{"id":"https://openalex.org/W73854387","doi":"https://doi.org/10.1007/978-3-642-32498-7_16","title":"Near Duplicate Document Detection for Large Information Flows","display_name":"Near Duplicate Document Detection for Large Information Flows","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W73854387","doi":"https://doi.org/10.1007/978-3-642-32498-7_16","mag":"73854387"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-32498-7_16","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-642-32498-7_16","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-642-32498-7_16.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-642-32498-7_16.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020507426","display_name":"D. Montanari","orcid":"https://orcid.org/0000-0002-1980-7686"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Daniele Montanari","raw_affiliation_strings":["ICT eni - Semantic Technologies, Via Arcoveggio 74/2, Bologna, 40129, Italy"],"affiliations":[{"raw_affiliation_string":"ICT eni - Semantic Technologies, Via Arcoveggio 74/2, Bologna, 40129, Italy","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036980875","display_name":"Piera Laura Puglisi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098188","display_name":"Laboratori Guglielmo Marconi (Italy)","ror":"https://ror.org/01r3vad87","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210098188"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Piera Laura Puglisi","raw_affiliation_strings":["GESP, Via Marconi 71, Bologna, 40122, Italy"],"affiliations":[{"raw_affiliation_string":"GESP, Via Marconi 71, Bologna, 40122, Italy","institution_ids":["https://openalex.org/I4210098188"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020507426"],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":1.2184,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77214579,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"203","last_page":"217"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11719","display_name":"Data Quality and Management","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9958999752998352,"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":0.872096061706543},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6468334794044495},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6355735063552856},{"id":"https://openalex.org/keywords/bitmap","display_name":"Bitmap","score":0.6147504448890686},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5510807037353516},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5410851240158081},{"id":"https://openalex.org/keywords/timestamp","display_name":"Timestamp","score":0.5292738676071167},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5040354132652283},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4982433319091797},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.44662389159202576},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4417160451412201},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.4352530241012573},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4246372878551483},{"id":"https://openalex.org/keywords/similarity-measure","display_name":"Similarity measure","score":0.41861197352409363},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23927053809165955},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12488338351249695},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.11017629504203796},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10038095712661743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.872096061706543},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6468334794044495},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6355735063552856},{"id":"https://openalex.org/C3115412","wikidata":"https://www.wikidata.org/wiki/Q1194708","display_name":"Bitmap","level":2,"score":0.6147504448890686},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5510807037353516},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5410851240158081},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.5292738676071167},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5040354132652283},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4982433319091797},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.44662389159202576},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4417160451412201},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.4352530241012573},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4246372878551483},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.41861197352409363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23927053809165955},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12488338351249695},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.11017629504203796},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10038095712661743},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-642-32498-7_16","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-642-32498-7_16","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-642-32498-7_16.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:HAL:hal-01542467v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01542467","pdf_url":null,"source":{"id":"https://openalex.org/S4406922276","display_name":"INRIA a CCSD electronic archive server","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Cross-Domain Conference and Workshop on Availability, Reliability, and Security (CD-ARES), Aug 2012, Prague, Czech Republic. pp.203-217, ⟨10.1007/978-3-642-32498-7_16⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"doi:10.1007/978-3-642-32498-7_16","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-642-32498-7_16","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-642-32498-7_16.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W73854387.pdf","grobid_xml":"https://content.openalex.org/works/W73854387.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W21318272","https://openalex.org/W604518226","https://openalex.org/W1491923463","https://openalex.org/W1526619693","https://openalex.org/W1609518033","https://openalex.org/W1614703486","https://openalex.org/W2067432306","https://openalex.org/W2109803107","https://openalex.org/W2147717514","https://openalex.org/W2148885851","https://openalex.org/W2153180170","https://openalex.org/W2161936973","https://openalex.org/W2397770138","https://openalex.org/W2483934186","https://openalex.org/W6683401941"],"related_works":["https://openalex.org/W2060561905","https://openalex.org/W2350456333","https://openalex.org/W2101993108","https://openalex.org/W2356608866","https://openalex.org/W2394126128","https://openalex.org/W185307983","https://openalex.org/W2117716920","https://openalex.org/W2130486040","https://openalex.org/W2084276039","https://openalex.org/W2214033462"],"abstract_inverted_index":null,"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}