{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T13:55:09Z","timestamp":1766066109550,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2011,6,13]],"date-time":"2011-06-13T00:00:00Z","timestamp":1307923200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2011,6,13]]},"DOI":"10.1145\/1998076.1998079","type":"proceedings-article","created":{"date-parts":[[2011,6,28]],"date-time":"2011-06-28T17:34:50Z","timestamp":1309282490000},"page":"11-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":21,"title":["Structure extraction from PDF-based book documents"],"prefix":"10.1145","author":[{"given":"Liangcai","family":"Gao","sequence":"first","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi","family":"Tang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofan","family":"Lin","sequence":"additional","affiliation":[{"name":"Vobile Inc., Santa Clara, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Liu","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology, Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiheng","family":"Qiu","sequence":"additional","affiliation":[{"name":"Peking University Founder Group Co.,Ltd., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongtao","family":"Wang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2011,6,13]]},"reference":[{"issue":"5","key":"e_1_3_2_1_1_1","first-page":"1","volume":"5","author":"Aiello M.","year":"2002","unstructured":"Aiello , M. , Monz , C. , Todoran , L. and Worring M. Document Understanding for a Broad Class of Documents. International Journal on Document Analysis and Recognition , 5 ( 5 ): 1 -- 16 , 2002 . Aiello, M., Monz, C., Todoran, L. and Worring M. Document Understanding for a Broad Class of Documents. International Journal on Document Analysis and Recognition, 5(5):1--16, 2002.","journal-title":"Broad Class of Documents. International Journal on Document Analysis and Recognition"},{"issue":"2","key":"e_1_3_2_1_2_1","first-page":"175","volume":"3","author":"Altamura O.","year":"2001","unstructured":"Altamura , O. , Esposito , F. and Malerba , D. Transforming Paper Documents into XML Format with WISDOM+. International Journal of Document Analysis and Recognition , 3 ( 2 ): 175 -- 198 , 2001 . Altamura, O., Esposito, F. and Malerba, D. Transforming Paper Documents into XML Format with WISDOM+. International Journal of Document Analysis and Recognition, 3(2):175--198, 2001.","journal-title":"International Journal of Document Analysis and Recognition"},{"key":"e_1_3_2_1_3_1","first-page":"374","volume-title":"A. AIDAS: Incremental Logical Structure Discovery in PDF Documents. In Proc. of the 6th International Conference on Document Analysis and Recognition, ICDAR'01","author":"Anjewierden","year":"2001","unstructured":"Anjewierden , A. AIDAS: Incremental Logical Structure Discovery in PDF Documents. In Proc. of the 6th International Conference on Document Analysis and Recognition, ICDAR'01 , pages 374 -- 378 , Seattle, USA , September 2001 . Anjewierden, A. AIDAS: Incremental Logical Structure Discovery in PDF Documents. In Proc. of the 6th International Conference on Document Analysis and Recognition, ICDAR'01, pages 374--378, Seattle, USA, September 2001."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1815330.1815353"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAS.2008.44"},{"key":"e_1_3_2_1_6_1","volume-title":"T. B. Layout Analysis Based on Text Line Segment Hypotheses. In Proc. of the International Workshop on Document Layout Interpretation and Its Applications, DLIA'03","author":"Breuel","year":"2003","unstructured":"Breuel , T. B. Layout Analysis Based on Text Line Segment Hypotheses. In Proc. of the International Workshop on Document Layout Interpretation and Its Applications, DLIA'03 , Edinburgh, Scotland , August 2003 . Breuel, T. B. Layout Analysis Based on Text Line Segment Hypotheses. In Proc. of the International Workshop on Document Layout Interpretation and Its Applications, DLIA'03, Edinburgh, Scotland, August 2003."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1378889.1378959"},{"key":"e_1_3_2_1_8_1","volume-title":"Proc. of ECML\/PKDD-10 Tutorial and Workshop on Preference Learning","author":"Ceci M.","year":"2010","unstructured":"Ceci , M. , Appice , A. , Loglisci , C. and Malerba , D . Preference Learning for Document Image Analysis . In Proc. of ECML\/PKDD-10 Tutorial and Workshop on Preference Learning , Barcelona, Spain , September 2010 . Ceci, M., Appice, A., Loglisci, C. and Malerba, D. Preference Learning for Document Image Analysis. In Proc. of ECML\/PKDD-10 Tutorial and Workshop on Preference Learning, Barcelona, Spain, September 2010."},{"key":"e_1_3_2_1_9_1","volume-title":"Work & Legacy. Thames & Hudson","author":"Cees W. D.J.","year":"2008","unstructured":"Cees W. D.J. Jan Tschichold: Master Typographer: His Life , Work & Legacy. Thames & Hudson . Thames & Hudson Ltd ., NY., 2008 . Cees W. D.J. Jan Tschichold: Master Typographer: His Life, Work & Legacy. Thames & Hudson.Thames & Hudson Ltd., NY., 2008."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/WAINA.2008.125"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/11669487_12"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1555400.1555412"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAS.2008.30"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2009.143"},{"key":"e_1_3_2_1_15_1","volume-title":"PDF to HTML Conversion. Technical report","author":"Hassan T.","year":"2003","unstructured":"Hassan , T. PDF to HTML Conversion. Technical report , University of Warwick , 2003 . Hassan, T. PDF to HTML Conversion. Technical report, University of Warwick, 2003."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2009.238"},{"key":"e_1_3_2_1_17_1","first-page":"6","volume-title":"Proc. of the International Conference on Document Recognition and Retrieval XI","author":"He F.","year":"2004","unstructured":"He , F. , Ding , X. , and Peng , L . Hierarchical Logical Structure Extraction of Book Documents by Analyzing Tables of Contents . In Proc. of the International Conference on Document Recognition and Retrieval XI , pages 6 -- 13 , San Jose, USA , January 2004 . He, F., Ding, X., and Peng, L. Hierarchical Logical Structure Extraction of Book Documents by Analyzing Tables of Contents. In Proc. of the International Conference on Document Recognition and Retrieval XI, pages 6--13, San Jose, USA, January 2004."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/938979.939305"},{"key":"e_1_3_2_1_19_1","first-page":"99","volume-title":"Proc. of the 4th International Workshop on Document Analysis Systems, DAS'00","author":"Klink S.","year":"2000","unstructured":"Klink , S. , Dengel , A. and Kieninger , T . Document Structure Analysis Based on Layout and Textual Features . In Proc. of the 4th International Workshop on Document Analysis Systems, DAS'00 , pages 99 -- 111 , Rio de Janeiro, Brazil , June 2000 . Klink, S., Dengel, A. and Kieninger, T. Document Structure Analysis Based on Layout and Textual Features. In Proc. of the 4th International Workshop on Document Analysis Systems, DAS'00, pages 99--111, Rio de Janeiro, Brazil, June 2000."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2003.1232278"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/646270.685300"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.472833"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/1141753.1141835"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2005.182"},{"key":"e_1_3_2_1_25_1","first-page":"347","volume-title":"Proc. of the 7th International Conference on Pattern Recognition","author":"Nagy G.","year":"1984","unstructured":"Nagy , G. , and Seth , S . Hierarchical Representation of Optically Scanned Documents . In Proc. of the 7th International Conference on Pattern Recognition , pages 347 -- 349 , Montreal, Canada , 1984 . Nagy, G., and Seth, S. Hierarchical Representation of Optically Scanned Documents. In Proc. of the 7th International Conference on Pattern Recognition, pages 347--349, Montreal, Canada, 1984."},{"key":"e_1_3_2_1_26_1","volume-title":"Reengineering PDF-Based Documents Targeting Complex Software Specifications. Master's thesis","author":"Nojoumian M.","year":"2009","unstructured":"Nojoumian , M. and Lethbridge , T.C . Reengineering PDF-Based Documents Targeting Complex Software Specifications. Master's thesis , University of Waterloo , Canada , 2009 . Nojoumian, M. and Lethbridge, T.C. Reengineering PDF-Based Documents Targeting Complex Software Specifications. Master's thesis, University of Waterloo, Canada, 2009."},{"key":"e_1_3_2_1_27_1","volume-title":"Combinatorial Optimization: Algorithms and Complexity","author":"Papadimitriou C. H.","year":"1982","unstructured":"Papadimitriou , C. H. , and Steiglitz , K . Combinatorial Optimization: Algorithms and Complexity . Englewood Cliffs, NJ , 1982 . Papadimitriou, C. H., and Steiglitz, K. Combinatorial Optimization: Algorithms and Complexity. Englewood Cliffs, NJ, 1982."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2005.242"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/223904.223949"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/69.273022"},{"key":"e_1_3_2_1_31_1","volume-title":"Graph Theory and Its Algorithms","author":"Xiao W. S.","year":"1993","unstructured":"Xiao , W. S. Graph Theory and Its Algorithms . Aviation Industrial Press , Beijing , 1993 . Xiao, W. S. Graph Theory and Its Algorithms. Aviation Industrial Press, Beijing, 1993."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/312624.312647"}],"event":{"name":"JCDL '11: Joint Conference on Digital Libraries","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval","IEEE CS"],"location":"Ottawa Ontario Canada","acronym":"JCDL '11"},"container-title":["Proceedings of the 11th annual international ACM\/IEEE joint conference on Digital libraries"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1998076.1998079","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1998076.1998079","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T11:06:18Z","timestamp":1750244778000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1998076.1998079"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,6,13]]},"references-count":32,"alternative-id":["10.1145\/1998076.1998079","10.1145\/1998076"],"URL":"https:\/\/doi.org\/10.1145\/1998076.1998079","relation":{},"subject":[],"published":{"date-parts":[[2011,6,13]]},"assertion":[{"value":"2011-06-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}