{"id":"https://openalex.org/W7214027657","doi":"https://doi.org/10.48550/arxiv.2609.24058","title":"All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts","display_name":"All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts","publication_year":2026,"publication_date":"2026-09-21","ids":{"openalex":"https://openalex.org/W7214027657","doi":"https://doi.org/10.48550/arxiv.2609.24058"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.24058","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.24058","pdf_url":"https://arxiv.org/pdf/2609.24058","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"parent_works":[],"lineage":["https://openalex.org/W7214027657"],"child_works_count":0,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.24058","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125403847","display_name":"Xingsong Ye","orcid":"https://orcid.org/0009-0007-4046-7229","observed_orcids":["https://orcid.org/0009-0007-4046-7229"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye, Xingsong","raw_affiliation_strings":["Institute of Trustworthy Embodied AI , Fudan University ,","Shanghai Key Laboratory of Multimodal Embodied AI ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI , Fudan University ,","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Multimodal Embodied AI ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125160903","display_name":"Yongkun Du","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Du, Yongkun","raw_affiliation_strings":["Institute of Trustworthy Embodied AI , Fudan University ,","Shanghai Key Laboratory of Multimodal Embodied AI ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI , Fudan University ,","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Multimodal Embodied AI ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099670493","display_name":"Jiaxin Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Jiaxin","raw_affiliation_strings":["WeChat Vision , Tencent Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WeChat Vision , Tencent Inc","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015121213","display_name":"Zhixian Li","orcid":"https://orcid.org/0000-0003-2649-8137","observed_orcids":["https://orcid.org/0000-0003-2649-8137"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Zhixian","raw_affiliation_strings":["Institute of Trustworthy Embodied AI , Fudan University ,","Shanghai Key Laboratory of Multimodal Embodied AI ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI , Fudan University ,","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Multimodal Embodied AI ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120635511","display_name":"Chong Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sun, Chong","raw_affiliation_strings":["WeChat Vision , Tencent Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WeChat Vision , Tencent Inc","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125387301","display_name":"Chen Li","orcid":"https://orcid.org/0000-0002-0079-3106","observed_orcids":["https://orcid.org/0000-0002-0079-3106","https://orcid.org/0000-0002-2450-8525"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Chen","raw_affiliation_strings":["WeChat Vision , Tencent Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WeChat Vision , Tencent Inc","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124922835","display_name":"Jing Lyu","orcid":"https://orcid.org/0009-0004-2021-0256","observed_orcids":["https://orcid.org/0009-0004-2021-0256"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lyu, Jing","raw_affiliation_strings":["WeChat Vision , Tencent Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WeChat Vision , Tencent Inc","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126835491","display_name":"Lianwen Jin","orcid":"https://orcid.org/0000-0002-5456-0957","observed_orcids":["https://orcid.org/0000-0002-5456-0957"]},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin, Lianwen","raw_affiliation_strings":["South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073175832","display_name":"Zhineng Chen","orcid":"https://orcid.org/0000-0003-1543-6889","observed_orcids":["https://orcid.org/0000-0003-1543-6889"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Zhineng","raw_affiliation_strings":["Institute of Trustworthy Embodied AI , Fudan University ,","Shanghai Key Laboratory of Multimodal Embodied AI ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI , Fudan University ,","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Multimodal Embodied AI ,","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T12707","display_name":"Vehicle License Plate Recognition","score":9.999999747378752e-05,"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/T10036","display_name":"Advanced Neural Network Applications","score":9.999999747378752e-05,"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/mixture-of-experts","display_name":"mixture of experts","score":0.9350000023841858},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.48399999737739563}],"concepts":[{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.8263000249862671},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8246999979019165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.593500018119812},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5512999892234802},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5401999950408936},{"id":"https://openalex.org/C2775896111","wikidata":"https://www.wikidata.org/wiki/Q642560","display_name":"Router","level":2,"score":0.4779999852180481},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.45809999108314514},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39169999957084656},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.3912000060081482},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3898000121116638},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2994999885559082},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2799000144004822},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.27079999446868896},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.24058","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.24058","pdf_url":"https://arxiv.org/pdf/2609.24058","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.24058","doi":"https://doi.org/10.48550/arxiv.2609.24058","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.24058","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.24058","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.24058","pdf_url":"https://arxiv.org/pdf/2609.24058","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214027657.pdf","grobid_xml":"https://content.openalex.org/works/W7214027657.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2194187530","https://openalex.org/W4407451030","https://openalex.org/W4407937981"],"related_works":["https://openalex.org/W4393315369","https://openalex.org/W2965892653","https://openalex.org/W2786443337","https://openalex.org/W4411751016","https://openalex.org/W4367011772","https://openalex.org/W3119673760","https://openalex.org/W7128300691","https://openalex.org/W7161147938","https://openalex.org/W7212029797","https://openalex.org/W4401181723"],"abstract_inverted_index":{"Multilingual":[0],"scene":[1,88],"text":[2,89],"recognition":[3],"(STR)":[4],"remains":[5],"challenging":[6],"due":[7],"to":[8,142,199],"the":[9,18,125,143,168,174,181,188,203,211],"scarcity":[10],"of":[11,20,135,171,210],"training":[12],"data":[13,105],"for":[14],"most":[15],"languages":[16],"and":[17,38,52,76,94,100,123,147],"difficulty":[19],"serving":[21],"diverse":[22],"scripts":[23,93],"within":[24],"a":[25,85,112,119,129,148,208],"single":[26,120],"model.":[27],"Existing":[28],"solutions":[29],"either":[30],"deploy":[31],"one":[32],"recognizer":[33,66,189],"per":[34],"language,":[35],"inflating":[36],"cost":[37],"introducing":[39],"error":[40],"accumulation,":[41],"or":[42],"rely":[43],"on":[44,55,156],"massive":[45],"vision-language":[46],"models":[47],"(VLMs)":[48],"that":[49,67,165],"are":[50],"expensive":[51],"still":[53],"inaccurate":[54],"many":[56],"scripts.":[57],"In":[58],"this":[59],"work,":[60],"we":[61,82,109],"pursue":[62],"an":[63,136],"all-in-one":[64],"multilingual":[65,184],"is":[68,106],"simpler":[69],"than":[70,74,79],"per-language":[71],"experts,":[72],"lighter":[73],"VLMs,":[75],"more":[77],"accurate":[78],"both.":[80],"First,":[81],"construct":[83],"TextMuSS-10M,":[84],"large-scale":[86],"synthetic":[87],"dataset":[90],"spanning":[91],"10":[92],"229":[95],"languages.":[96],"It":[97,117],"provides":[98],"balanced":[99],"sufficient":[101],"supervision":[102],"where":[103],"real":[104],"unavailable.":[107],"Second,":[108],"propose":[110],"ScriptMoE,":[111],"script-aware":[113],"Mixture-of-Experts":[114],"(MoE)":[115],"architecture.":[116],"shares":[118],"visual":[121],"encoder":[122],"replaces":[124],"dense":[126],"decoder":[127],"with":[128,192],"sparse":[130],"MoE":[131],"block,":[132],"which":[133],"consists":[134],"image-level":[137],"router":[138],"dispatches":[139],"each":[140],"image":[141],"top-2":[144],"script-aligned":[145],"experts":[146],"shared":[149],"expert":[150],"absorbs":[151],"cross-script":[152],"knowledge.":[153],"Extensive":[154],"experiments":[155],"our":[157],"assembled":[158],"TextMuSS-Bench":[159],"(10":[160],"scripts,":[161],"10,899":[162],"images)":[163],"show":[164],"ScriptMoE":[166,193],"achieves":[167],"highest":[169],"accuracy":[170],"82.06%,":[172],"outperforming":[173],"strongest":[175],"STR":[176],"baseline":[177],"by":[178],"1.31%.":[179],"On":[180],"CC-OCR":[182],"end-to-end":[183],"task,":[185],"replacing":[186],"only":[187],"in":[190],"PP-OCRv5":[191],"lifts":[194],"F1":[195],"score":[196],"from":[197],"65.71%":[198],"80.89%,":[200],"slightly":[201],"surpassing":[202],"best":[204],"VLM":[205],"(80.73%)":[206],"at":[207],"fraction":[209],"parameter":[212],"count.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-15T12:55:33.944570","created_date":"2026-09-23T00:00:00"}
