{"id":"https://openalex.org/W4390660210","doi":"https://doi.org/10.1109/tmm.2024.3350916","title":"VOLTER: Visual Collaboration and Dual-Stream Fusion for Scene Text Recognition","display_name":"VOLTER: Visual Collaboration and Dual-Stream Fusion for Scene Text Recognition","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4390660210","doi":"https://doi.org/10.1109/tmm.2024.3350916"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3350916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3350916","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":"Jia-Nan Li","orcid":"https://orcid.org/0009-0004-7660-5724"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia-Nan Li","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0004-7660-5724","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100683612","display_name":"Xiaoqian Liu","orcid":"https://orcid.org/0000-0002-2187-8598"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Qian Liu","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-2187-8598","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052168662","display_name":"Xin Luo","orcid":"https://orcid.org/0000-0002-6901-5476"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Luo","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-6901-5476","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086235570","display_name":"Xin-Shun Xu","orcid":"https://orcid.org/0000-0001-9972-7370"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin-Shun Xu","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0001-9972-7370","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":1.0219,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74903212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"26","issue":null,"first_page":"6437","last_page":"6448"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9955000281333923,"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":0.9955000281333923,"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":0.993399977684021,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9908000230789185,"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":0.8554195165634155},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6160911917686462},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5661681890487671},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5497973561286926},{"id":"https://openalex.org/keywords/fusion-mechanism","display_name":"Fusion mechanism","score":0.48754259943962097},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4817347824573517},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4273911118507385},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36243683099746704},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35402143001556396},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.3535583019256592}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8554195165634155},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6160911917686462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5661681890487671},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5497973561286926},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.48754259943962097},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4817347824573517},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4273911118507385},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36243683099746704},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35402143001556396},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3535583019256592},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C103038307","wikidata":"https://www.wikidata.org/wiki/Q6556360","display_name":"Lipid bilayer fusion","level":3,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded 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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3350916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3350916","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":[{"score":0.47999998927116394,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[{"id":"https://openalex.org/G513007275","display_name":null,"funder_award_id":"62202278","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5641611171","display_name":null,"funder_award_id":"ZR2020QF036","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G5877029504","display_name":null,"funder_award_id":"ZR2019ZD06","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G7923371280","display_name":null,"funder_award_id":"62202272","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G98586731","display_name":null,"funder_award_id":"62172256","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/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1491389626","https://openalex.org/W1901129140","https://openalex.org/W1971822075","https://openalex.org/W1981283549","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2064675550","https://openalex.org/W2078008442","https://openalex.org/W2128409098","https://openalex.org/W2130103520","https://openalex.org/W2144554289","https://openalex.org/W2146835493","https://openalex.org/W2194187530","https://openalex.org/W2290736026","https://openalex.org/W2343052201","https://openalex.org/W2537773590","https://openalex.org/W2795619303","https://openalex.org/W2810983211","https://openalex.org/W2914107945","https://openalex.org/W2963517393","https://openalex.org/W2963712589","https://openalex.org/W2964065044","https://openalex.org/W2972424968","https://openalex.org/W3003218881","https://openalex.org/W3003711889","https://openalex.org/W3003868038","https://openalex.org/W3003921261","https://openalex.org/W3004846386","https://openalex.org/W3034414401","https://openalex.org/W3035449864","https://openalex.org/W3096831136","https://openalex.org/W3110267192","https://openalex.org/W3119350346","https://openalex.org/W3134064484","https://openalex.org/W3175618949","https://openalex.org/W3177684257","https://openalex.org/W3181186176","https://openalex.org/W3198359920","https://openalex.org/W3202415716","https://openalex.org/W3202912918","https://openalex.org/W3206651063","https://openalex.org/W3217697975","https://openalex.org/W4210692322","https://openalex.org/W4225562651","https://openalex.org/W4229030834","https://openalex.org/W4281616076","https://openalex.org/W4295246343","https://openalex.org/W4308757601","https://openalex.org/W4308759326","https://openalex.org/W4312787220","https://openalex.org/W4312843595","https://openalex.org/W4312928771","https://openalex.org/W4312950730","https://openalex.org/W4313045695","https://openalex.org/W4313170256","https://openalex.org/W4385767840","https://openalex.org/W6618372016","https://openalex.org/W6629590909","https://openalex.org/W6691603626","https://openalex.org/W6767563286","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6846421636"],"related_works":["https://openalex.org/W2988498288","https://openalex.org/W1991764124","https://openalex.org/W2786308501","https://openalex.org/W2012247345","https://openalex.org/W4318719019","https://openalex.org/W2145243726","https://openalex.org/W2351649588","https://openalex.org/W4378188910","https://openalex.org/W1998943912","https://openalex.org/W2463550667"],"abstract_inverted_index":{"Recently,":[0],"the":[1,40,47,60,67,71,74,79,86,89,92,96,114,179,212,220,237],"approaches":[2],"of":[3,16,42,51,56,70,101,182,215,223],"linguistic":[4],"modeling":[5],"for":[6,138,143,211],"scene":[7,139],"text":[8],"recognition":[9],"have":[10,199],"gradually":[11],"become":[12,91],"mainstream,":[13],"mainly":[14,49],"consisting":[15],"a":[17,21,52,120,146,171,188,203],"vision":[18,167,173],"model":[19,23],"(VM),":[20],"language":[22,99],"(LM),":[24],"and":[25,35,98,135,160,184,226],"an":[26],"optional":[27],"fusion":[28,36,137,228],"module.":[29],"These":[30],"methods":[31,103],"typically":[32],"use":[33],"LM":[34],"modules":[37],"to":[38,66,119,122,155,169,176,198,218],"refine":[39],"results":[41,87],"VM-based":[43],"predictions":[44],"iteratively.":[45],"However,":[46],"VM":[48,90,183],"consists":[50],"Transformer":[53],"on":[54,157,232],"top":[55],"ResNet.":[57],"It":[58],"means":[59],"attention":[61],"mechanism":[62],"is":[63,153,209],"only":[64],"applied":[65],"high":[68],"layer":[69],"VM,":[72],"ignoring":[73],"internal":[75],"image":[76],"dependencies":[77],"in":[78,88,105],"dense":[80],"features":[81,100,162,217],"at":[82,163],"multiple":[83,164],"scales.":[84],"Therefore,":[85],"performance":[93],"bottleneck.":[94],"Meanwhile,":[95],"visual":[97],"these":[102,129],"reside":[104],"their":[106],"own":[107],"space.":[108],"In":[109],"this":[110],"way,":[111],"it":[112],"ignores":[113],"alignment":[115,221],"before":[116],"fusion,":[117],"leading":[118],"failure":[121],"achieve":[123,241],"maximum":[124],"information":[125],"interaction.":[126],"To":[127],"address":[128],"issues,":[130],"we":[131,186],"propose":[132],"Visual":[133],"cOllaboration":[134],"duaL-stream":[136],"TExt":[140],"Recognition,":[141],"VOLTER":[142],"short.":[144],"Firstly,":[145],"multi-stage":[147],"Local-Global":[148],"Collaboration":[149],"Vision":[150],"Model":[151],"(LGC-VM)":[152],"constructed":[154],"focus":[156],"both":[158],"local":[159],"global":[161],"scales,":[165],"breaking":[166],"bottlenecks":[168],"provide":[170],"better":[172],"prediction.":[174],"Secondly,":[175],"explicitly":[177],"align":[178],"feature":[180],"space":[181],"LM,":[185],"introduce":[187],"Vision-Language":[189],"Contrastive":[190],"(VLC)":[191],"module":[192,208],"by":[193],"encouraging":[194],"positive":[195],"vision-language":[196],"pairs":[197],"similar":[200],"representations.":[201],"Moreover,":[202],"Dual-Stream":[204],"Feature":[205],"Enhancement":[206],"(DSFE)":[207],"proposed":[210,238],"unidirectional":[213],"interaction":[214],"visual-language":[216],"alleviate":[219],"problem":[222],"different":[224],"modalities":[225],"execute":[227],"further.":[229],"Extensive":[230],"experiments":[231],"benchmark":[233],"datasets":[234],"demonstrate":[235],"that":[236],"framework":[239],"can":[240],"state-of-the-art":[242],"performance.":[243]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}