{"id":"https://openalex.org/W2031637148","doi":"https://doi.org/10.1145/2348283.2348339","title":"Learning hash codes for efficient content reuse detection","display_name":"Learning hash codes for efficient content reuse detection","publication_year":2012,"publication_date":"2012-08-12","ids":{"openalex":"https://openalex.org/W2031637148","doi":"https://doi.org/10.1145/2348283.2348339","mag":"2031637148"},"language":"en","primary_location":{"id":"doi:10.1145/2348283.2348339","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2348283.2348339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},"type":"article","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/A5014306843","display_name":"Qi Zhang","orcid":"https://orcid.org/0000-0002-5203-8778"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qi Zhang","raw_affiliation_strings":["Fudan University, Shanghai, China","Fudan University Shanghai, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Fudan University Shanghai, China#TAB#","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070702602","display_name":"Yan Wu","orcid":"https://orcid.org/0000-0002-8874-8886"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Wu","raw_affiliation_strings":["Fudan University, Shanghai, China","Fudan University Shanghai, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Fudan University Shanghai, China#TAB#","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008043408","display_name":"Zhuoye Ding","orcid":"https://orcid.org/0000-0001-7430-5980"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuoye Ding","raw_affiliation_strings":["Fudan University, Shanghai, China","Fudan University Shanghai, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Fudan University Shanghai, China#TAB#","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088834359","display_name":"Xuanjing Huang","orcid":"https://orcid.org/0000-0001-9197-9426"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanjing Huang","raw_affiliation_strings":["Fudan University, Shanghai, China","Fudan University Shanghai, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Fudan University Shanghai, China#TAB#","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014306843"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":3.2945,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.92997142,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"405","last_page":"414"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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/T11478","display_name":"Caching and Content Delivery","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9889000058174133,"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":0.8689249753952026},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.8449125289916992},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7384485006332397},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.7312630414962769},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6885995268821716},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4867822825908661},{"id":"https://openalex.org/keywords/signature","display_name":"Signature (topology)","score":0.4643452763557434},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4576486647129059},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3473038077354431},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34712982177734375},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3328574299812317},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3302338719367981},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3088539242744446},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.22596925497055054},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14602896571159363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8689249753952026},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.8449125289916992},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7384485006332397},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.7312630414962769},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6885995268821716},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4867822825908661},{"id":"https://openalex.org/C2779696439","wikidata":"https://www.wikidata.org/wiki/Q7512811","display_name":"Signature (topology)","level":2,"score":0.4643452763557434},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4576486647129059},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3473038077354431},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34712982177734375},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3328574299812317},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3302338719367981},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3088539242744446},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.22596925497055054},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14602896571159363},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2348283.2348339","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2348283.2348339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321659","display_name":"Shanghai Education Development Foundation","ror":"https://ror.org/02kq92y46"},{"id":"https://openalex.org/F4320321881","display_name":"Shanghai Municipal Education Commission","ror":"https://ror.org/05tewj457"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W179105903","https://openalex.org/W1502916507","https://openalex.org/W1536700701","https://openalex.org/W1596691921","https://openalex.org/W1835419070","https://openalex.org/W1971763646","https://openalex.org/W1977729554","https://openalex.org/W2019076926","https://openalex.org/W2044434631","https://openalex.org/W2067432306","https://openalex.org/W2079580248","https://openalex.org/W2081004195","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2100495367","https://openalex.org/W2109803107","https://openalex.org/W2110764701","https://openalex.org/W2123871098","https://openalex.org/W2132069633","https://openalex.org/W2132540527","https://openalex.org/W2136922672","https://openalex.org/W2139774022","https://openalex.org/W2148578434","https://openalex.org/W2148885851","https://openalex.org/W2153180170","https://openalex.org/W2154118576","https://openalex.org/W2167206925","https://openalex.org/W2167302605","https://openalex.org/W2221852422","https://openalex.org/W2293597654","https://openalex.org/W2916086000","https://openalex.org/W2990138404","https://openalex.org/W2997945685","https://openalex.org/W3145042860","https://openalex.org/W4250981202","https://openalex.org/W4299828299"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W2597809628","https://openalex.org/W3046370962"],"abstract_inverted_index":{"Content":[0],"reuse":[1],"is":[2,64],"extremely":[3],"common":[4],"in":[5,95,108],"user":[6,31],"generated":[7,32],"mediums.":[8],"Reuse":[9],"detection":[10,85,131],"serves":[11],"as":[12],"be":[13],"the":[14,22,34,84,105,124,129],"basis":[15],"for":[16,70],"many":[17],"applications.":[18],"However,":[19],"along":[20],"with":[21,76,133],"explosion":[23],"of":[24,30,78,80,100,104,111],"Internet":[25],"and":[26,39,49,102,117],"continuously":[27],"growing":[28],"uses":[29,137],"mediums,":[33],"task":[35],"becomes":[36],"more":[37],"critical":[38],"difficult.":[40],"In":[41,72],"this":[42,96],"paper,":[43],"we":[44,82],"present":[45],"a":[46,58],"novel":[47],"efficient":[48],"scalable":[50],"approach":[51,86,107,126],"to":[52,74,146],"detect":[53],"content":[54],"reuse.":[55],"We":[56],"propose":[57],"new":[59],"signature":[60],"generation":[61],"algorithm,":[62],"which":[63],"based":[65],"on":[66,87],"learned":[67],"hash":[68],"functions":[69],"words.":[71],"order":[73],"deal":[75],"tens":[77],"billions":[79],"documents,":[81],"implement":[83],"graphical":[88],"processing":[89],"units":[90],"(GPUs).":[91],"The":[92],"experimental":[93],"comparison":[94],"paper":[97],"involves":[98],"studies":[99],"efficiency":[101],"effectiveness":[103],"proposed":[106,125],"different":[109],"types":[110],"document":[112],"collections,":[113],"including":[114],"ClueWeb09,":[115],"Tweets2011,":[116],"so":[118],"on.":[119],"Experimental":[120],"results":[121],"show":[122],"that":[123],"can":[127],"achieve":[128],"same":[130],"rates":[132],"state-of-the-art":[134],"systems":[135],"while":[136],"significantly":[138],"less":[139],"execution":[140],"time":[141],"than":[142],"them":[143],"(from":[144],"400X":[145],"1500X":[147],"speedup).":[148]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
