{"id":"https://openalex.org/W2080782708","doi":"https://doi.org/10.1109/icdar.2007.4377051","title":"A General Approach for Partitioning Web Page Content Based on Geometric and Style Information","display_name":"A General Approach for Partitioning Web Page Content Based on Geometric and Style Information","publication_year":2007,"publication_date":"2007-09-01","ids":{"openalex":"https://openalex.org/W2080782708","doi":"https://doi.org/10.1109/icdar.2007.4377051","mag":"2080782708"},"language":"en","primary_location":{"id":"doi:10.1109/icdar.2007.4377051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2007.4377051","pdf_url":null,"source":{"id":"https://openalex.org/S4210215987","display_name":"Proceedings of the International Conference on Document Analysis and Recognition","issn_l":"1520-5363","issn":["1520-5363","2379-2140"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 2","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/A5075613260","display_name":"Hai-Feng Guo","orcid":"https://orcid.org/0000-0002-7558-8465"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"H. Guo","raw_affiliation_strings":["Computer Science Department, Stony Brook University, Stony Brook, NY, USA","Stony Brook Univ, Stony Brook"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stony Brook University, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I59553526"]},{"raw_affiliation_string":"Stony Brook Univ, Stony Brook","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112967180","display_name":"Jishnu Mahmud","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Mahmud","raw_affiliation_strings":["Computer Science Department, Stony Brook University, Stony Brook, NY, USA","Stony Brook Univ, Stony Brook"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stony Brook University, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I59553526"]},{"raw_affiliation_string":"Stony Brook Univ, Stony Brook","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068471186","display_name":"Yevgen Borodin","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Y. Borodin","raw_affiliation_strings":["Computer Science Department, Stony Brook University, Stony Brook, NY, USA","Stony Brook Univ, Stony Brook"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stony Brook University, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I59553526"]},{"raw_affiliation_string":"Stony Brook Univ, Stony Brook","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053693571","display_name":"Amanda Stent","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Stent","raw_affiliation_strings":["Computer Science Department, Stony Brook University, Stony Brook, NY, USA","Stony Brook Univ, Stony Brook"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stony Brook University, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I59553526"]},{"raw_affiliation_string":"Stony Brook Univ, Stony Brook","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005648942","display_name":"I. V. Ramakrishnan","orcid":"https://orcid.org/0000-0002-1768-7043"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"I. Ramakrishnan","raw_affiliation_strings":["Computer Science Department, Stony Brook University, Stony Brook, NY, USA","Stony Brook Univ, Stony Brook"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stony Brook University, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I59553526"]},{"raw_affiliation_string":"Stony Brook Univ, Stony Brook","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5075613260"],"corresponding_institution_ids":["https://openalex.org/I59553526"],"apc_list":null,"apc_paid":null,"fwci":2.3427,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.88166895,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"929","last_page":"933"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9801999926567078,"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":0.9749000072479248,"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":0.739037811756134},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.6195533275604248},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5973532795906067},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5876972675323486},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4709884822368622},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4298820495605469},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15551984310150146}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.739037811756134},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.6195533275604248},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5973532795906067},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5876972675323486},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4709884822368622},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4298820495605469},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15551984310150146},{"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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icdar.2007.4377051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2007.4377051","pdf_url":null,"source":{"id":"https://openalex.org/S4210215987","display_name":"Proceedings of the International Conference on Document Analysis and Recognition","issn_l":"1520-5363","issn":["1520-5363","2379-2140"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 2","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.304.8808","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.304.8808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.sunysb.edu/~jmahmud/ICDAR.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W11658723","https://openalex.org/W1506984360","https://openalex.org/W1553306009","https://openalex.org/W1576923525","https://openalex.org/W1803802947","https://openalex.org/W1978852834","https://openalex.org/W2036114781","https://openalex.org/W2067161274","https://openalex.org/W2095680579","https://openalex.org/W2100815879","https://openalex.org/W2104086170","https://openalex.org/W2115461474","https://openalex.org/W2143309843","https://openalex.org/W2150721933","https://openalex.org/W4285719527","https://openalex.org/W6600490174","https://openalex.org/W6633201171","https://openalex.org/W6634274187","https://openalex.org/W6638151354","https://openalex.org/W6674674992","https://openalex.org/W6675573929","https://openalex.org/W6676955721"],"related_works":["https://openalex.org/W2356684049","https://openalex.org/W1488511360","https://openalex.org/W1781894645","https://openalex.org/W2894902932","https://openalex.org/W569715723","https://openalex.org/W188332989","https://openalex.org/W2982387199","https://openalex.org/W2106946048","https://openalex.org/W2000745862","https://openalex.org/W2120930843"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"describe":[4],"a":[5,28],"general-purpose":[6],"approach":[7],"for":[8],"partitioning":[9],"Web":[10,29],"page":[11,30],"content.":[12],"The":[13],"novelty":[14],"of":[15,23,43,65],"our":[16,66],"ap-":[17],"proach":[18],"lies":[19],"in":[20],"the":[21,41,62],"use":[22,42],"detailed":[24],"layout":[25],"information":[26,50],"from":[27],"renderer":[31],"to":[32,51,60],"determine":[33,52],"spatial":[34],"locality":[35],"and":[36,40],"identify":[37],"visual":[38],"separators,":[39],"relaxed":[44],"matching":[45],"over":[46],"pre-":[47],"sentation":[48],"style":[49,54],"presentation":[53],"similarity.":[55],"We":[56],"present":[57],"several":[58],"examples":[59],"illustrate":[61],"gen-":[63],"erality":[64],"approach.":[67]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}