{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T23:58:49Z","timestamp":1729641529279,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009,11]]},"DOI":"10.1109\/icdim.2009.5356801","type":"proceedings-article","created":{"date-parts":[[2009,12,24]],"date-time":"2009-12-24T18:27:01Z","timestamp":1261679221000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["Effectively and efficiently detect web page duplication"],"prefix":"10.1109","author":[{"given":"Zhongming","family":"Han","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Mo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongzhi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianzhi","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"publisher","DOI":"10.1145\/331983.331992"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1145\/1062745.1062838"},{"key":"18","article-title":"Research on methods for extracting text information from HTML","volume":"4","author":"zhongming","year":"2008","journal-title":"Journal of Application Research of Computers"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1145\/775107.775134"},{"key":"16","article-title":"Learning to classify text using positive and unlabeled data","author":"li","year":"2003","journal-title":"Proc of IJCAI 2003"},{"key":"13","article-title":"Ipeirotis automatic extraction of useful facet hierarchies from text databases","author":"wisam","year":"2008","journal-title":"ICDE"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1016\/j.datak.2008.04.003"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1016\/S1389-1286(99)00021-3"},{"key":"12","first-page":"204","article-title":"Finding near-replicas of document s on the Web [C]","author":"shivakumar","year":"1998","journal-title":"Proc Workshop on Web and Databases"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1109\/LAWEB.2003.1250280"},{"key":"3","first-page":"284","article-title":"Finding near-duplicate Web pages: A large scale evaluation of algorithms[C]","author":"geram","year":"2006","journal-title":"Annual ACM Conference on Research and Development in Information Retrieval"},{"key":"20","article-title":"Finding similar files in a large file system[C]","volume":"2","author":"manber","year":"1994","journal-title":"Usenix Winter 1994 Technical Conference"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-47887-6_29"},{"key":"1","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1117\/12.270062","article-title":"Duplicate document detection","author":"lawrence spitz","year":"1997","journal-title":"The Proceedings of the SPIE-International Society for Optical Engineering Document Recognition IV"},{"key":"10","first-page":"179","article-title":"Two effective functions on hashing URL [J]","volume":"15","author":"li","year":"2004","journal-title":"Journal of Software"},{"journal-title":"The Smart \/Empire TIPSTER IR System TIPSTER Phase III Proceedings","year":"2000","author":"buckley","key":"7"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1108\/eb047198"},{"key":"5","article-title":"SCAM: A copy detection mechanism for digital documents","author":"narayanan","year":"1995","journal-title":"Proceedings of 2nd International Conference in Theory and Practice of Digital Libraries (DL'95)"},{"key":"4","first-page":"511","article-title":"Web document duplicate removal algorithm based on keyword sequences [C]","author":"li","year":"2005","journal-title":"Proc Natural Language Processing and Knowledge Engineering"},{"key":"9","first-page":"226","article-title":"Dynamic management of URL based on object2oriented paradigmf C]","author":"nam","year":"1998","journal-title":"Proc Int l Conf Parallel and Distributed Systems"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1145\/335191.335429"}],"event":{"name":"2009 Fourth International Conference on Digital Information Management (ICDIM)","start":{"date-parts":[[2009,11,1]]},"location":"Ann Arbor, MI, USA","end":{"date-parts":[[2009,11,4]]}},"container-title":["2009 Fourth International Conference on Digital Information Management"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5351158\/5356756\/05356801.pdf?arnumber=5356801","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,19]],"date-time":"2017-06-19T03:13:05Z","timestamp":1497841985000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5356801\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,11]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icdim.2009.5356801","relation":{},"subject":[],"published":{"date-parts":[[2009,11]]}}}