{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T02:36:45Z","timestamp":1789094205008,"version":"build-2803163510"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2015,4,1]],"date-time":"2015-04-01T00:00:00Z","timestamp":1427846400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2015,4,1]],"date-time":"2015-04-01T00:00:00Z","timestamp":1427846400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2015,4,1]],"date-time":"2015-04-01T00:00:00Z","timestamp":1427846400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2015,4]]},"DOI":"10.1109\/tc.2014.2308181","type":"journal-article","created":{"date-parts":[[2014,2,25]],"date-time":"2014-02-25T19:01:15Z","timestamp":1393354875000},"page":"1162-1176","source":"Crossref","is-referenced-by-count":52,"title":["Similarity and Locality Based Indexing for High Performance Data Deduplication"],"prefix":"10.1109","volume":"64","author":[{"given":"Wen","family":"Xia","sequence":"first","affiliation":[{"name":"Wuhan National Laboratory for Optoelectronics, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of Nebraska-Lincoln, 217 Schorr Center, 1101 T Street, Lincoln"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Feng","sequence":"additional","affiliation":[{"name":"Wuhan National Laboratory for Optoelectronics, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Hua","sequence":"additional","affiliation":[{"name":"Wuhan National Laboratory for Optoelectronics, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref31","article-title":"iDedup: Latency-Aware, Inline Data Deduplication for Primary Storage","author":"bisson","year":"2012","journal-title":"Proc 10th USENIX Conf File and Storage Technologies"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/NAS.2012.46"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOT.2009.5366623"},{"key":"ref11","article-title":"Chunkstash: Speeding Up Inline Storage Deduplication Using Flash Memory","author":"debnath","year":"2010","journal-title":"Proc 2010 USENIX Conf USENIX Ann Technical Conf"},{"key":"ref12","article-title":"Tradeoffs in Scalable Data Routing for Deduplication Clusters","author":"dong","year":"2011","journal-title":"Proc Ninth USENIX Conf File and Storage Technologies"},{"key":"ref13","article-title":"Bimodal Content Defined Chunking for Backup Streams","author":"kruus","year":"2010","journal-title":"Proc Eighth USENIX Conf File and Storage Technologies"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1288783.1288788"},{"key":"ref15","article-title":"Characteristics of Backup Workloads in Production Systems","author":"wallace","year":"2012","journal-title":"Proc 10th USENIX Conf File and Storage Technologies"},{"key":"ref16","article-title":"On the Resemblance and Containment of Documents","author":"broder","year":"1997","journal-title":"Proc Compression and Complexity of Sequences"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1281192.1281207"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2010.69"},{"key":"ref19","year":"0"},{"key":"ref28","article-title":"Cumulus: Filesystem Backup to the Cloud","author":"michael","year":"2009","journal-title":"Proc Seventh USENIX Conf File and Storage Technologies"},{"key":"ref4","article-title":"Avoiding the Disk Bottleneck in the Data Domain Deduplication File System","author":"zhu","year":"2008","journal-title":"Proc Sixth USENIX Conf File and Storage Technologies"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1534530.1534539"},{"key":"ref3","article-title":"Alternatives for Detecting Redundancy in Storage Systems Data","author":"policroniades","year":"2004","journal-title":"Proc Ann Conf USENIX Ann Technical Conf"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2010.5496987"},{"key":"ref29","article-title":"Shredder: GPU-Accelerated Incremental Storage and Computation","author":"bhatotia","year":"2012","journal-title":"Proc 10th USENIX Conf File and Storage Technologies"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1534530.1534540"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/502034.502052"},{"key":"ref7","article-title":"A Study of Practical Deduplication","author":"meyer","year":"2011","journal-title":"Proc Ninth USENIX Conf File and Storage Technologies"},{"key":"ref2","first-page":"59","article-title":"Redundancy Elimination within Large Collections of Files","author":"kulkarni","year":"2004","journal-title":"Proc USENIX Ann Technical Conf"},{"key":"ref9","first-page":"111","article-title":"Sparse Indexing: Large Scale, Inline Deduplication Using Sampling and Locality","author":"lillibridge","year":"2009","journal-title":"Proc Seventh Conf File and Storage Technologies"},{"key":"ref1","article-title":"Venti: A New Approach to Archival Storage","author":"quinlan","year":"2002","journal-title":"Proc First USENIX Conf File and Storage Technologies"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/P2P.2010.5570004"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalgor.2003.12.002"},{"key":"ref21","article-title":"Building a High-Performance Deduplication System","author":"guo","year":"2011","journal-title":"Proc 2011 Conf USENIX Ann Technical Conf"},{"key":"ref24","author":"eshghi","year":"2005","journal-title":"A framework for analyzing and improving content-based chunking algorithms"},{"key":"ref23","author":"broder","year":"1993","journal-title":"Sequences II Methods in Comm Security and Computer Science"},{"key":"ref26","first-page":"1","article-title":"Finding Similar Files in a Large File System","author":"manber","year":"1994","journal-title":"Proc USENIX Winter Technical Conf"},{"key":"ref25","first-page":"197","article-title":"HYDRAstor: A Scalable Secondary Storage","author":"dubnicki","year":"2009","journal-title":"Proc Seventh Conf File and Storage Technologies"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/12\/7056411\/06747963.pdf?arnumber=6747963","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,18]],"date-time":"2022-06-18T02:29:23Z","timestamp":1655519363000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6747963\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,4]]},"references-count":31,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tc.2014.2308181","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"value":"0018-9340","type":"print"},{"value":"1557-9956","type":"electronic"},{"value":"2326-3814","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,4]]}}}