{"id":"https://openalex.org/W4304080492","doi":"https://doi.org/10.1145/3503161.3547885","title":"End-to-End Compound Table Understanding with Multi-Modal Modeling","display_name":"End-to-End Compound Table Understanding with Multi-Modal Modeling","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304080492","doi":"https://doi.org/10.1145/3503161.3547885"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3547885","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547885","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/A5034730393","display_name":"Zaisheng Li","orcid":"https://orcid.org/0000-0001-8052-0708"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zaisheng Li","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/A5100421687","display_name":"Yi Li","orcid":"https://orcid.org/0000-0003-0152-6605"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Li","raw_affiliation_strings":["ShanghaiTech University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026297587","display_name":"Qiao Liang","orcid":"https://orcid.org/0000-0003-4464-4644"},"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":"Qiao Liang","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/A5100339791","display_name":"Pengfei Li","orcid":"https://orcid.org/0009-0009-4234-1579"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengfei Li","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhanzhan Cheng","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/A5007634402","display_name":"Yi Niu","orcid":"https://orcid.org/0000-0003-1838-5714"},"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":"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":"last","author":{"id":"https://openalex.org/A5100407758","display_name":"Xi Li","orcid":"https://orcid.org/0000-0003-3023-1662"},"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":"Xi Li","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/A5034730393"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4195,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.7062598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4112","last_page":"4121"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9973999857902527,"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":0.9973999857902527,"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":0.9907000064849854,"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":0.9799000024795532,"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/table","display_name":"Table (database)","score":0.8357595205307007},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8304256200790405},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6445135474205017},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5344589948654175},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5271774530410767},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.503903329372406},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4335481524467468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42334744334220886},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3275521397590637}],"concepts":[{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.8357595205307007},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8304256200790405},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6445135474205017},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5344589948654175},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5271774530410767},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.503903329372406},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4335481524467468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42334744334220886},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3275521397590637},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3547885","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547885","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":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2001642682","https://openalex.org/W2021167849","https://openalex.org/W2051265407","https://openalex.org/W2116716943","https://openalex.org/W2138556038","https://openalex.org/W2150673968","https://openalex.org/W2154764394","https://openalex.org/W2290320465","https://openalex.org/W2342096063","https://openalex.org/W2483402000","https://openalex.org/W2604225376","https://openalex.org/W2786162033","https://openalex.org/W2810376801","https://openalex.org/W2963091658","https://openalex.org/W3003206728","https://openalex.org/W3003496674","https://openalex.org/W3003760744","https://openalex.org/W3034556525","https://openalex.org/W3034997246","https://openalex.org/W3061754956","https://openalex.org/W3088604029","https://openalex.org/W3093787307","https://openalex.org/W3098495697","https://openalex.org/W3101082165","https://openalex.org/W3107064625","https://openalex.org/W3109870706","https://openalex.org/W3118722740","https://openalex.org/W3165753548","https://openalex.org/W3167404434","https://openalex.org/W3168052339","https://openalex.org/W3173486678","https://openalex.org/W3180751782","https://openalex.org/W3207083256","https://openalex.org/W4214693170"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"Table":[0],"is":[1,105,151],"a":[2,73,98,123,147,163,181],"widely":[3],"used":[4,27],"data":[5],"form":[6,127],"in":[7,143],"webpages,":[8],"spreadsheets,":[9],"or":[10],"PDFs":[11],"to":[12,28,57,132,153],"organize":[13],"and":[14,86,109,159,174,201],"present":[15],"structural":[16,34],"data.":[17],"Although":[18],"studies":[19],"on":[20,42,63,117,138],"table":[21,58,84,140,171,177,190],"structure":[22],"recognition":[23,85,172],"have":[24],"been":[25],"successfully":[26],"convert":[29],"image-based":[30],"tables":[31],"into":[32],"digital":[33],"formats,":[35],"solving":[36],"many":[37],"real":[38],"problems":[39],"still":[40],"relies":[41],"further":[43],"understanding":[44,59,87,141,178,191],"of":[45,101,196],"the":[46,64,93,118,129,135,139,155,170,175,194],"table,":[47],"such":[48],"as":[49,180],"cell":[50],"relationship":[51],"extraction.":[52],"The":[53],"current":[54],"datasets":[55,91],"related":[56],"are":[60,203],"all":[61],"based":[62],"digit":[65],"format.":[66],"To":[67],"boost":[68],"research":[69],"development,":[70],"we":[71,120],"release":[72],"new":[74],"benchmark":[75],"named":[76,149],"ComFinTab":[77,96],"with":[78,128,162,186],"rich":[79],"annotations":[80],"that":[81],"support":[82],"both":[83],"tasks.":[88],"Unlike":[89],"previous":[90,188],"containing":[92],"basic":[94],"tables,":[95,103],"contains":[97],"large":[99],"ratio":[100],"compound":[102,144],"which":[104,167],"much":[106],"more":[107],"challenging":[108,176],"requires":[110],"methods":[111,192],"using":[112],"multiple":[113],"information":[114],"sources.":[115],"Based":[116],"dataset,":[119],"also":[121],"propose":[122],"uniform,":[124],"concise":[125],"task":[126,142,173,179],"evaluation":[130],"metric":[131],"better":[133],"evaluate":[134],"model's":[136],"performance":[137],"tables.":[145],"Finally,":[146],"framework":[148],"CTUNet":[150],"proposed":[152,198],"integrate":[154],"compromised":[156],"visual,":[157],"semantic,":[158],"position":[160],"features":[161],"graph":[164],"attention":[165],"network,":[166],"can":[168],"solve":[169],"whole.":[182],"Experimental":[183],"results":[184],"compared":[185],"some":[187],"advanced":[189],"demonstrate":[193],"effectiveness":[195],"our":[197],"model.":[199],"Code":[200],"dataset":[202],"available":[204],"at":[205],"\\urlhttps://github.com/hikopensource/DAVAR-Lab-OCR.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}