{"id":"https://openalex.org/W7125581941","doi":"https://doi.org/10.1145/3793249","title":"Improving Chinese Text Recognition with Multi-Granularity Features and Vision-Language Reasoning","display_name":"Improving Chinese Text Recognition with Multi-Granularity Features and Vision-Language Reasoning","publication_year":2026,"publication_date":"2026-01-23","ids":{"openalex":"https://openalex.org/W7125581941","doi":"https://doi.org/10.1145/3793249"},"language":"en","primary_location":{"id":"doi:10.1145/3793249","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793249","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3793249","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123763759","display_name":"Tao Li","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Li","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China"],"raw_orcid":"https://orcid.org/0000-0003-0441-6655","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zengfu Wang","orcid":"https://orcid.org/0000-0003-1859-900X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"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/I4210099079","display_name":"Institute of Intelligent Machines","ror":"https://ror.org/00w0qep84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667","https://openalex.org/I4210099079"]},{"id":"https://openalex.org/I4210159412","display_name":"Intelligent Machines (Sweden)","ror":"https://ror.org/05nzk9q32","country_code":"SE","type":"company","lineage":["https://openalex.org/I4210159412"]}],"countries":["CN","SE"],"is_corresponding":false,"raw_author_name":"Zengfu Wang","raw_affiliation_strings":["Chinese Academy of Sciences Institute of Intelligent Machines","School of Information Science and Technology, University of Science and Technology of China"],"raw_orcid":"https://orcid.org/0000-0003-1859-900X","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences Institute of Intelligent Machines","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099079","https://openalex.org/I4210159412"]},{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":0.08005449,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":"4","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9054999947547913,"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":0.9054999947547913,"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":0.05310000106692314,"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":0.0071000000461936,"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/encoder","display_name":"Encoder","score":0.5171999931335449},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4749999940395355},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.41110000014305115},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.374099999666214},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.3617999851703644},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3492000102996826},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.3458999991416931},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.34369999170303345}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7832000255584717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6347000002861023},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5180000066757202},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5171999931335449},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4749999940395355},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.41110000014305115},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3617999851703644},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.3458999991416931},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3305000066757202},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33009999990463257},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C2779200073","wikidata":"https://www.wikidata.org/wiki/Q18395575","display_name":"Visual masking","level":4,"score":0.29919999837875366},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2678999900817871},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26249998807907104},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2572000026702881},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3793249","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793249","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3793249","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793249","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5871076583862305,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2194775991","https://openalex.org/W2294053032","https://openalex.org/W2531409750","https://openalex.org/W2565262489","https://openalex.org/W2945136398","https://openalex.org/W2963526661","https://openalex.org/W2965066169","https://openalex.org/W2997749585","https://openalex.org/W3034414401","https://openalex.org/W3034447740","https://openalex.org/W3035449864","https://openalex.org/W3181186176","https://openalex.org/W3197469504","https://openalex.org/W3202415716","https://openalex.org/W4224284647","https://openalex.org/W4312879041","https://openalex.org/W4312950730","https://openalex.org/W4382202677","https://openalex.org/W4386410320","https://openalex.org/W4387580232","https://openalex.org/W4390463734","https://openalex.org/W4390872693","https://openalex.org/W4395085401","https://openalex.org/W4406047244","https://openalex.org/W4407937981"],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"Chinese":[1,132],"text":[2,92,133],"recognition":[3],"(CTR)":[4],"is":[5],"vital":[6],"for":[7,72],"applications":[8],"such":[9],"as":[10],"document":[11],"digitization,":[12],"but":[13],"remains":[14],"challenging":[15],"due":[16],"to":[17,65,90],"high":[18],"inter-class":[19],"visual":[20,27,45,69,96],"similarity,":[21],"complex":[22],"hierarchical":[23,62],"structures,":[24],"and":[25,57,97],"diverse":[26],"degradations":[28],"in":[29,127],"real-world":[30],"scenes.":[31],"To":[32],"address":[33],"these":[34],"challenges,":[35],"we":[36],"propose":[37],"a":[38,85],"robust":[39],"CTR":[40],"framework":[41],"that":[42,104,118],"synergizes":[43],"structure-aware":[44,68],"discrimination":[46],"with":[47,84],"cross-modal":[48],"reasoning.":[49],"The":[50],"hybrid":[51],"encoder":[52],"integrates":[53],"multi-scale":[54],"attention":[55],"modulation":[56],"global":[58],"self-attention,":[59],"guided":[60],"by":[61],"structural":[63],"supervision,":[64],"capture":[66],"fine-grained":[67],"representations":[70],"essential":[71],"distinguishing":[73],"visually":[74,107],"similar":[75],"characters.":[76,111],"Complementing":[77],"this,":[78],"an":[79],"iterative":[80],"vision-language":[81,102],"decoder,":[82],"trained":[83],"stochastic":[86],"masking":[87],"strategy,":[88],"learns":[89],"reconstruct":[91],"from":[93],"partially":[94],"observed":[95],"contextual":[98],"cues,":[99],"enabling":[100],"complementary":[101],"reasoning":[103],"effectively":[105],"resolves":[106],"ambiguous":[108],"or":[109],"degraded":[110],"Extensive":[112],"experiments":[113],"on":[114],"public":[115],"benchmarks":[116],"demonstrate":[117],"our":[119],"method":[120],"achieves":[121],"state-of-the-art":[122],"performance,":[123],"validating":[124],"its":[125],"effectiveness":[126],"addressing":[128],"the":[129],"challenges":[130],"of":[131],"recognition.":[134]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-01-25T00:00:00"}
