{"id":"https://openalex.org/W1984130280","doi":"https://doi.org/10.1145/1998076.1998079","title":"Structure extraction from PDF-based book documents","display_name":"Structure extraction from PDF-based book documents","publication_year":2011,"publication_date":"2011-06-13","ids":{"openalex":"https://openalex.org/W1984130280","doi":"https://doi.org/10.1145/1998076.1998079","mag":"1984130280"},"language":"en","primary_location":{"id":"doi:10.1145/1998076.1998079","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1998076.1998079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th annual international ACM/IEEE joint conference on Digital libraries","raw_type":"proceedings-article"},"type":"conference-paper","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/A5004474713","display_name":"Liangcai Gao","orcid":"https://orcid.org/0000-0001-9444-1568"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangcai Gao","raw_affiliation_strings":["Peking University, Beijing, China","Peking University, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103175239","display_name":"Zhi Tang","orcid":"https://orcid.org/0000-0002-6021-8357"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Tang","raw_affiliation_strings":["Peking University, Beijing, China","Peking University, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108543316","display_name":"Xiaofan Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaofan Lin","raw_affiliation_strings":["Vobile Inc., Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vobile Inc., Santa Clara, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101772017","display_name":"Ying Liu","orcid":"https://orcid.org/0000-0003-0214-6479"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ying Liu","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089276181","display_name":"Ruiheng Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiheng Qiu","raw_affiliation_strings":["Peking University Founder Group Co.,Ltd., Beijing, China","Peking University Founder Group Co. LTD., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University Founder Group Co.,Ltd., Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University Founder Group Co. LTD., Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100781631","display_name":"Yongtao Wang","orcid":"https://orcid.org/0000-0003-1379-2206"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongtao Wang","raw_affiliation_strings":["Peking University, Beijing, China","Peking University, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9991000294685364,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9991000294685364,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9976000189781189,"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":0.8529359698295593},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7125426530838013},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6178756356239319},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.5413126945495605},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.485347181558609},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.48026442527770996},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4785086214542389},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.46732842922210693},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.45341241359710693},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.4526902139186859},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4454510807991028},{"id":"https://openalex.org/keywords/bipartite-graph","display_name":"Bipartite graph","score":0.4374021887779236},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4159521460533142},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3518295884132385},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.26257842779159546},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.25458335876464844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24162691831588745},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.12041690945625305},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11365523934364319},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.10641810297966003}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8529359698295593},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7125426530838013},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6178756356239319},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.5413126945495605},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.485347181558609},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.48026442527770996},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4785086214542389},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.46732842922210693},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.45341241359710693},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.4526902139186859},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4454510807991028},{"id":"https://openalex.org/C197657726","wikidata":"https://www.wikidata.org/wiki/Q174733","display_name":"Bipartite graph","level":3,"score":0.4374021887779236},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4159521460533142},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3518295884132385},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.26257842779159546},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25458335876464844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24162691831588745},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.12041690945625305},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11365523934364319},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.10641810297966003},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1998076.1998079","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1998076.1998079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th annual international ACM/IEEE joint conference on Digital libraries","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"},{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W8079469","https://openalex.org/W44107710","https://openalex.org/W615575058","https://openalex.org/W1530730108","https://openalex.org/W1967011969","https://openalex.org/W1972467623","https://openalex.org/W1983284692","https://openalex.org/W1991334432","https://openalex.org/W1999053255","https://openalex.org/W2005422315","https://openalex.org/W2044900178","https://openalex.org/W2048135704","https://openalex.org/W2069323107","https://openalex.org/W2105413446","https://openalex.org/W2110412794","https://openalex.org/W2115927545","https://openalex.org/W2116771527","https://openalex.org/W2121496069","https://openalex.org/W2124991807","https://openalex.org/W2131043005","https://openalex.org/W2132006538","https://openalex.org/W2134524813","https://openalex.org/W2134590793","https://openalex.org/W2136783895","https://openalex.org/W2147800461","https://openalex.org/W2155395197","https://openalex.org/W2482935363","https://openalex.org/W3023264106","https://openalex.org/W3104729387","https://openalex.org/W7008583937"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W1964661231","https://openalex.org/W4254960163","https://openalex.org/W3110264473","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2370831213","https://openalex.org/W4315704968","https://openalex.org/W4285478380","https://openalex.org/W2100255360"],"abstract_inverted_index":{"Nowadays":[0],"PDF":[1,51,117],"documents":[2],"have":[3],"become":[4],"a":[5,63,140],"dominating":[6],"knowledge":[7],"repository":[8],"for":[9,57,143],"both":[10,81],"the":[11,26,40,46,50,55,69,108,127,136,160,163,172,184,191],"academia":[12],"and":[13,23,39,73,84,96,112,152,155,187],"industry":[14],"largely":[15],"because":[16],"they":[17],"are":[18,33,119],"very":[19],"convenient":[20],"to":[21,35,67,125,170],"print":[22],"exchange.":[24],"However,":[25],"methods":[27,44],"of":[28,42,49,101,116,190],"automated":[29],"structure":[30,72,130,142],"information":[31,47],"extraction":[32,131],"yet":[34],"be":[36],"fully":[37,120],"explored":[38],"lack":[41],"effective":[43],"hinders":[45],"reuse":[48],"documents.":[52],"To":[53],"enhance":[54],"usability":[56],"PDF-formatted":[58],"electronic":[59],"books,":[60,103],"we":[61],"propose":[62],"novel":[64],"computational":[65],"framework":[66],"analyze":[68],"underlying":[70],"physical":[71],"logical":[74,92],"structure.":[75],"The":[76],"analysis":[77],"is":[78,168],"conducted":[79],"at":[80],"page":[82],"level":[83],"document":[85,111],"level,":[86],"including":[87,147],"global":[88,173],"typographies,":[89],"reading":[90,148],"order,":[91],"elements,":[93],"chapter/section":[94],"hierarchy":[95],"metadata.":[97],"Moreover,":[98],"two":[99],"characteristics":[100],"PDF-based":[102],"i.e.,":[104],"style":[105],"consistency":[106],"in":[107,122,175],"whole":[109],"book":[110],"natural":[113],"rendering":[114],"order":[115,149],"files,":[118],"exploited":[121],"this":[123],"paper":[124,134],"improve":[126],"conventional":[128],"image-based":[129],"methods.":[132],"This":[133],"employs":[135],"bipartite":[137],"graph":[138,161],"as":[139],"common":[141],"modeling":[144],"various":[145],"tasks,":[146],"recovery,":[150],"figure":[151],"caption":[153],"association,":[154],"metadata":[156],"extraction.":[157],"Based":[158],"on":[159],"representation,":[162],"optimal":[164],"matching":[165],"(OM)":[166],"method":[167],"utilized":[169],"find":[171],"optima":[174],"those":[176],"tasks.":[177],"Extensive":[178],"benchmarking":[179],"using":[180],"real-world":[181],"data":[182],"validates":[183],"high":[185],"efficiency":[186],"discrimination":[188],"ability":[189],"proposed":[192],"method.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}