{"id":"https://openalex.org/W4416965991","doi":"https://doi.org/10.1109/tmm.2025.3639908","title":"HAAP: Vision-Context Hierarchical Attention Autoregressive With Adaptive Permutation for Scene Text Recognition","display_name":"HAAP: Vision-Context Hierarchical Attention Autoregressive With Adaptive Permutation for Scene Text Recognition","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4416965991","doi":"https://doi.org/10.1109/tmm.2025.3639908"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2025.3639908","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3639908","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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":null,"display_name":"Honghui Chen","orcid":"https://orcid.org/0000-0002-7127-9665"},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honghui Chen","raw_affiliation_strings":["College of Physics and Information Engineering, Fuzhou University, Fuzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7127-9665","affiliations":[{"raw_affiliation_string":"College of Physics and Information Engineering, Fuzhou University, Fuzhou, China","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015955856","display_name":"Yuhang Qiu","orcid":"https://orcid.org/0000-0002-9706-4013"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yuhang Qiu","raw_affiliation_strings":["Faculty of Engineering, Monash University, Melbourne, VIC, Australia","Faculty of Engineering, Monash University, Clayton, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9706-4013","affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Monash University, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]},{"raw_affiliation_string":"Faculty of Engineering, Monash University, Clayton, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiabao Wang","orcid":"https://orcid.org/0009-0007-2243-786X"},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiabao Wang","raw_affiliation_strings":["College of Physics and Information Engineering, Fuzhou University, Fuzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-2243-786X","affiliations":[{"raw_affiliation_string":"College of Physics and Information Engineering, Fuzhou University, Fuzhou, China","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748906","display_name":"Pingping Chen","orcid":"https://orcid.org/0000-0002-2876-653X"},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pingping Chen","raw_affiliation_strings":["College of Physics and Information Engineering, Fuzhou University, Fuzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2876-653X","affiliations":[{"raw_affiliation_string":"College of Physics and Information Engineering, Fuzhou University, Fuzhou, China","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018686979","display_name":"Nam Ling","orcid":"https://orcid.org/0000-0002-5741-7937"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nam Ling","raw_affiliation_strings":["Department of Computer Science and Engineering, Santa Clara University, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5741-7937","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Santa Clara University, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I16269868"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"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":0.35092084,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"1523","last_page":"1533"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.7670999765396118,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.7670999765396118,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.15129999816417694,"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":0.01889999955892563,"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/autoregressive-model","display_name":"Autoregressive model","score":0.6262999773025513},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5375000238418579},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.5314000248908997},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.43619999289512634},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.43230000138282776},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42080000042915344},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3955000042915344},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.3483000099658966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8673999905586243},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6262999773025513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5752999782562256},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5375000238418579},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.5314000248908997},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.43619999289512634},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.43230000138282776},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42080000042915344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40869998931884766},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3955000042915344},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C200985842","wikidata":"https://www.wikidata.org/wiki/Q3375503","display_name":"Random permutation","level":3,"score":0.3427000045776367},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3021000027656555},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3639908","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3639908","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7307896700","display_name":null,"funder_award_id":"62171135","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":52,"referenced_works":["https://openalex.org/W108866686","https://openalex.org/W1903029394","https://openalex.org/W1934184906","https://openalex.org/W1971822075","https://openalex.org/W1981283549","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2024484010","https://openalex.org/W2105482032","https://openalex.org/W2144554289","https://openalex.org/W2146835493","https://openalex.org/W2194187530","https://openalex.org/W2294053032","https://openalex.org/W2343052201","https://openalex.org/W2795619303","https://openalex.org/W2810983211","https://openalex.org/W2875814315","https://openalex.org/W2963587345","https://openalex.org/W2964065044","https://openalex.org/W2965066169","https://openalex.org/W2997749585","https://openalex.org/W3003218881","https://openalex.org/W3003711889","https://openalex.org/W3003868038","https://openalex.org/W3003921261","https://openalex.org/W3034447740","https://openalex.org/W3035449864","https://openalex.org/W3035682985","https://openalex.org/W3177684257","https://openalex.org/W3179897446","https://openalex.org/W3181186176","https://openalex.org/W3202415716","https://openalex.org/W3204479434","https://openalex.org/W3217697975","https://openalex.org/W4210692322","https://openalex.org/W4225562651","https://openalex.org/W4281616076","https://openalex.org/W4283819468","https://openalex.org/W4285065310","https://openalex.org/W4285191490","https://openalex.org/W4285606530","https://openalex.org/W4293202879","https://openalex.org/W4307157288","https://openalex.org/W4312879041","https://openalex.org/W4319777850","https://openalex.org/W4360595157","https://openalex.org/W4362475272","https://openalex.org/W4385245566","https://openalex.org/W4387740410","https://openalex.org/W4390463734","https://openalex.org/W4402753732","https://openalex.org/W4405784827"],"related_works":[],"abstract_inverted_index":{"Scene":[0],"Text":[1],"Recognition":[2],"(STR)":[3],"is":[4,16,22,124],"challenging":[5],"in":[6,36,164],"extracting":[7],"effective":[8],"character":[9,26],"representations":[10],"from":[11],"visual":[12,33,103,136],"data":[13],"when":[14],"text":[15],"unreadable.":[17],"Permutation":[18,71,86],"language":[19],"modeling":[20],"(PLM)":[21],"introduced":[23,125],"to":[24,73,89,126,142],"refine":[25],"predictions":[27],"by":[28],"jointly":[29],"capturing":[30],"contextual":[31,133],"and":[32,47,105,135,169],"information.":[34,137],"However,":[35],"PLM,":[37],"the":[38,48,64,100,111,118,128,148,157],"use":[39],"of":[40,166],"random":[41],"permutations":[42],"causes":[43],"training":[44,114],"fit":[45,115],"oscillation,":[46],"iterative":[49],"refinement":[50],"(IR)":[51],"operation":[52],"also":[53],"introduces":[54],"additional":[55],"overhead.":[56],"To":[57],"address":[58],"these":[59],"issues,":[60],"this":[61],"paper":[62],"proposes":[63],"Hierarchical":[65,120],"Attention":[66,121],"autoregressive":[67,79],"Model":[68],"with":[69],"Adaptive":[70,107],"(HAAP)":[72],"enhance":[74],"position-context-image":[75],"interaction":[76],"capability,":[77],"improving":[78],"LM":[80],"generalization.":[81],"First,":[82],"we":[83],"propose":[84],"Implicit":[85],"Neurons":[87],"(IPN)":[88],"generate":[90],"adaptive":[91],"attention":[92],"masks":[93],"that":[94,156],"dynamically":[95],"exploit":[96],"token":[97],"dependencies,":[98],"enhancing":[99],"correlation":[101,108],"between":[102],"information":[104],"context.":[106],"representation":[109],"helps":[110],"model":[112],"avoid":[113],"oscillation.":[116],"Second,":[117],"Cross-modal":[119],"mechanism":[122],"(CHA)":[123],"capture":[127],"dependencies":[129],"among":[130],"position":[131,140],"queries,":[132],"semantics":[134],"CHA":[138],"enables":[139],"tokens":[141],"aggregate":[143],"global":[144],"semantic":[145],"information,":[146],"avoiding":[147],"need":[149],"for":[150],"IR.":[151],"Extensive":[152],"experimental":[153],"results":[154],"show":[155],"proposed":[158],"HAAP":[159],"achieves":[160],"state-of-the-art":[161],"(SOTA)":[162],"performance":[163],"terms":[165],"accuracy,":[167],"complexity,":[168],"latency":[170],"on":[171],"several":[172],"datasets.":[173]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-03T00:00:00"}