{"id":"https://openalex.org/W3093218477","doi":"https://doi.org/10.1145/3394171.3413900","title":"TRIE: End-to-End Text Reading and Information Extraction for Document Understanding","display_name":"TRIE: End-to-End Text Reading and Information Extraction for Document Understanding","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3093218477","doi":"https://doi.org/10.1145/3394171.3413900","mag":"3093218477"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413900","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th 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/A5100364260","display_name":"Peng Zhang","orcid":"https://orcid.org/0000-0003-4955-9123"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011474118","display_name":"Yunlu Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunlu Xu","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011185036","display_name":"Zhanzhan Cheng","orcid":"https://orcid.org/0000-0002-5732-1513"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanzhan Cheng","raw_affiliation_strings":["Zhejiang University & Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University & Hikvision Research Institute, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085955762","display_name":"Shiliang Pu","orcid":"https://orcid.org/0000-0001-5269-7821"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiliang Pu","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101810007","display_name":"Jing Lu","orcid":"https://orcid.org/0000-0001-7922-9921"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Lu","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026297587","display_name":"Qiao Liang","orcid":"https://orcid.org/0000-0003-4464-4644"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Qiao","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101448949","display_name":"Yi Niu","orcid":"https://orcid.org/0000-0002-7359-276X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Niu","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004882141","display_name":"Fei Wu","orcid":"https://orcid.org/0000-0003-2139-8807"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100364260"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.3274,"has_fulltext":false,"cited_by_count":110,"citation_normalized_percentile":{"value":0.97924649,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1413","last_page":"1422"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9941999912261963,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9934999942779541,"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":0.8526818156242371},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.7124267816543579},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6738377809524536},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6590919494628906},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5774515867233276},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5699564218521118},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5359120965003967},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5254884362220764},{"id":"https://openalex.org/keywords/plain-text","display_name":"Plain text","score":0.49779534339904785},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.47028636932373047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4575352966785431},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0920037031173706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8526818156242371},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.7124267816543579},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6738377809524536},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6590919494628906},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5774515867233276},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5699564218521118},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5359120965003967},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5254884362220764},{"id":"https://openalex.org/C46503548","wikidata":"https://www.wikidata.org/wiki/Q1145976","display_name":"Plain text","level":3,"score":0.49779534339904785},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.47028636932373047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4575352966785431},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0920037031173706},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C148730421","wikidata":"https://www.wikidata.org/wiki/Q141090","display_name":"Encryption","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3413900","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8899999856948853,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1493793991","https://openalex.org/W1791544012","https://openalex.org/W2008830554","https://openalex.org/W2033599040","https://openalex.org/W2064675550","https://openalex.org/W2078777599","https://openalex.org/W2153752143","https://openalex.org/W2162340487","https://openalex.org/W2164949130","https://openalex.org/W2170240176","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2296283641","https://openalex.org/W2550687635","https://openalex.org/W2565639579","https://openalex.org/W2605076167","https://openalex.org/W2745461083","https://openalex.org/W2748159032","https://openalex.org/W2750938222","https://openalex.org/W2777652944","https://openalex.org/W2794506130","https://openalex.org/W2809273748","https://openalex.org/W2857028992","https://openalex.org/W2875814315","https://openalex.org/W2891117443","https://openalex.org/W2896457183","https://openalex.org/W2922714365","https://openalex.org/W2949847953","https://openalex.org/W2950923448","https://openalex.org/W2951285986","https://openalex.org/W2951692098","https://openalex.org/W2952439627","https://openalex.org/W2953106684","https://openalex.org/W2962773189","https://openalex.org/W2962902328","https://openalex.org/W2963150697","https://openalex.org/W2963383024","https://openalex.org/W2963647456","https://openalex.org/W2963954913","https://openalex.org/W2963977642","https://openalex.org/W2964018263","https://openalex.org/W2964110616","https://openalex.org/W2964296749","https://openalex.org/W2968124245","https://openalex.org/W2970597249","https://openalex.org/W2970608575","https://openalex.org/W2970971581","https://openalex.org/W2972985407","https://openalex.org/W2973706664","https://openalex.org/W2988098900","https://openalex.org/W2996711979","https://openalex.org/W2997371611","https://openalex.org/W3003261556","https://openalex.org/W3005922567","https://openalex.org/W3034864438","https://openalex.org/W3104953317","https://openalex.org/W3122604748","https://openalex.org/W3163650427"],"related_works":["https://openalex.org/W2020521331","https://openalex.org/W101162712","https://openalex.org/W4256618828","https://openalex.org/W2786691313","https://openalex.org/W1990527953","https://openalex.org/W2030910246","https://openalex.org/W4287775364","https://openalex.org/W36911888","https://openalex.org/W13099415","https://openalex.org/W3029858749"],"abstract_inverted_index":{"Since":[0],"real-world":[1,132],"ubiquitous":[2],"documents":[3],"(e.g.,":[4],"invoices,":[5],"tickets,":[6],"resumes":[7],"and":[8,37,42,48,72,88,104,115,161],"leaflets)":[9],"contain":[10],"rich":[11],"information,":[12],"automatic":[13],"document":[14,136],"image":[15],"understanding":[16],"has":[17],"become":[18],"a":[19,83],"hot":[20],"topic.":[21],"Most":[22],"existing":[23],"works":[24],"decouple":[25],"the":[26,67,93,101,118,125,155],"problem":[27],"into":[28],"two":[29,94],"separate":[30],"tasks,":[31],"(1)":[32],"text":[33,70,86,108,128,146],"reading":[34,71,87,109],"for":[35,46,112],"detecting":[36],"recognizing":[38],"texts":[39],"in":[40,116,120,158],"images":[41,137],"(2)":[43],"information":[44,62,73,89,113,121],"extraction":[45,63,74,90,114,122],"analyzing":[47],"extracting":[49],"key":[50],"elements":[51],"from":[52,144],"previously":[53],"extracted":[54],"plain":[55],"text.However,":[56],"they":[57],"mainly":[58],"focus":[59],"on":[60],"improving":[61],"task,":[64],"while":[65],"neglecting":[66],"fact":[68],"that":[69],"are":[75,110],"mutually":[76],"correlated.":[77],"In":[78],"this":[79],"paper,":[80],"we":[81],"propose":[82],"unified":[84],"end-to-end":[85],"network,":[91],"where":[92],"tasks":[95],"can":[96],"reinforce":[97],"each":[98],"other.":[99],"Specifically,":[100],"multimodal":[102],"visual":[103],"textual":[105],"features":[106],"of":[107,127],"fused":[111],"turn,":[117],"semantics":[119],"contribute":[123],"to":[124,141,147],"optimization":[126],"reading.":[129],"On":[130],"three":[131],"datasets":[133],"with":[134],"diverse":[135],"(from":[138],"fixed":[139],"layout":[140],"variable":[142],"layout,":[143],"structured":[145],"semi-structured":[148],"text),":[149],"our":[150],"proposed":[151],"method":[152],"significantly":[153],"outperforms":[154],"state-of-the-art":[156],"methods":[157],"both":[159],"efficiency":[160],"accuracy.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":27},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}