{"id":"https://openalex.org/W2121871415","doi":"https://doi.org/10.1109/icdm.2002.1183910","title":"Recognition of common areas in a Web page using visual information: a possible application in a page classification","display_name":"Recognition of common areas in a Web page using visual information: a possible application in a page classification","publication_year":2003,"publication_date":"2003-06-26","ids":{"openalex":"https://openalex.org/W2121871415","doi":"https://doi.org/10.1109/icdm.2002.1183910","mag":"2121871415"},"language":"en","primary_location":{"id":"doi:10.1109/icdm.2002.1183910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2002.1183910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2002 IEEE International Conference on Data Mining, 2002. Proceedings.","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/A5060465245","display_name":"Milo\u0161 Kova\u010devi\u0107","orcid":"https://orcid.org/0000-0002-8216-4564"},"institutions":[{"id":"https://openalex.org/I4068193","display_name":"University of Belgrade","ror":"https://ror.org/02qsmb048","country_code":"RS","type":"education","lineage":["https://openalex.org/I4068193"]}],"countries":["RS"],"is_corresponding":true,"raw_author_name":"M. Kovacevic","raw_affiliation_strings":["School of Civil Engineering, University of Belgrade, Serbia"],"affiliations":[{"raw_affiliation_string":"School of Civil Engineering, University of Belgrade, Serbia","institution_ids":["https://openalex.org/I4068193"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107224746","display_name":"Michelangelo Diligenti","orcid":"https://orcid.org/0000-0002-5805-8032"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M. Diligenti","raw_affiliation_strings":["Dipartimento di Ingegneria dell'Informazione, University of Sienna, Italy"],"affiliations":[{"raw_affiliation_string":"Dipartimento di Ingegneria dell'Informazione, University of Sienna, Italy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022658803","display_name":"Marco Gori","orcid":"https://orcid.org/0000-0001-6337-5430"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M. Gori","raw_affiliation_strings":["Dipartimento di Ingegneria dell'Informazione, University of Sienna, Italy"],"affiliations":[{"raw_affiliation_string":"Dipartimento di Ingegneria dell'Informazione, University of Sienna, Italy","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030033846","display_name":"Veljko Milutinovi\u0107","orcid":"https://orcid.org/0000-0002-9380-5232"},"institutions":[{"id":"https://openalex.org/I4068193","display_name":"University of Belgrade","ror":"https://ror.org/02qsmb048","country_code":"RS","type":"education","lineage":["https://openalex.org/I4068193"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"V. Milutinovic","raw_affiliation_strings":["School of Electrical Engineering, University of Belgrade, Serbia"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, University of Belgrade, Serbia","institution_ids":["https://openalex.org/I4068193"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5060465245"],"corresponding_institution_ids":["https://openalex.org/I4068193"],"apc_list":null,"apc_paid":null,"fwci":11.1851,"has_fulltext":false,"cited_by_count":106,"citation_normalized_percentile":{"value":0.97957339,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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":0.9998000264167786,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9958999752998352,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.994700014591217,"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":0.8467432260513306},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.70945143699646},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6450172662734985},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.62785804271698},{"id":"https://openalex.org/keywords/header","display_name":"Header","score":0.6275115013122559},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6048035621643066},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4954873323440552},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45091870427131653},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4393094480037689},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.324896901845932},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.25555264949798584},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.10597863793373108}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8467432260513306},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.70945143699646},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6450172662734985},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.62785804271698},{"id":"https://openalex.org/C48105269","wikidata":"https://www.wikidata.org/wiki/Q1141160","display_name":"Header","level":2,"score":0.6275115013122559},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6048035621643066},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4954873323440552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45091870427131653},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4393094480037689},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.324896901845932},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.25555264949798584},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.10597863793373108},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icdm.2002.1183910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2002.1183910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2002 IEEE International Conference on Data Mining, 2002. Proceedings.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.15.7954","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.15.7954","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://galeb.etf.bg.ac.yu/~vm/papers/RecognitionWebPageAreas.pdf","raw_type":"text"},{"id":"pmh:oai:grafar.grf.bg.ac.rs:123456789/33","is_oa":false,"landing_page_url":"https://grafar.grf.bg.ac.rs/handle/123456789/33","pdf_url":null,"source":{"id":"https://openalex.org/S4306402541","display_name":"GraFar (University of Belgrade, Faculty of Civil Engineering)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210101313","host_organization_name":"University Hospital Center Dr Dragi\u0161a Mi\u0161ovi\u0107","host_organization_lineage":["https://openalex.org/I4210101313"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2002 Ieee International Conference On Data Mining, Proceedings","raw_type":"conferenceObject"},{"id":"pmh:oai:usiena-air.unisi.it:11365/33005","is_oa":false,"landing_page_url":"http://hdl.handle.net/11365/33005","pdf_url":null,"source":{"id":"https://openalex.org/S4377196319","display_name":"Use Siena air (University of Siena)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102064193","host_organization_name":"University of Siena","host_organization_lineage":["https://openalex.org/I102064193"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W21178600","https://openalex.org/W79173122","https://openalex.org/W1485536830","https://openalex.org/W1489992655","https://openalex.org/W1956559956","https://openalex.org/W2118020653","https://openalex.org/W2124673015","https://openalex.org/W2149706766","https://openalex.org/W2166407869","https://openalex.org/W2325227998","https://openalex.org/W2558287625","https://openalex.org/W3139831614","https://openalex.org/W4233527139","https://openalex.org/W4236137412","https://openalex.org/W6628883518","https://openalex.org/W6678701036","https://openalex.org/W6730126985","https://openalex.org/W6738852829"],"related_works":["https://openalex.org/W2171597999","https://openalex.org/W2189136227","https://openalex.org/W1866537546","https://openalex.org/W630850086","https://openalex.org/W3200508093","https://openalex.org/W4372053344","https://openalex.org/W3193978431","https://openalex.org/W2519240373","https://openalex.org/W36911888","https://openalex.org/W4385731361"],"abstract_inverted_index":{"Extracting":[0],"and":[1,20,43,92,96],"processing":[2,48],"information":[3,18,74,140],"from":[4,23],"Web":[5],"pages":[6],"is":[7,33,76],"an":[8],"important":[9],"task":[10],"in":[11,29,69,103,115],"many":[12],"areas":[13,87],"like":[14],"constructing":[15],"search":[16],"engines,":[17],"retrieval,":[19],"data":[21],"mining":[22],"the":[24,30,82,130,135,142],"Web.":[25],"A":[26],"common":[27,85],"approach":[28],"extraction":[31],"process":[32],"to":[34,45,78],"represent":[35],"a":[36,39,51,56,70,99,123],"page":[37,86],"as":[38,89],"\"bag":[40],"of":[41,84,98,117,144],"words\"":[42],"then":[44],"perform":[46],"additional":[47],"on":[49],"such":[50,88],"flat":[52],"representation.":[53],"We":[54,101],"propose":[55],"new,":[57],"hierarchical":[58],"representation":[59],"that":[60,106,122],"includes":[61],"browser":[62],"screen":[63],"coordinates":[64],"for":[65,81],"every":[66],"HTML":[67],"object":[68],"page.":[71,100],"Using":[72],"visual":[73],"one":[75],"able":[77],"define":[79],"heuristics":[80,109],"recognition":[83],"header,":[90],"left":[91],"right":[93],"menu,":[94],"footer":[95],"center":[97],"show":[102,121],"initial":[104],"experiments":[105],"using":[107,138],"our":[108],"defined":[110],"objects":[111],"are":[112],"recognized":[113],"properly":[114],"73%":[116],"cases.":[118],"Finally,":[119],"we":[120],"Naive":[124],"Bayes":[125],"classifier,":[126],"taking":[127],"into":[128],"account":[129],"proposed":[131],"representation,":[132],"clearly":[133],"outperforms":[134],"same":[136],"classifier":[137],"only":[139],"about":[141],"content":[143],"documents.":[145]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
