{"id":"https://openalex.org/W2026968007","doi":"https://doi.org/10.1145/1148170.1148243","title":"Near-duplicate detection by instance-level constrained clustering","display_name":"Near-duplicate detection by instance-level constrained clustering","publication_year":2006,"publication_date":"2006-08-06","ids":{"openalex":"https://openalex.org/W2026968007","doi":"https://doi.org/10.1145/1148170.1148243","mag":"2026968007"},"language":"en","primary_location":{"id":"doi:10.1145/1148170.1148243","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th annual 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/A5006992390","display_name":"Hui Yang","orcid":"https://orcid.org/0000-0003-2560-9528"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hui Yang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009879041","display_name":"Jamie Callan","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jamie Callan","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5006992390"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":11.3799,"has_fulltext":false,"cited_by_count":88,"citation_normalized_percentile":{"value":0.98855382,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.998199999332428,"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/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.998199999332428,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9977999925613403,"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":0.7091180682182312},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6413921117782593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45103558897972107},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3272045850753784},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.326050728559494}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7091180682182312},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6413921117782593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45103558897972107},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3272045850753784},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.326050728559494}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1148170.1148243","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.116.4413","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.116.4413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~huiyang/publication/sigir2006.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1575770195","https://openalex.org/W1583837637","https://openalex.org/W1596382552","https://openalex.org/W1596691921","https://openalex.org/W1994748209","https://openalex.org/W2007842132","https://openalex.org/W2044434631","https://openalex.org/W2067432306","https://openalex.org/W2111549955","https://openalex.org/W2115657355","https://openalex.org/W2117154949","https://openalex.org/W2129070169","https://openalex.org/W2136542423","https://openalex.org/W2152565070","https://openalex.org/W2153180170","https://openalex.org/W2164634022","https://openalex.org/W2999905431","https://openalex.org/W4240913316"],"related_works":["https://openalex.org/W2033914206","https://openalex.org/W2146076056","https://openalex.org/W2163831990","https://openalex.org/W3003836766","https://openalex.org/W2046077695","https://openalex.org/W2378160586","https://openalex.org/W2042327336","https://openalex.org/W2996038082","https://openalex.org/W3047965787","https://openalex.org/W3184582087"],"abstract_inverted_index":{"For":[0],"the":[1,32,35,50,59,85,108],"task":[2,53],"of":[3,37,44,96],"near-duplicated":[4,38],"document":[5,79],"detection,":[6],"both":[7,45],"traditional":[8],"fingerprinting":[9],"techniques":[10],"used":[11,19],"in":[12,20,49,58],"database":[13],"community":[14,23],"and":[15,54,81,120],"bag-of-word":[16],"comparison":[17],"approaches":[18],"information":[21,76],"retrieval":[22],"are":[24,40],"not":[25],"sufficiently":[26],"accurate.":[27],"This":[28,62],"is":[29],"due":[30],"to":[31,88,100],"fact":[33],"that":[34,43,112],"characteristics":[36],"documents":[39,48,57],"different":[41],"from":[42,93],"\u201calmost-identical":[46],"\u201d":[47,56],"data":[51],"cleaning":[52],"\u201crelevant":[55],"search":[60],"task.":[61],"paper":[63],"presents":[64],"an":[65],"instance-level":[66],"constrained":[67],"clustering":[68,86],"approach":[69,114],"for":[70],"near-duplicate":[71,90,117],"detection.":[72],"The":[73],"framework":[74],"incorporates":[75],"such":[77],"as":[78,121,123,125],"attributes":[80],"content":[82],"structure":[83],"into":[84],"process":[87],"form":[89],"clusters.":[91],"Gathered":[92],"several":[94],"collections":[95],"public":[97],"comments":[98],"sent":[99],"U.S.":[101],"government":[102],"agencies":[103],"on":[104],"proposed":[105],"new":[106],"regulations,":[107],"experimental":[109],"results":[110],"demonstrate":[111],"our":[113],"outperforms":[115],"other":[116],"detection":[118],"algorithms":[119],"about":[122],"effective":[124],"human":[126],"assessors.":[127]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}