{"id":"https://openalex.org/W1984849632","doi":"https://doi.org/10.1145/1277741.1277924","title":"A web page topic segmentation algorithm based on visual criteria and content layout","display_name":"A web page topic segmentation algorithm based on visual criteria and content layout","publication_year":2007,"publication_date":"2007-07-23","ids":{"openalex":"https://openalex.org/W1984849632","doi":"https://doi.org/10.1145/1277741.1277924","mag":"1984849632"},"language":"en","primary_location":{"id":"doi:10.1145/1277741.1277924","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval","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/A5003793107","display_name":"Idir Chibane","orcid":null},"institutions":[{"id":"https://openalex.org/I102475099","display_name":"Sup\u00e9lec","ror":"https://ror.org/00n7gwn90","country_code":"FR","type":"education","lineage":["https://openalex.org/I102475099"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Idir Chibane","raw_affiliation_strings":["SUPELEC, Gif sur Yvette, France","SUPELEC - Gif sur Yvette, France"],"affiliations":[{"raw_affiliation_string":"SUPELEC, Gif sur Yvette, France","institution_ids":["https://openalex.org/I102475099"]},{"raw_affiliation_string":"SUPELEC - Gif sur Yvette, France","institution_ids":["https://openalex.org/I102475099"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109248825","display_name":"Bich-Li\u00ean Doan","orcid":"https://orcid.org/0009-0001-5853-2486"},"institutions":[{"id":"https://openalex.org/I102475099","display_name":"Sup\u00e9lec","ror":"https://ror.org/00n7gwn90","country_code":"FR","type":"education","lineage":["https://openalex.org/I102475099"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Bich-Lien Doan","raw_affiliation_strings":["SUPELEC, Gif sur Yvette, France","SUPELEC - Gif sur Yvette, France"],"affiliations":[{"raw_affiliation_string":"SUPELEC, Gif sur Yvette, France","institution_ids":["https://openalex.org/I102475099"]},{"raw_affiliation_string":"SUPELEC - Gif sur Yvette, France","institution_ids":["https://openalex.org/I102475099"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5003793107"],"corresponding_institution_ids":["https://openalex.org/I102475099"],"apc_list":null,"apc_paid":null,"fwci":3.94821674,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.93499448,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"817","last_page":"818"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9660000205039978,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9649999737739563,"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":0.7724634408950806},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5748367309570312},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5630342364311218},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5193942189216614},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.4774751663208008},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.46993881464004517},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3773602843284607},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33630573749542236},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2552988827228546},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10712912678718567}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7724634408950806},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5748367309570312},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5630342364311218},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5193942189216614},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.4774751663208008},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.46993881464004517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3773602843284607},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33630573749542236},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2552988827228546},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10712912678718567},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1277741.1277924","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1566513354","https://openalex.org/W2015933107","https://openalex.org/W2019264297","https://openalex.org/W2082884138","https://openalex.org/W2162565240","https://openalex.org/W2166419939"],"related_works":["https://openalex.org/W4250539519","https://openalex.org/W4294018197","https://openalex.org/W2611741382","https://openalex.org/W3135843367","https://openalex.org/W4379231730","https://openalex.org/W3112355890","https://openalex.org/W2613685774","https://openalex.org/W4233433299","https://openalex.org/W4389858081","https://openalex.org/W1522196789"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"experiments":[3],"using":[4],"an":[5],"algorithm":[6],"of":[7,20,28,32,83,91],"web":[8,38],"page":[9,39,85],"topic":[10],"segmentation":[11,96],"that":[12,66],"show":[13],"significant":[14],"precision":[15],"improvement":[16],"in":[17],"the":[18,24,34,74,79,81,84,95],"retrieval":[19],"documents":[21],"issued":[22],"from":[23,94],"Web":[25],"track":[26],"corpus":[27],"TREC":[29],"2001.":[30],"Instead":[31],"processing":[33],"whole":[35],"document,":[36],"a":[37],"is":[40,86],"segmented":[41],"into":[42],"different":[43],"semantic":[44],"blocks":[45],"according":[46],"to":[47],"visual":[48,68],"criteria":[49,72],"(such":[50,58],"as":[51,59],"horizontal":[52],"lines,":[53],"colors)":[54],"and":[55,69],"structural":[56],"tags":[57],"headings":[60],"<H1>~<H6>,":[61],"paragraph":[62],"<P>).":[63],"We":[64],"conclude":[65],"combining":[67],"content":[70],"layout":[71],"gives":[73],"best":[75],"results":[76],"for":[77,88],"increasing":[78],"precision:":[80],"ranking":[82],"calculated":[87],"relevant":[89],"segments":[90],"pages":[92],"resulting":[93],"algorithm.":[97]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
