{"id":"https://openalex.org/W4400048060","doi":"https://doi.org/10.31577/cai_2024_3_583","title":"Parallel Near-Duplicate Document Detection Using General-Purpose GPU","display_name":"Parallel Near-Duplicate Document Detection Using General-Purpose GPU","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4400048060","doi":"https://doi.org/10.31577/cai_2024_3_583"},"language":"en","primary_location":{"id":"doi:10.31577/cai_2024_3_583","is_oa":true,"landing_page_url":"https://doi.org/10.31577/cai_2024_3_583","pdf_url":"https://www.cai.sk/ojs/index.php/cai/article/download/2024_3_583/1294","source":{"id":"https://openalex.org/S4210200093","display_name":"Computing and Informatics","issn_l":"1335-9150","issn":["1335-9150","2585-8807"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing and Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.cai.sk/ojs/index.php/cai/article/download/2024_3_583/1294","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099522394","display_name":"Dimitar Peshevski","orcid":null},"institutions":[{"id":"https://openalex.org/I76245029","display_name":"Ss. Cyril and Methodius University in Skopje","ror":"https://ror.org/02wk2vx54","country_code":"MK","type":"education","lineage":["https://openalex.org/I76245029"]}],"countries":["MK"],"is_corresponding":false,"raw_author_name":"Dimitar Peshevski","raw_affiliation_strings":["Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University, Rugjer Boshkovikj 16, 1020, Skopje, North Macedonia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University, Rugjer Boshkovikj 16, 1020, Skopje, North Macedonia","institution_ids":["https://openalex.org/I76245029"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111770351","display_name":"Vladimir Zdraveski","orcid":null},"institutions":[{"id":"https://openalex.org/I76245029","display_name":"Ss. Cyril and Methodius University in Skopje","ror":"https://ror.org/02wk2vx54","country_code":"MK","type":"education","lineage":["https://openalex.org/I76245029"]}],"countries":["MK"],"is_corresponding":false,"raw_author_name":"Vladimir Zdraveski","raw_affiliation_strings":["Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University, Rugjer Boshkovikj 16, 1020, Skopje, North Macedonia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University, Rugjer Boshkovikj 16, 1020, Skopje, North Macedonia","institution_ids":["https://openalex.org/I76245029"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020080393","display_name":"Sasko Ristov","orcid":"https://orcid.org/0000-0003-1996-0098"},"institutions":[{"id":"https://openalex.org/I190249584","display_name":"Universit\u00e4t Innsbruck","ror":"https://ror.org/054pv6659","country_code":"AT","type":"education","lineage":["https://openalex.org/I190249584"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Sashko Ristov","raw_affiliation_strings":["Department of Computer Science, University of Innsbruck, Technikerstra\u00dfe 21a, A - 6020, Innsbruck, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Innsbruck, Technikerstra\u00dfe 21a, A - 6020, Innsbruck, Austria","institution_ids":["https://openalex.org/I190249584"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4375,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6027112,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"43","issue":"3","first_page":"583","last_page":"610"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9991999864578247,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9991999864578247,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9684000015258789,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9598000049591064,"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":0.6892955899238586},{"id":"https://openalex.org/keywords/general-purpose","display_name":"General purpose","score":0.5841629505157471},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4797581434249878},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.40591734647750854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3780919313430786},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3416043817996979},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32188889384269714},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.07387599349021912}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6892955899238586},{"id":"https://openalex.org/C2982832238","wikidata":"https://www.wikidata.org/wiki/Q5531640","display_name":"General purpose","level":2,"score":0.5841629505157471},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4797581434249878},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.40591734647750854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3780919313430786},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3416043817996979},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32188889384269714},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.07387599349021912}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.31577/cai_2024_3_583","is_oa":true,"landing_page_url":"https://doi.org/10.31577/cai_2024_3_583","pdf_url":"https://www.cai.sk/ojs/index.php/cai/article/download/2024_3_583/1294","source":{"id":"https://openalex.org/S4210200093","display_name":"Computing and Informatics","issn_l":"1335-9150","issn":["1335-9150","2585-8807"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing and Informatics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.31577/cai_2024_3_583","is_oa":true,"landing_page_url":"https://doi.org/10.31577/cai_2024_3_583","pdf_url":"https://www.cai.sk/ojs/index.php/cai/article/download/2024_3_583/1294","source":{"id":"https://openalex.org/S4210200093","display_name":"Computing and Informatics","issn_l":"1335-9150","issn":["1335-9150","2585-8807"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing and Informatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4400048060.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2115140794","https://openalex.org/W2041120224","https://openalex.org/W1977781958","https://openalex.org/W1504320321","https://openalex.org/W2067902980","https://openalex.org/W2548529098","https://openalex.org/W4312275919","https://openalex.org/W2338293335","https://openalex.org/W2039378765","https://openalex.org/W2614685449"],"abstract_inverted_index":{"In":[0,87],"today's":[1],"data-rich":[2],"world,":[3],"one":[4],"of":[5,38,82,96],"the":[6,36,80,97,105,116,125],"most":[7],"significant":[8],"challenges":[9],"is":[10,120],"efficiently":[11],"identifying":[12],"near-duplicate":[13,23,59,70,101],"data,":[14],"especially":[15],"when":[16],"integrating":[17],"data":[18],"from":[19,56],"various":[20],"sources.":[21],"Identifying":[22],"documents":[24],"applies":[25],"to":[26,34,68,78],"any":[27],"content":[28],"and":[29,45,62,128],"has":[30],"been":[31],"widely":[32],"used":[33],"enhance":[35],"efficiency":[37],"search":[39,52],"engines,":[40],"identify":[41],"plagiarism":[42],"or":[43,50],"spam,":[44],"so":[46],"on.":[47],"Even":[48],"smaller":[49],"specialized":[51],"engines":[53],"can":[54],"benefit":[55],"knowledge":[57],"about":[58],"documents.":[60,71],"Shingling":[61],"MinHash":[63,98],"are":[64,74],"two":[65],"state-of-the-art":[66],"approaches":[67],"detecting":[69],"However,":[72],"there":[73],"not":[75],"many":[76],"attempts":[77],"improve":[79],"performance":[81],"this":[83,88],"locality-sensitive":[84],"hashing":[85],"technique.":[86],"research":[89],"paper,":[90],"we":[91],"propose":[92],"a":[93],"parallel":[94,118,129],"implementation":[95],"algorithm":[99],"for":[100],"document":[102],"detection":[103],"utilizing":[104],"immense":[106],"parallelism":[107],"offered":[108],"by":[109],"general-purpose":[110],"GPUs.":[111],"Experimental":[112],"results":[113],"show":[114],"that":[115],"GPU-based":[117],"solution":[119],"far":[121],"more":[122],"cost-effective":[123],"than":[124],"CPU-based":[126],"sequential":[127],"solutions.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
