{"id":"https://openalex.org/W4414359547","doi":"https://doi.org/10.24963/ijcai.2025/574","title":"Structure-Aware Handwritten Text Recognition via Graph-Enhanced Cross-Modal Mutual Learning","display_name":"Structure-Aware Handwritten Text Recognition via Graph-Enhanced Cross-Modal Mutual Learning","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359547","doi":"https://doi.org/10.24963/ijcai.2025/574"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/574","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-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/A5004714275","display_name":"Ji Gan","orcid":"https://orcid.org/0000-0001-6041-588X"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ji Gan","raw_affiliation_strings":["Chongqing Institute for Brain and Intelligence, Guangyang Bay Laboratory","Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications","School of Computer Science and Technology, Chongqing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Chongqing Institute for Brain and Intelligence, Guangyang Bay Laboratory","institution_ids":[]},{"raw_affiliation_string":"Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I10535382"]},{"raw_affiliation_string":"School of Computer Science and Technology, Chongqing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006623562","display_name":"Yupeng Zhou","orcid":"https://orcid.org/0000-0002-9328-1328"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yupeng Zhou","raw_affiliation_strings":["Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications","School of Computer Science and Technology, Chongqing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I10535382"]},{"raw_affiliation_string":"School of Computer Science and Technology, Chongqing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019724982","display_name":"Yanming Zhang","orcid":"https://orcid.org/0000-0002-9134-3812"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanming Zhang","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061201566","display_name":"Jiaxu Leng","orcid":"https://orcid.org/0000-0003-2802-8139"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxu Leng","raw_affiliation_strings":["Chongqing Institute for Brain and Intelligence, Guangyang Bay Laboratory","Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications","School of Computer Science and Technology, Chongqing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Chongqing Institute for Brain and Intelligence, Guangyang Bay Laboratory","institution_ids":[]},{"raw_affiliation_string":"Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I10535382"]},{"raw_affiliation_string":"School of Computer Science and Technology, Chongqing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101785348","display_name":"Xinbo Gao","orcid":"https://orcid.org/0000-0003-1443-0776"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinbo Gao","raw_affiliation_strings":["Chongqing Institute for Brain and Intelligence, Guangyang Bay Laboratory","Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications","School of Computer Science and Technology, Chongqing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Chongqing Institute for Brain and Intelligence, Guangyang Bay Laboratory","institution_ids":[]},{"raw_affiliation_string":"Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I10535382"]},{"raw_affiliation_string":"School of Computer Science and Technology, Chongqing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I10535382"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5004714275"],"corresponding_institution_ids":["https://openalex.org/I10535382"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26689437,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5154","last_page":"5162"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9866999983787537,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9855999946594238,"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/mutual-information","display_name":"Mutual information","score":0.6898999810218811},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5803999900817871},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5644999742507935},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4941999912261963},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.486299991607666},{"id":"https://openalex.org/keywords/handwriting","display_name":"Handwriting","score":0.48080000281333923},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.43560001254081726},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.43380001187324524},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.41029998660087585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7382000088691711},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.6898999810218811},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6294000148773193},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5803999900817871},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5644999742507935},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4941999912261963},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.486299991607666},{"id":"https://openalex.org/C2779386606","wikidata":"https://www.wikidata.org/wiki/Q2393642","display_name":"Handwriting","level":2,"score":0.48080000281333923},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.43560001254081726},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.43380001187324524},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.41029998660087585},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35530000925064087},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C112640561","wikidata":"https://www.wikidata.org/wiki/Q2440634","display_name":"Handwriting recognition","level":3,"score":0.33820000290870667},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31949999928474426},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2955000102519989},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28540000319480896},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/574","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"handwriting":[1],"recognition":[2],"methods":[3,157],"only":[4,127],"focus":[5],"on":[6,158],"learning":[7,35],"visual":[8,66],"patterns":[9],"by":[10],"modeling":[11],"low-level":[12],"relationships":[13],"of":[14,23,51,86,130,140],"adjacent":[15],"pixels,":[16],"while":[17],"overlooking":[18],"the":[19,62,71,75,78,84,138,141],"intrinsic":[20],"geometric":[21,47,68],"structures":[22],"characters.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28],"propose":[29],"a":[30],"novel":[31],"graph-enhanced":[32],"cross-modal":[33,54,72,87,95,121],"mutual":[34,107],"network":[36],"GCM":[37,131],"to":[38],"fully":[39,118],"process":[40],"handwritten":[41],"text":[42],"images":[43],"alongside":[44],"their":[45],"corresponding":[46],"graphs,":[48],"which":[49,112],"consists":[50],"one":[52,128],"shared":[53],"encoder":[55,63],"and":[56,67,74,101,117,144,165],"two":[57,90],"parallel":[58,91],"inverse":[59,98],"decoders.":[60],"Specifically,":[61],"simultaneously":[64],"extracts":[65],"information":[69,122],"from":[70,123],"inputs,":[73],"decoders":[76,92],"fuse":[77],"multi-modal":[79],"features":[80,96],"for":[81,147],"prediction":[82],"under":[83],"guidance":[85],"fusion.":[88],"Moreover,":[89],"sequentially":[93],"aggregate":[94],"in":[97,134],"orders":[99],"(V\u2192G":[100],"G\u2192V)":[102],"but":[103],"are":[104],"enhanced":[105],"through":[106],"distillation":[108],"at":[109],"each":[110],"time-step,":[111],"involves":[113],"one-to-one":[114],"knowledge":[115],"transfer":[116],"leverages":[119],"complementary":[120],"both":[124],"directions.":[125],"Notably,":[126],"branch":[129],"is":[132,172],"activated":[133],"inference,":[135],"thus":[136],"avoiding":[137],"increase":[139],"model":[142],"parameters":[143],"computation":[145],"costs":[146],"testing.":[148],"Experiments":[149],"show":[150],"that":[151],"our":[152],"method":[153],"outperforms":[154],"previous":[155],"state-of-the-art":[156],"public":[159],"benchmarks":[160],"such":[161],"as":[162],"IAM,":[163],"RIMES,":[164],"ICDAR-2013":[166],"when":[167],"no":[168],"extra":[169],"training":[170],"data":[171],"utilized.":[173]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}