{"id":"https://openalex.org/W4417106274","doi":"https://doi.org/10.1108/ijwis-07-2025-0204","title":"Geometry-aware and autonomous reading-order learning for OCR-free document parsing","display_name":"Geometry-aware and autonomous reading-order learning for OCR-free document parsing","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W4417106274","doi":"https://doi.org/10.1108/ijwis-07-2025-0204"},"language":"en","primary_location":{"id":"doi:10.1108/ijwis-07-2025-0204","is_oa":false,"landing_page_url":"https://doi.org/10.1108/ijwis-07-2025-0204","pdf_url":null,"source":{"id":"https://openalex.org/S145159096","display_name":"International Journal of Web Information Systems","issn_l":"1744-0084","issn":["1744-0084","1744-0092"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Web Information Systems","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":"https://openalex.org/A5101801467","display_name":"Weina Zhang","orcid":"https://orcid.org/0009-0002-8467-512X"},"institutions":[{"id":"https://openalex.org/I23632641","display_name":"Shanghai University of Electric Power","ror":"https://ror.org/02w4tny03","country_code":"CN","type":"education","lineage":["https://openalex.org/I23632641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weina Zhang","raw_affiliation_strings":["Shanghai University of Electric Power College of Computer Science and Technology, , Shanghai,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University of Electric Power College of Computer Science and Technology, , Shanghai,","institution_ids":["https://openalex.org/I23632641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101576478","display_name":"Fangyu Liu","orcid":"https://orcid.org/0000-0003-1554-1478"},"institutions":[{"id":"https://openalex.org/I23632641","display_name":"Shanghai University of Electric Power","ror":"https://ror.org/02w4tny03","country_code":"CN","type":"education","lineage":["https://openalex.org/I23632641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangyu Liu","raw_affiliation_strings":["Shanghai University of Electric Power College of Computer Science and Technology, , Shanghai,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University of Electric Power College of Computer Science and Technology, , Shanghai,","institution_ids":["https://openalex.org/I23632641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013789785","display_name":"Zhe Xu","orcid":"https://orcid.org/0000-0002-0440-0912"},"institutions":[{"id":"https://openalex.org/I23632641","display_name":"Shanghai University of Electric Power","ror":"https://ror.org/02w4tny03","country_code":"CN","type":"education","lineage":["https://openalex.org/I23632641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Xu","raw_affiliation_strings":["Shanghai University of Electric Power College of Computer Science and Technology, , Shanghai,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University of Electric Power College of Computer Science and Technology, , Shanghai,","institution_ids":["https://openalex.org/I23632641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068537006","display_name":"Zhongqin Bi","orcid":"https://orcid.org/0000-0001-8815-4845"},"institutions":[{"id":"https://openalex.org/I23632641","display_name":"Shanghai University of Electric Power","ror":"https://ror.org/02w4tny03","country_code":"CN","type":"education","lineage":["https://openalex.org/I23632641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongqin Bi","raw_affiliation_strings":["Shanghai University of Electric Power College of Computer Science and Technology, , Shanghai,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University of Electric Power College of Computer Science and Technology, , Shanghai,","institution_ids":["https://openalex.org/I23632641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101801467"],"corresponding_institution_ids":["https://openalex.org/I23632641"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36021633,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"1","first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9182999730110168,"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":0.9182999730110168,"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":0.02459999918937683,"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":0.003700000001117587,"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/parsing","display_name":"Parsing","score":0.7217000126838684},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5777999758720398},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.438400000333786},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.4287000000476837},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3776000142097473},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.3630000054836273},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35600000619888306},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3488999903202057},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.310699999332428}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8744999766349792},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7217000126838684},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5777999758720398},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5213000178337097},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.438400000333786},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.4287000000476837},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.3630000054836273},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3564999997615814},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.310699999332428},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.30230000615119934},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.29510000348091125},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29269999265670776},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.2874000072479248},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2619999945163727},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2587999999523163},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.25760000944137573},{"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/C164883195","wikidata":"https://www.wikidata.org/wiki/Q674834","display_name":"Dependency grammar","level":3,"score":0.257099986076355},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1108/ijwis-07-2025-0204","is_oa":false,"landing_page_url":"https://doi.org/10.1108/ijwis-07-2025-0204","pdf_url":null,"source":{"id":"https://openalex.org/S145159096","display_name":"International Journal of Web Information Systems","issn_l":"1744-0084","issn":["1744-0084","1744-0092"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Web Information Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2163534337","https://openalex.org/W2986619406","https://openalex.org/W2997154779","https://openalex.org/W3003484198","https://openalex.org/W3138516171","https://openalex.org/W3173325518","https://openalex.org/W3176664887","https://openalex.org/W4221167941","https://openalex.org/W4304013646","https://openalex.org/W4385990846","https://openalex.org/W4389519972","https://openalex.org/W4402856535","https://openalex.org/W4403808856","https://openalex.org/W4405416283"],"related_works":[],"abstract_inverted_index":{"Purpose":[0],"The":[1,138],"purpose":[2],"of":[3,11,130,153],"this":[4],"study":[5],"is":[6,75],"to":[7,49,53,60,92,116,121],"address":[8,67],"the":[9,46,57,70,111],"task":[10],"visually":[12],"rich":[13],"document":[14,23,81,122,144,180],"understanding,":[15],"which":[16],"extracts":[17],"structured":[18,147],"semantics":[19],"from":[20,30,36],"complex":[21,37],"multimodal":[22],"images.":[24],"Core":[25],"challenges,":[26],"including":[27],"feature":[28,104,132],"distortion":[29,187],"geometric":[31,154],"deformations":[32],"and":[33,43,56,110,134,146,156,201],"structural":[34,157,209],"deviations":[35],"layouts,":[38],"jointly":[39],"undermine":[40],"extraction":[41,149],"precision":[42],"robustness":[44],"\u2013":[45],"former":[47],"due":[48,59],"inadequate":[50],"cross-modal":[51],"adaptation":[52],"local":[54],"distortions":[55],"latter":[58],"constrained":[61],"global":[62],"topology":[63,210],"modeling.":[64],"Design/methodology/approach":[65],"To":[66],"these":[68],"limitations,":[69],"Geometry-Topology":[71],"Collaborative":[72],"Parsing":[73],"Framework":[74],"proposed.":[76],"This":[77,125,171],"framework":[78,139],"achieves":[79],"robust":[80,198],"parsing":[82],"through":[83,150,189],"dual":[84],"technical":[85],"approaches.":[86],"First,":[87],"deformable":[88],"kernels":[89],"are":[90],"used":[91],"correct":[93],"geometrically":[94],"warped":[95],"text":[96,131,191],"features,":[97],"with":[98,208],"channel":[99],"attention":[100],"mechanisms":[101,109],"integrated":[102],"for":[103,177,197],"noise":[105],"suppression.":[106],"Second,":[107],"cross-attention":[108],"XY-Cut":[112],"algorithm":[113],"work":[114,172],"collaboratively":[115],"construct":[117],"reading":[118,194],"orders":[119],"adapted":[120],"topological":[123],"structures.":[124],"co-design":[126],"ensures":[127],"simultaneous":[128],"optimization":[129,152],"enhancement":[133],"reading-order":[135],"construction.":[136],"Findings":[137],"demonstrates":[140],"superior":[141],"performance":[142],"in":[143],"classification":[145],"information":[148],"synergistic":[151],"correction":[155],"relationship":[158],"decoding,":[159],"significantly":[160],"reducing":[161],"reliance":[162],"on":[163],"error-prone":[164],"optical":[165],"character":[166],"recognition":[167],"(OCR)":[168],"preprocessing.":[169],"Originality/value":[170],"establishes":[173],"a":[174],"novel":[175],"paradigm":[176],"joint":[178],"spatial-semantic":[179],"understanding":[181],"via":[182],"three":[183],"key":[184],"advancements:":[185],"adaptive":[186],"rectification":[188],"deformable-convolutional":[190],"localization;":[192],"density-aware":[193],"sequence":[195],"generation":[196],"layout":[199],"parsing;":[200],"unified":[202],"representation":[203],"learning":[204],"bridging":[205],"visual":[206],"features":[207],"without":[211],"intermediate":[212],"OCR":[213],"dependencies.":[214]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-12-08T00:00:00"}