{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T21:08:02Z","timestamp":1787951282135,"version":"build-2784847793"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"ARC Discovery","award":["DP 180100966"],"award-info":[{"award-number":["DP 180100966"]}]},{"name":"Fudan University Startup Research","award":["SXH2301005"],"award-info":[{"award-number":["SXH2301005"]}]},{"name":"Shanghai Municipal Science & Technology Commission","award":["16JC1420401"],"award-info":[{"award-number":["16JC1420401"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2019,12,1]]},"DOI":"10.1109\/tkde.2018.2876250","type":"journal-article","created":{"date-parts":[[2018,10,16]],"date-time":"2018-10-16T18:52:26Z","timestamp":1539715946000},"page":"2332-2345","source":"Crossref","is-referenced-by-count":16,"title":["Improved Consistent Weighted Sampling Revisited"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0975-4613","authenticated-orcid":false,"given":"Wei","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9633-0033","authenticated-orcid":false,"given":"Bin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ling","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5715-7154","authenticated-orcid":false,"given":"Chengqi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philip S.","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.14778\/2140436.2140440"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2638838"},{"key":"ref33","article-title":"Efficient near-duplicate detection and sub-image retrieval","volume":"4","author":"ke","year":"2004","journal-title":"Proc Int Conf Multimedia"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1401921"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553462"},{"key":"ref30","first-page":"1498","article-title":"Simple and efficient weighted minwise hashing","author":"shrivastava","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2014.2373385"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874004"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-31753-3_17"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502152"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/1526709.1526769"},{"key":"ref62","first-page":"873","article-title":"Conditional random sampling: A sketch-based sampling technique for sparse data","author":"li","year":"2006","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2013.119"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1162\/coli.2007.33.3.305"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783406"},{"key":"ref64","first-page":"732","article-title":"Improved densification of one permutation hashing","author":"shrivastava","year":"2014","journal-title":"Proc Conf Uncertainty of Artificial Intelligence"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052598"},{"key":"ref65","first-page":"1387","article-title":"b-Bit minwise hashing for estimating three-way similarities","author":"li","year":"2010","journal-title":"Proc 23rd Int Conf Neural Inf Process Syst"},{"key":"ref66","first-page":"1","article-title":"b-Bit minwise hashing for large-scale learning","author":"li","year":"0","journal-title":"Big Learning 2011 NIPS 2011 Workshop on Algorithms Systems and Tools for Learning at Scale"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0174"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.5244\/C.22.50"},{"key":"ref2","author":"goode","year":"2016","journal-title":"Messenger and WhatsApp Process 60 Billion Messages a Day three Times More than SMS"},{"key":"ref1","author":"sullivan","year":"2016","journal-title":"Google Now Handles at Least 2 Trillion Searches per Year"},{"key":"ref20","first-page":"129","article-title":"Scalable techniques for clustering the web","author":"haveliwala","year":"2000","journal-title":"Proc 3rd Int l Workshop Web and Databases"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2016.30"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140446"},{"key":"ref24","article-title":"Consistent weighted sampling made fast, small, and easy","author":"haeupler","year":"2014"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1183614.1183683"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.80"},{"key":"ref25","article-title":"Consistent weighted sampling","author":"manasse","year":"0"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.121"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.193"},{"key":"ref59","first-page":"2672","article-title":"Hashing algorithms for large-scale learning","author":"li","year":"2011","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2010.140"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973440.12"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/1326561.1326564"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/1341531.1341560"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148222"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/775152.775246"},{"key":"ref52","first-page":"21","article-title":"On the resemblance and containment of documents","author":"broder","year":"1997","journal-title":"Proc Compression Complexity Sequences"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/997817.997857"},{"key":"ref11","first-page":"886","article-title":"In defense of minhash over SimHash","author":"shrivastava","year":"2014","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref40","first-page":"1926","article-title":"On symmetric and asymmetric LSHs for inner product search","author":"neyshabur","year":"2015","journal-title":"Proc Int Conf Int Conf Mach Learn"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557049"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/397"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2782278"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557137"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772759"},{"key":"ref17","first-page":"3113","article-title":"One permutation hashing","author":"li","year":"2012","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2566486.2568017"},{"key":"ref19","first-page":"557","article-title":"Densifying one permutation hashing via rotation for fast near neighbor search","author":"shrivastava","year":"2014","journal-title":"Proc 31st Int Conf Int Conf Mach Learn"},{"key":"ref4","volume":"1","author":"rajaraman","year":"2012","journal-title":"Mining of Massive Datasets"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1089\/big.2013.0016"},{"key":"ref6","first-page":"518","article-title":"Similarity search in high dimensions via hashing","volume":"99","author":"gionis","year":"1999","journal-title":"Proc 5th Int Conf Very Large Data Bases"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/276698.276876"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/509961.509965"},{"key":"ref7","first-page":"327","article-title":"Min-wise independent permutations","author":"broder","year":"1998","journal-title":"Proc 13th Annu ACM Symp Theory Comput"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/2348283.2348294"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242592"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459466"},{"key":"ref45","first-page":"108","article-title":"Super-bit locality-sensitive hashing","author":"ji","year":"2012","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2193120"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.219"},{"key":"ref42","first-page":"943","article-title":"No free lunch: Brute force vs. locality-sensitive hashing for cross-lingual pairwise similarity","author":"ture","year":"2011","journal-title":"Proc Int ACM SIGIR Conf Res Develop Inf Retrieval"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/1219840.1219917"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2020408.2020578"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2006.49"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/8893432\/08493289.pdf?arnumber=8493289","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:09:19Z","timestamp":1657746559000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8493289\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12,1]]},"references-count":67,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2018.2876250","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,12,1]]}}}