{"id":"https://openalex.org/W4304098606","doi":"https://doi.org/10.1145/3503161.3547877","title":"Query-driven Generative Network for Document Information Extraction in the Wild","display_name":"Query-driven Generative Network for Document Information Extraction in the Wild","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304098606","doi":"https://doi.org/10.1145/3503161.3547877"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3547877","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547877","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","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/A5068313625","display_name":"Haoyu Cao","orcid":"https://orcid.org/0000-0002-3789-9705"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoyu Cao","raw_affiliation_strings":["Tencent YouTu Lab, HeFei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, HeFei, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353721","display_name":"Xin Li","orcid":"https://orcid.org/0000-0001-6888-7064"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["Tencent YouTu Lab, HeFei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, HeFei, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006572116","display_name":"Jiefeng Ma","orcid":"https://orcid.org/0000-0003-2416-3720"},"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":"Jiefeng Ma","raw_affiliation_strings":["University of Science and Technology of China, HeFei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, HeFei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016912950","display_name":"Deqiang Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deqiang Jiang","raw_affiliation_strings":["Tencent YouTu Lab, HeFei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, HeFei, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063859253","display_name":"Antai Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Antai Guo","raw_affiliation_strings":["Tencent YouTu Lab, HeFei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, HeFei, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101541173","display_name":"Yiqing Hu","orcid":"https://orcid.org/0009-0000-0342-0834"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqing Hu","raw_affiliation_strings":["Tencent YouTu Lab, HeFei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, HeFei, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458818","display_name":"Hao Liu","orcid":"https://orcid.org/0000-0002-5248-935X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Liu","raw_affiliation_strings":["Tencent YouTu Lab, HeFei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, HeFei, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084063805","display_name":"Yinsong Liu","orcid":"https://orcid.org/0000-0002-0096-3662"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinsong Liu","raw_affiliation_strings":["Tencent YouTu Lab, HeFei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, HeFei, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073750509","display_name":"Bo Ren","orcid":"https://orcid.org/0000-0002-0619-7188"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Ren","raw_affiliation_strings":["Tencent YouTu Lab, HeFei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, HeFei, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5068313625"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":0.7157,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.79528677,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4261","last_page":"4271"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9912999868392944,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9908999800682068,"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":0.84371018409729},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7064683437347412},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5459141731262207},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45948538184165955},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.453773558139801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4227622449398041},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3939652740955353},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.34281685948371887}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.84371018409729},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7064683437347412},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5459141731262207},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45948538184165955},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.453773558139801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4227622449398041},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3939652740955353},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34281685948371887},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3547877","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547877","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":31,"referenced_works":["https://openalex.org/W251438302","https://openalex.org/W1963728304","https://openalex.org/W1966382373","https://openalex.org/W2078777599","https://openalex.org/W2144876877","https://openalex.org/W2194187530","https://openalex.org/W2560674852","https://openalex.org/W2741609678","https://openalex.org/W2951692098","https://openalex.org/W2965512000","https://openalex.org/W2981852735","https://openalex.org/W2986619406","https://openalex.org/W3003484198","https://openalex.org/W3034864438","https://openalex.org/W3092515419","https://openalex.org/W3092968218","https://openalex.org/W3104953317","https://openalex.org/W3132296545","https://openalex.org/W3171975879","https://openalex.org/W3173306993","https://openalex.org/W3173325518","https://openalex.org/W3173777717","https://openalex.org/W3176851559","https://openalex.org/W3190292546","https://openalex.org/W3190448953","https://openalex.org/W3198609383","https://openalex.org/W3202839357","https://openalex.org/W3205981739","https://openalex.org/W4248923238","https://openalex.org/W4287854430","https://openalex.org/W4288089799"],"related_works":["https://openalex.org/W2770593030","https://openalex.org/W4281727072","https://openalex.org/W4312219546","https://openalex.org/W3154990682","https://openalex.org/W2171975302","https://openalex.org/W1532073221","https://openalex.org/W2377538627","https://openalex.org/W2107220315","https://openalex.org/W2729046585","https://openalex.org/W2049632933"],"abstract_inverted_index":{"This":[0],"paper":[1],"focuses":[2],"on":[3,182,200],"solving":[4],"Document":[5],"Information":[6],"Extraction":[7],"(DIE)":[8],"in":[9,28,67],"the":[10,37,68,71,115,119,125,129,133,144,179,183,206,215],"wild":[11,216],"problem,":[12],"which":[13,89],"is":[14,90],"rarely":[15],"explored":[16],"before.":[17],"In":[18,170],"contrast":[19],"to":[20,46,131],"existing":[21],"studies":[22],"mainly":[23],"tailored":[24],"for":[25,54,128,214],"document":[26,59,108],"cases":[27],"known":[29],"templates":[30],"with":[31,92,110,138,163],"predefined":[32],"layouts":[33,64,112,165],"and":[34,65,101,113,166,198,208],"keys":[35,66],"under":[36],"ideal":[38],"input":[39,58],"without":[40],"OCR":[41,73,139],"errors":[42],"involved,":[43],"we":[44,79,149,172],"aim":[45],"build":[47],"up":[48],"a":[49,81,107,151],"more":[50,194],"practical":[51],"DIE":[52,217],"paradigm":[53],"real-world":[55],"scenarios":[56],"where":[57],"images":[60],"may":[61],"contain":[62],"unknown":[63],"scenes":[69],"of":[70,146,210],"problematic":[72],"results.":[74],"To":[75,141],"achieve":[76],"this":[77],"goal,":[78],"propose":[80],"novel":[82],"architecture,":[83],"termed":[84],"Query-driven":[85],"Generative":[86],"Network":[87],"(QGN),":[88],"equipped":[91],"two":[93],"consecutive":[94],"modules,":[95],"i.e.,":[96],"Layout":[97],"Context-aware":[98],"Module":[99,104],"(LCM)":[100],"Structured":[102],"Generation":[103],"(SGM).":[105],"Given":[106],"image":[109],"unseen":[111],"fields,":[114],"former":[116],"LCM":[117],"yields":[118],"value":[120],"prefix":[121],"candidates":[122],"serving":[123],"as":[124],"query":[126],"prompts":[127],"SGM":[130],"generate":[132],"final":[134],"key-value":[135],"pairs":[136],"even":[137],"noise.":[140],"further":[142],"investigate":[143],"potential":[145],"our":[147,175,211],"method,":[148],"create":[150],"new":[152,184],"large-scale":[153],"dataset,":[154],"named":[155],"LArge-scale":[156],"STructured":[157],"Documents":[158],"(LastDoc4000),":[159],"containing":[160],"4,000":[161],"documents":[162],"1,511":[164],"3,500":[167],"different":[168],"keys.":[169],"experiments,":[171],"demonstrate":[173],"that":[174],"QGN":[176],"consistently":[177],"achieves":[178],"best":[180],"F1-score":[181],"LastDoc4000":[185],"dataset":[186],"by":[187],"at":[188],"most":[189],"30.32%":[190],"absolute":[191],"improvement.":[192],"A":[193],"comprehensive":[195],"experimental":[196],"analysis":[197],"experiments":[199],"other":[201],"public":[202],"benchmarks":[203],"also":[204],"verify":[205],"effectiveness":[207],"robustness":[209],"proposed":[212],"method":[213],"task.":[218]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}