{"id":"https://openalex.org/W2052416092","doi":"https://doi.org/10.1109/icis.2013.6607818","title":"Layout-tree-based approach for identifying visually similar blocks in a web page","display_name":"Layout-tree-based approach for identifying visually similar blocks in a web page","publication_year":2013,"publication_date":"2013-06-01","ids":{"openalex":"https://openalex.org/W2052416092","doi":"https://doi.org/10.1109/icis.2013.6607818","mag":"2052416092"},"language":"en","primary_location":{"id":"doi:10.1109/icis.2013.6607818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icis.2013.6607818","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE/ACIS 12th International Conference on Computer and Information Science (ICIS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://catalog.lib.kyushu-u.ac.jp/opac_download_md/1442112/hirokawa_37.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024752776","display_name":"Jun Zeng","orcid":"https://orcid.org/0000-0003-3129-9052"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Jun Zeng","raw_affiliation_strings":["Graduate School of Information Science and Electrical Engineering, Kyushu University, Fukuoka, Japan","Grad. Sch. of Inf., Sci. & Electr. Eng., Kyushu Univ., Fukuoka, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Electrical Engineering, Kyushu University, Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]},{"raw_affiliation_string":"Grad. Sch. of Inf., Sci. & Electr. Eng., Kyushu Univ., Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025409280","display_name":"Brendan Flanagan","orcid":"https://orcid.org/0000-0001-7644-997X"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Brendan Flanagan","raw_affiliation_strings":["Graduate School of Information Science and Electrical Engineering, Kyushu University, Fukuoka, Japan","Grad. Sch. of Inf., Sci. & Electr. Eng., Kyushu Univ., Fukuoka, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Electrical Engineering, Kyushu University, Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]},{"raw_affiliation_string":"Grad. Sch. of Inf., Sci. & Electr. Eng., Kyushu Univ., Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006267512","display_name":"Sachio Hirokawa","orcid":"https://orcid.org/0000-0002-8050-1109"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sachio Hirokawa","raw_affiliation_strings":["Graduate School of Information Science and Electrical Engineering, Kyushu University, Fukuoka, Japan","Research Institute for Information Technology, Kyushu University, Fukuoka, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Electrical Engineering, Kyushu University, Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]},{"raw_affiliation_string":"Research Institute for Information Technology, Kyushu University, Fukuoka, Japan#TAB#","institution_ids":["https://openalex.org/I135598925"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5024752776"],"corresponding_institution_ids":["https://openalex.org/I135598925"],"apc_list":null,"apc_paid":null,"fwci":1.6711,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.88632779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"14","issue":null,"first_page":"65","last_page":"70"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.973800003528595,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9472000002861023,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8173379898071289},{"id":"https://openalex.org/keywords/xpath","display_name":"XPath","score":0.6957976818084717},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6369035243988037},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6319172978401184},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6158827543258667},{"id":"https://openalex.org/keywords/page-layout","display_name":"Page layout","score":0.49414733052253723},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.4930724799633026},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44292521476745605},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39612361788749695},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.387861043214798},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38709893822669983},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1874433159828186},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.1709253191947937},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0788273811340332}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8173379898071289},{"id":"https://openalex.org/C2780213375","wikidata":"https://www.wikidata.org/wiki/Q16340","display_name":"XPath","level":4,"score":0.6957976818084717},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6369035243988037},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6319172978401184},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6158827543258667},{"id":"https://openalex.org/C188985296","wikidata":"https://www.wikidata.org/wiki/Q868954","display_name":"Page layout","level":2,"score":0.49414733052253723},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.4930724799633026},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44292521476745605},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39612361788749695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.387861043214798},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38709893822669983},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1874433159828186},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.1709253191947937},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0788273811340332},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.0},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icis.2013.6607818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icis.2013.6607818","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE/ACIS 12th International Conference on Computer and Information Science (ICIS)","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01211:0005974416","is_oa":true,"landing_page_url":"https://hdl.handle.net/2324/1442112","pdf_url":"https://catalog.lib.kyushu-u.ac.jp/opac_download_md/1442112/hirokawa_37.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2013 IEEE/ACIS 12th International Conference on Computer and Information Science, ICIS 2013 - Proceedings","raw_type":"conference paper"},{"id":"pmh:oai:catalog.lib.kyushu-u.ac.jp:2324/1442112","is_oa":true,"landing_page_url":"http://hdl.handle.net/2324/1442112","pdf_url":null,"source":{"id":"https://openalex.org/S4306400832","display_name":"Kyushu University Institutional Repository (QIR) (Kyushu University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I135598925","host_organization_name":"Kyushu University","host_organization_lineage":["https://openalex.org/I135598925"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2013 IEEE/ACIS 12th International Conference on Computer and Information Science, ICIS 2013 - Proceedings","raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01211:0005974416","is_oa":true,"landing_page_url":"https://hdl.handle.net/2324/1442112","pdf_url":"https://catalog.lib.kyushu-u.ac.jp/opac_download_md/1442112/hirokawa_37.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2013 IEEE/ACIS 12th International Conference on Computer and Information Science, ICIS 2013 - Proceedings","raw_type":"conference paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2052416092.pdf","grobid_xml":"https://content.openalex.org/works/W2052416092.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W36911888","https://openalex.org/W151043533","https://openalex.org/W1821340588","https://openalex.org/W1976373002","https://openalex.org/W2049051779","https://openalex.org/W2084886972","https://openalex.org/W2121137265","https://openalex.org/W2134150392","https://openalex.org/W2160189941","https://openalex.org/W2171364811","https://openalex.org/W6678272963"],"related_works":["https://openalex.org/W2390183027","https://openalex.org/W2031790754","https://openalex.org/W2373402338","https://openalex.org/W2467186806","https://openalex.org/W3144508074","https://openalex.org/W2951920527","https://openalex.org/W3175996217","https://openalex.org/W3045321859","https://openalex.org/W2076910790","https://openalex.org/W2126372189"],"abstract_inverted_index":{"When":[0],"extracting":[1],"information":[2],"from":[3],"a":[4,65,70,90,95,98,116,134],"web":[5,42,96],"page,":[6],"IE":[7],"systems":[8],"usually":[9],"need":[10],"to":[11,15,59,74,173],"perform":[12],"pattern":[13,71,81],"recognition":[14,72],"identify":[16,75,174],"the":[17,108,122,131,139,142,152,166],"elements":[18,109],"that":[19,121,165],"have":[20,53],"similar":[21,79,117,157,176],"patterns.":[22],"However,":[23],"most":[24],"of":[25,41,67,110,141,145,162],"them":[26],"are":[27,46,113,125,155],"mainly":[28],"based":[29],"on":[30],"analyzing":[31],"HMTL":[32],"source":[33],"code,":[34],"DOM":[35],"tree,":[36],"tag":[37],"tree":[38,168],"or":[39,48,101,158],"Xpath":[40],"pages.":[43],"These":[44],"methods":[45],"language-dependent,":[47],"more":[49],"precisely,":[50],"HTML-dependent.":[51],"They":[52],"some":[54],"insuperable":[55],"limitations.":[56],"In":[57,85],"order":[58],"overcome":[60],"these":[61],"limitations,":[62],"we":[63,88,119,148],"propose":[64],"notion":[66],"layout-tree":[68],"and":[69],"method":[73,172],"visual":[76,80,99],"blocks":[77,112,124,154],"with":[78],"using":[82],"layout":[83,132,135,143,167],"tree.":[84,136],"this":[86],"paper,":[87],"call":[89],"visible":[91],"rectangular":[92],"region":[93],"in":[94,115],"page":[97],"block":[100,102],"for":[103],"short.":[104],"We":[105,128],"consider":[106],"if":[107],"two":[111,123,146,153],"displayed":[114],"layout,":[118],"define":[120],"visually":[126,156,175],"similar.":[127],"first":[129],"transform":[130],"into":[133],"By":[137],"calculating":[138],"similarity":[140],"trees":[144],"blocks,":[147],"can":[149],"determine":[150],"whether":[151],"not.":[159],"The":[160],"result":[161],"experiment":[163],"shows":[164],"is":[169],"an":[170],"effective":[171],"blocks.":[177]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
