{"id":"https://openalex.org/W1566513354","doi":"https://doi.org/10.1007/3-540-36901-5_42","title":"Extracting Content Structure for Web Pages Based on Visual Representation","display_name":"Extracting Content Structure for Web Pages Based on Visual Representation","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W1566513354","doi":"https://doi.org/10.1007/3-540-36901-5_42","mag":"1566513354"},"language":"en","primary_location":{"id":"doi:10.1007/3-540-36901-5_42","is_oa":false,"landing_page_url":"https://doi.org/10.1007/3-540-36901-5_42","pdf_url":null,"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":"conference-paper","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/A5037942269","display_name":"Deng Cai","orcid":"https://orcid.org/0000-0001-9817-4065"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Deng Cai","raw_affiliation_strings":["Microsoft Research Asia, China","Tsinghua University, Beijing, P.R.China","Microsoft Research Asia, Tsinghua University, Beijing, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Tsinghua University, Beijing, P.R.China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Microsoft Research Asia, Tsinghua University, Beijing, P. R. China","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084034136","display_name":"Shipeng Yu","orcid":"https://orcid.org/0000-0002-0262-4031"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shipeng Yu","raw_affiliation_strings":["Microsoft Research Asia, China","Peking University, Beijing, P.R.China","Microsoft Research Asia, Peking University, Beijing, P. R. China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Peking University, Beijing, P.R.China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Microsoft Research Asia, Peking University, Beijing, P. R. China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025631695","display_name":"Ji-Rong Wen","orcid":"https://orcid.org/0000-0002-9777-9676"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji-Rong Wen","raw_affiliation_strings":["Microsoft Research Asia, China","Microsoft Research Asia,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia,","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103733614","display_name":"Wei\u2010Ying Ma","orcid":"https://orcid.org/0000-0002-7384-0735"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Ying Ma","raw_affiliation_strings":["Microsoft Research Asia, China","Microsoft Research Asia,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia,","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":7.585,"has_fulltext":false,"cited_by_count":344,"citation_normalized_percentile":{"value":0.97834974,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"406","last_page":"417"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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/T13976","display_name":"Web visibility and informetrics","score":0.9731000065803528,"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/T11478","display_name":"Caching and Content Delivery","score":0.9509000182151794,"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":0.8770037889480591},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7110111713409424},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6873603463172913},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5950918793678284},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.5740207433700562},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.5047484636306763},{"id":"https://openalex.org/keywords/html-element","display_name":"HTML element","score":0.48705771565437317},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4457981288433075},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.43715041875839233},{"id":"https://openalex.org/keywords/content-adaptation","display_name":"Content adaptation","score":0.4201534390449524},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.33378732204437256},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.3322111964225769},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.17180120944976807},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10770058631896973},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.058097511529922485}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8770037889480591},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7110111713409424},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6873603463172913},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5950918793678284},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.5740207433700562},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.5047484636306763},{"id":"https://openalex.org/C81639021","wikidata":"https://www.wikidata.org/wiki/Q179551","display_name":"HTML element","level":3,"score":0.48705771565437317},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4457981288433075},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.43715041875839233},{"id":"https://openalex.org/C2776987467","wikidata":"https://www.wikidata.org/wiki/Q5165073","display_name":"Content adaptation","level":3,"score":0.4201534390449524},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.33378732204437256},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3322111964225769},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.17180120944976807},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10770058631896973},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.058097511529922485},{"id":"https://openalex.org/C172195944","wikidata":"https://www.wikidata.org/wiki/Q541265","display_name":"Ubiquitous computing","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/3-540-36901-5_42","is_oa":false,"landing_page_url":"https://doi.org/10.1007/3-540-36901-5_42","pdf_url":null,"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:CiteSeerX.psu:10.1.1.85.3169","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.85.3169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dbs.informatik.uni-muenchen.de/~spyu/paper/VIPS-APWeb.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W126367074","https://openalex.org/W128309512","https://openalex.org/W1748877974","https://openalex.org/W1908950999","https://openalex.org/W1981202432","https://openalex.org/W2015933107","https://openalex.org/W2017726337","https://openalex.org/W2019264297","https://openalex.org/W2066636486","https://openalex.org/W2070030212","https://openalex.org/W2076470289","https://openalex.org/W2095680579","https://openalex.org/W2100815879","https://openalex.org/W2118131693","https://openalex.org/W2166407869","https://openalex.org/W2169347997","https://openalex.org/W4233527139","https://openalex.org/W6600030697"],"related_works":["https://openalex.org/W1656419755","https://openalex.org/W1539890081","https://openalex.org/W2373402338","https://openalex.org/W2114620981","https://openalex.org/W2372453241","https://openalex.org/W2371387875","https://openalex.org/W4302086745","https://openalex.org/W2531660186","https://openalex.org/W2626998250","https://openalex.org/W1566513354"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":34},{"year":2014,"cited_by_count":37},{"year":2013,"cited_by_count":29},{"year":2012,"cited_by_count":22}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}
