{"id":"https://openalex.org/W4381198646","doi":"https://doi.org/10.1109/tcsvt.2023.3287296","title":"DCMAI: A Dynamical Cross-Modal Alignment Interaction Framework for Document Key Information Extraction","display_name":"DCMAI: A Dynamical Cross-Modal Alignment Interaction Framework for Document Key Information Extraction","publication_year":2023,"publication_date":"2023-06-19","ids":{"openalex":"https://openalex.org/W4381198646","doi":"https://doi.org/10.1109/tcsvt.2023.3287296"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3287296","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3287296","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","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/A5069570508","display_name":"Pengcheng Guo","orcid":"https://orcid.org/0000-0002-5939-007X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pengcheng Guo","raw_affiliation_strings":["Department of Software Engineering, Xi’an Jiaotong University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"Department of Software Engineering, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110814145","display_name":"Yonghong Song","orcid":"https://orcid.org/0000-0001-5978-3781"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Song","raw_affiliation_strings":["Department of Software Engineering, Xi’an Jiaotong University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"Department of Software Engineering, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025676641","display_name":"Yongbiao Deng","orcid":"https://orcid.org/0000-0002-4673-5606"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongbiao Deng","raw_affiliation_strings":["Department of Software Engineering, Xi’an Jiaotong University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"Department of Software Engineering, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100925506","display_name":"Kangkang Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kang-Kang Xie","raw_affiliation_strings":["Department of Software Engineering, Xi’an Jiaotong University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"Department of Software Engineering, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069307874","display_name":"Mingjie Xu","orcid":"https://orcid.org/0000-0002-4976-789X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjie Xu","raw_affiliation_strings":["Department of Software Engineering, Xi’an Jiaotong University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"Department of Software Engineering, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100347861","display_name":"Jiahao Liu","orcid":"https://orcid.org/0009-0006-0116-0024"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahao Liu","raw_affiliation_strings":["Department of Software Engineering, Xi’an Jiaotong University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"Department of Software Engineering, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034218462","display_name":"Haijun Ren","orcid":"https://orcid.org/0000-0002-8211-3820"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haijun Ren","raw_affiliation_strings":["Department of Software Engineering, Xi’an Jiaotong University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"Department of Software Engineering, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5069570508"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.8425,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.74748928,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"34","issue":"1","first_page":"504","last_page":"517"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9976000189781189,"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":0.9968000054359436,"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/computer-science","display_name":"Computer science","score":0.8035526275634766},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7842057347297668},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6633613109588623},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6583173274993896},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.49176934361457825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4156278371810913},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.41469860076904297},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3467780351638794},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3452734351158142},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3371589779853821},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3362959325313568}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8035526275634766},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7842057347297668},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6633613109588623},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6583173274993896},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.49176934361457825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4156278371810913},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.41469860076904297},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3467780351638794},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3452734351158142},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3371589779853821},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3362959325313568},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2023.3287296","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3287296","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G1984591968","display_name":null,"funder_award_id":"61973245","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1966382373","https://openalex.org/W2187089797","https://openalex.org/W2891117443","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2949861626","https://openalex.org/W2962772269","https://openalex.org/W2965373594","https://openalex.org/W2969876226","https://openalex.org/W2970231061","https://openalex.org/W2972985407","https://openalex.org/W2986619406","https://openalex.org/W2997154779","https://openalex.org/W3035524453","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3093218477","https://openalex.org/W3099103595","https://openalex.org/W3104953317","https://openalex.org/W3120043490","https://openalex.org/W3134875898","https://openalex.org/W3136792391","https://openalex.org/W3163650427","https://openalex.org/W3173325518","https://openalex.org/W3176664887","https://openalex.org/W3176851559","https://openalex.org/W3181159501","https://openalex.org/W3181286780","https://openalex.org/W3182680257","https://openalex.org/W3190448953","https://openalex.org/W3195903836","https://openalex.org/W3198984549","https://openalex.org/W3200439183","https://openalex.org/W3201693581","https://openalex.org/W3205981739","https://openalex.org/W4221167659","https://openalex.org/W4226020328","https://openalex.org/W4226391640","https://openalex.org/W4229042118","https://openalex.org/W4285220052","https://openalex.org/W4285221285","https://openalex.org/W4285600262","https://openalex.org/W4304013646","https://openalex.org/W4385245566","https://openalex.org/W4385570772","https://openalex.org/W4385570779","https://openalex.org/W4385574075","https://openalex.org/W6631190155","https://openalex.org/W6637242042","https://openalex.org/W6682948231","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6764124961","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6768033458","https://openalex.org/W6772827613","https://openalex.org/W6773829392","https://openalex.org/W6787566904","https://openalex.org/W6789753369","https://openalex.org/W6789909235","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6804223093","https://openalex.org/W6811072154","https://openalex.org/W6845518869"],"related_works":["https://openalex.org/W2353179089","https://openalex.org/W2923538289","https://openalex.org/W2353125546","https://openalex.org/W2470643824","https://openalex.org/W2349635380","https://openalex.org/W4353089801","https://openalex.org/W2353819554","https://openalex.org/W2359488321","https://openalex.org/W4386136067","https://openalex.org/W4286858940"],"abstract_inverted_index":{"Document":[0],"key":[1],"information":[2,119],"extraction":[3],"(DKIE)":[4],"is":[5,112,130,145,162],"a":[6,96,149,159],"crucial":[7],"topic":[8],"that":[9,172],"aims":[10],"at":[11],"automatically":[12],"comprehending":[13],"documents":[14],"with":[15],"complex":[16],"formats":[17],"and":[18,158],"layouts":[19],"(invoices,":[20],"business":[21],"insurance,":[22],"etc.).":[23],"While":[24],"pre-trained":[25],"approaches":[26,45],"have":[27],"shown":[28],"high":[29],"performance":[30,178],"on":[31,182],"many":[32],"DKIE":[33],"tasks,":[34],"they":[35,58],"suffer":[36],"from":[37,50,86],"three":[38],"major":[39],"challenges.":[40],"First":[41],"of":[42,154],"all,":[43],"these":[44,92],"ignore":[46],"the":[47,173,192],"ambiguity":[48],"resulting":[49],"similar":[51,122],"text":[52,123],"representations":[53,135],"before":[54,65,136],"cross-modal":[55,62,66,72,134,137,155],"interaction.":[56,67,138],"Secondly,":[57],"do":[59],"not":[60],"consider":[61],"representation":[63,84,167],"alignment":[64,128],"Finally,":[68],"self-attention":[69],"layers":[70],"in":[71],"interaction":[73,142],"incur":[74],"significant":[75],"computing":[76],"costs,":[77],"making":[78],"it":[79],"hard":[80],"to":[81,114,120,132,147,164,191],"perform":[82],"joint":[83,166],"learning":[85],"all":[87],"negative":[88,156],"samples.":[89],"To":[90,103],"address":[91],"issues,":[93],"we":[94],"propose":[95],"Dynamical":[97],"Cross-Modal":[98],"Alignment":[99],"Interaction":[100],"framework":[101],"(DCMAI).":[102],"be":[104,189],"more":[105],"specific,":[106],"1)":[107],"A":[108,126,140],"prior":[109],"knowledge-guided":[110],"module":[111],"designed":[113],"adaptively":[115],"mine":[116],"fine-grained":[117],"visual":[118],"disambiguate":[121],"representations.":[124],"2)":[125],"crossover":[127],"loss":[129,161],"formulated":[131],"align":[133],"3)":[139],"hierarchical":[141],"sampling":[143],"scheme":[144],"introduced":[146],"obtain":[148],"small":[150],"but":[151],"efficient":[152],"subset":[153],"samples,":[157],"contrastive":[160],"employed":[163],"improve":[165],"learning.":[168],"Comprehensive":[169],"experiments":[170],"show":[171],"proposed":[174],"DCMAI":[175],"achieves":[176],"state-of-the-art":[177],"than":[179],"competitive":[180],"baselines":[181],"several":[183],"public":[184],"downstream":[185],"benchmarks.":[186],"Code":[187],"will":[188],"open":[190],"public.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}