{"id":"https://openalex.org/W2098029937","doi":"https://doi.org/10.1145/2361354.2361380","title":"Structural and visual comparisons for web page archiving","display_name":"Structural and visual comparisons for web page archiving","publication_year":2012,"publication_date":"2012-09-04","ids":{"openalex":"https://openalex.org/W2098029937","doi":"https://doi.org/10.1145/2361354.2361380","mag":"2098029937"},"language":"en","primary_location":{"id":"doi:10.1145/2361354.2361380","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2361354.2361380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2012 ACM symposium on Document engineering","raw_type":"proceedings-article"},"type":"preprint","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/A5021018507","display_name":"Marc T. Law","orcid":"https://orcid.org/0000-0001-7767-2313"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Marc Teva Law","raw_affiliation_strings":["LIP6, UPMC - Sorbonne University, Paris, France"],"affiliations":[{"raw_affiliation_string":"LIP6, UPMC - Sorbonne University, Paris, France","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017490804","display_name":"Nicolas Thome","orcid":"https://orcid.org/0000-0003-4871-3045"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Thome","raw_affiliation_strings":["LIP6, UPMC - Sorbonne University, Paris, France"],"affiliations":[{"raw_affiliation_string":"LIP6, UPMC - Sorbonne University, Paris, France","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049035512","display_name":"St\u00e9phane Gan\u00e7arski","orcid":"https://orcid.org/0000-0002-5252-5314"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"St\u00e9phane Gan\u00e7arski","raw_affiliation_strings":["LIP6, UPMC - Sorbonne University, Paris, France"],"affiliations":[{"raw_affiliation_string":"LIP6, UPMC - Sorbonne University, Paris, France","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108118084","display_name":"Matthieu Cord","orcid":"https://orcid.org/0000-0002-0627-5844"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Matthieu Cord","raw_affiliation_strings":["LIP6, UPMC - Sorbonne University, Paris, France"],"affiliations":[{"raw_affiliation_string":"LIP6, UPMC - Sorbonne University, Paris, France","institution_ids":["https://openalex.org/I39804081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021018507"],"corresponding_institution_ids":["https://openalex.org/I39804081"],"apc_list":null,"apc_paid":null,"fwci":1.67,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.86278582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"117","last_page":"120"},"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":0.9994999766349792,"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":0.9994999766349792,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9955999851226807,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9922000169754028,"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":0.8133665323257446},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7694947719573975},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7679253220558167},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6226314306259155},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5616273880004883},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4692642092704773},{"id":"https://openalex.org/keywords/web-mapping","display_name":"Web mapping","score":0.4352415204048157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4117376208305359},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4115932881832123},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4107625186443329},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3379825949668884},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32065799832344055},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.31458598375320435},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3115401864051819},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.29609644412994385}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8133665323257446},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7694947719573975},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7679253220558167},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6226314306259155},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5616273880004883},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4692642092704773},{"id":"https://openalex.org/C24733836","wikidata":"https://www.wikidata.org/wiki/Q649186","display_name":"Web mapping","level":4,"score":0.4352415204048157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4117376208305359},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4115932881832123},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4107625186443329},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3379825949668884},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32065799832344055},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31458598375320435},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3115401864051819},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.29609644412994385},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2361354.2361380","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2361354.2361380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2012 ACM symposium on Document engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01272800v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01272800","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"12th edition of the ACM Symposium on Document Engineering, DocEng'12, Sep 2012, Paris, France. pp.117-120, ⟨10.1145/2361354.2361380⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1803802947","https://openalex.org/W1947400014","https://openalex.org/W1976921161","https://openalex.org/W1985659105","https://openalex.org/W2019373793","https://openalex.org/W2061783331","https://openalex.org/W2069796578","https://openalex.org/W2090193136","https://openalex.org/W2101098151","https://openalex.org/W2103509666","https://openalex.org/W2105730821","https://openalex.org/W2112451145","https://openalex.org/W2140390894","https://openalex.org/W2142995284","https://openalex.org/W2151103935","https://openalex.org/W2167859982","https://openalex.org/W2291511009","https://openalex.org/W6640954329","https://openalex.org/W6675303841","https://openalex.org/W6675930361"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W2186876116","https://openalex.org/W2105588725","https://openalex.org/W1972854571","https://openalex.org/W180238871","https://openalex.org/W1997016290","https://openalex.org/W2626548695","https://openalex.org/W2017818230"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,33,46,56,61,74,85],"Web":[6,21,34,67,81],"page":[7,35],"archiving":[8],"system":[9,41],"that":[10,69],"combines":[11],"state-of-the-art":[12],"comparison":[13,52],"methods":[14,53],"based":[15,43],"on":[16,120],"the":[17],"source":[18],"codes":[19],"of":[20,32,48,92,98,112],"pages,":[22],"with":[23,90],"computer":[24],"vision":[25],"techniques.":[26],"To":[27],"detect":[28],"whether":[29,105],"successive":[30,96],"versions":[31,97],"are":[36,115],"similar":[37,116],"or":[38,117],"not,":[39],"our":[40,124],"is":[42],"on:":[44],"(1)":[45],"combination":[47],"structural":[49],"and":[50],"visual":[51,62],"embedded":[54],"in":[55],"statistical":[57],"discriminative":[58],"model,":[59],"(2)":[60],"similarity":[63,93,113],"measure":[64],"designed":[65],"for":[66],"pages":[68],"improves":[70],"change":[71],"detection,":[72],"(3)":[73],"supervised":[75],"feature":[76],"selection":[77],"method":[78],"adapted":[79],"to":[80],"archiving.":[82],"We":[83],"train":[84],"Support":[86],"Vector":[87],"Machine":[88],"model":[89,102],"vectors":[91],"scores":[94],"between":[95],"pages.":[99],"The":[100],"trained":[101],"then":[103],"determines":[104],"two":[106],"versions,":[107],"defined":[108],"by":[109],"their":[110],"vector":[111],"scores,":[114],"not.":[118],"Experiments":[119],"real":[121],"archives":[122],"validate":[123],"approach.":[125]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}