalex.org/W6620707391","https://openalex.org/W6769627184","https://openalex.org/W6781214006","https://openalex.org/W6845600268"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W4212839359","https://openalex.org/W2115758952"],"abstract_inverted_index":{"Text-based":[0],"Visual":[1,125],"Question":[2],"Answering":[3],"(TextVQA)":[4],"requires":[5],"models":[6],"to":[7,78,99,118,129],"answer":[8,144],"questions":[9],"about":[10],"the":[11,18,21,25,32,37,40,47,70,80,105,114,143,166],"scene":[12,22,33,44,53,63,106],"text":[13,23,34,54,64,136],"in":[14,46,61,69,104],"images":[15],"by":[16,153],"reasoning":[17,145],"context":[19,41],"between":[20,42],"and":[24,96,102,108,155,159],"question.":[26],"Previous":[27],"works":[28],"demonstrated":[29],"that":[30,116],"clustering":[31],"could":[35],"help":[36,109],"model":[38],"understand":[39],"different":[43],"texts":[45,101,112],"image.":[48],"However,":[49],"these":[50],"methods":[51,152],"cluster":[52],"solely":[55],"based":[56],"on":[57,157],"spatial":[58],"information,":[59],"resulting":[60],"close":[62],"being":[65],"grouped":[66],"together":[67],"even":[68],"absence":[71],"of":[72,134,168],"semantic":[73,131],"contextual":[74],"relationships.":[75],"In":[76],"order":[77],"solve":[79],"above":[81],"problem,":[82],"we":[83,91,121],"proposed":[84,148],"a":[85,123],"Segment":[86],"then":[87],"Match":[88],"method.":[89,170],"Specifically,":[90],"propose":[92,122],"an":[93],"OCR-carrier":[94],"Segmentation":[95],"Matching":[97],"module":[98,128],"segment":[100],"carriers":[103],"image":[107],"all":[110],"OCR":[111,135],"find":[113],"carrier":[115],"belongs":[117],"them.":[119],"Then,":[120],"Hierarchical":[124],"Feature":[126],"Fusion":[127],"facilitate":[130],"relevance":[132],"judgment":[133],"from":[137],"multiple":[138],"visual":[139],"perspectives,":[140],"thereby":[141],"aiding":[142],"process.":[146],"Our":[147],"method":[149],"outperforms":[150],"state-of-the-art":[151],"3.65%":[154],"3.31%":[156],"TextVQA":[158],"ST-VQA":[160],"datasets,":[161],"respectively.":[162],"Extensive":[163],"experiments":[164],"validate":[165],"effectiveness":[167],"our":[169]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}