{"id":"https://openalex.org/W4414404370","doi":"https://doi.org/10.3724/2096-7004.di.2025.0140","title":"TibOCR-Bench: A Comprehensive Benchmark and Training Pipeline for Tibetan Multimodal OCR","display_name":"TibOCR-Bench: A Comprehensive Benchmark and Training Pipeline for Tibetan Multimodal OCR","publication_year":2025,"publication_date":"2025-09-22","ids":{"openalex":"https://openalex.org/W4414404370","doi":"https://doi.org/10.3724/2096-7004.di.2025.0140"},"language":"en","primary_location":{"id":"doi:10.3724/2096-7004.di.2025.0140","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0140","pdf_url":null,"source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.3724/2096-7004.di.2025.0140","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022571725","display_name":"Lu Jie","orcid":"https://orcid.org/0000-0001-5046-3917"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"LAMA Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119694904","display_name":"Manla Cairang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manla Cairang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072794373","display_name":"Kuntharrgyal Khysru","orcid":"https://orcid.org/0000-0002-6673-9583"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kuntharrgyal Khysru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119694905","display_name":"Hua Guo Cai Rang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hua Guo Cai Rang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051304090","display_name":"Jiahui Jiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiao Jiahui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yue Yingkai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Yingkai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100932272","display_name":"Qian Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan Qian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.12837465,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":"2","first_page":"20250140","last_page":"20250140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9904000163078308,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9904000163078308,"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"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9836000204086304,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9620000123977661,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7231000065803528},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.715399980545044},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5805000066757202},{"id":"https://openalex.org/keywords/strengths-and-weaknesses","display_name":"Strengths and weaknesses","score":0.48660001158714294},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.48500001430511475},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.43709999322891235},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.43309998512268066},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.37630000710487366}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.745199978351593},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7231000065803528},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.715399980545044},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5805000066757202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5717999935150146},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.48660001158714294},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.48500001430511475},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4839000105857849},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.43709999322891235},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.37630000710487366},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3384000062942505},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3084999918937683},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3050000071525574},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.2752000093460083},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.263700008392334},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.25870001316070557}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3724/2096-7004.di.2025.0140","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0140","pdf_url":null,"source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3724/2096-7004.di.2025.0140","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0140","pdf_url":null,"source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"large":[3],"multimodal":[4,148,243],"language":[5,18],"models":[6,150],"(such":[7],"as":[8,221,223],"GPT-4V":[9],"and":[10,20,64,68,97,100,133,155,170,182,197,226,239],"Gemini)":[11],"have":[12,209],"achieved":[13],"significant":[14],"advancements":[15],"in":[16,26,205,241],"natural":[17],"processing":[19],"vision-language":[21],"tasks.":[22],"However,":[23],"their":[24,164],"capabilities":[25],"text-related":[27],"visual":[28],"tasks":[29],"for":[30,54,112,236,245],"low-resource":[31,246],"languages,":[32],"particularly":[33],"Tibetan,":[34],"re-":[35],"main":[36],"insufficiently":[37],"explored.":[38],"To":[39,201],"bridge":[40],"this":[41,44,72],"research":[42,204,238],"gap,":[43],"paper":[45],"proposes":[46],"a":[47,125,233],"systematic":[48],"data":[49,110,215],"construction":[50,216],"pipeline":[51],"specifically":[52,104],"designed":[53],"Tibetan":[55,88,113,120,190,206],"Optical":[56],"Character":[57],"Recognition":[58],"(OCR)":[59],"tasks,":[60,122],"supporting":[61],"comprehensive":[62],"multi-scene":[63],"multi-task":[65],"model":[66,142],"training":[67,109,225],"evaluation.":[69],"Based":[70],"on":[71],"pipeline,":[73,217],"we":[74,123,208],"constructed":[75,174],"two":[76],"benchmark":[77,85],"datasets:":[78],"(1)":[79],"<bold>TibOCR-Bench</bold>,":[80],"the":[81,116,168,173,213,224],"first":[82],"eval-":[83],"uation":[84],"dedicated":[86],"to":[87,138],"OCR,":[89,207],"encompassing":[90],"30":[91],"diverse":[92],"application":[93],"scenarios,":[94,186],"ensuring":[95],"high-quality":[96],"uncontaminated":[98],"data;":[99],"(2)":[101],"<bold>TibOCR-Train</bold>,":[102],"which":[103],"ad-":[105],"dresses":[106],"human":[107,158],"preference-aligned":[108],"requirements":[111],"OCR.":[114],"Considering":[115],"unique":[117],"challenges":[118],"of":[119,172],"OCR":[121],"developed":[124],"standardized":[126],"evaluation":[127],"framework,":[128],"including":[129,187],"clear":[130],"inference":[131,227],"protocols":[132],"quantitative":[134],"metric":[135],"calculations":[136],"tailored":[137],"effectively":[139],"as-":[140],"sess":[141],"performance.":[143],"Experimental":[144],"results":[145],"demonstrated":[146],"that":[147],"baseline":[149],"fine-tuned":[151],"via":[152],"instruction":[153],"tuning":[154],"reinforcement":[156],"learning-based":[157],"preference":[159],"alignment":[160],"strategies":[161],"significantly":[162],"outperformed":[163],"un-tuned":[165],"counterparts,":[166],"highlighting":[167],"effectiveness":[169],"practicality":[171],"datasets.":[175],"Further":[176],"analysis":[177],"revealed":[178],"these":[179],"models\u2019":[180],"strengths":[181],"weaknesses":[183],"across":[184],"various":[185],"recognizing":[188],"printed":[189],"text,":[191,196],"handwrit-":[192],"ten":[193],"content,":[194],"non-semantic":[195],"structured":[198],"table":[199],"extraction.":[200],"promote":[202],"further":[203],"made":[210],"publicly":[211],"available":[212],"entire":[214],"datasets,":[218],"trained":[219],"models,":[220],"well":[222],"code.":[228],"These":[229],"open-source":[230],"resources":[231],"provide":[232],"robust":[234],"foundation":[235],"future":[237],"innovation":[240],"zero-shot":[242],"techniques":[244],"languages.":[247]},"counts_by_year":[],"updated_date":"2026-06-14T06:11:07.267592","created_date":"2025-10-10T00:00:00"}