{"id":"https://openalex.org/W2096031153","doi":"https://doi.org/10.1145/1135777.1135951","title":"Visually guided bottom-up table detection and segmentation in web documents","display_name":"Visually guided bottom-up table detection and segmentation in web documents","publication_year":2006,"publication_date":"2006-05-23","ids":{"openalex":"https://openalex.org/W2096031153","doi":"https://doi.org/10.1145/1135777.1135951","mag":"2096031153"},"language":"en","primary_location":{"id":"doi:10.1145/1135777.1135951","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","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/A5081670164","display_name":"Bernhard Kr\u00fcpl","orcid":null},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Bernhard Kr\u00fcpl","raw_affiliation_strings":["Vienna University of Technology"],"affiliations":[{"raw_affiliation_string":"Vienna University of Technology","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111482934","display_name":"Marcus Herzog","orcid":null},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Marcus Herzog","raw_affiliation_strings":["Vienna University of Technology"],"affiliations":[{"raw_affiliation_string":"Vienna University of Technology","institution_ids":["https://openalex.org/I145847075"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081670164"],"corresponding_institution_ids":["https://openalex.org/I145847075"],"apc_list":null,"apc_paid":null,"fwci":7.3875,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.96546793,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"933","last_page":"934"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9983000159263611,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9966999888420105,"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":0.8444289565086365},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6830297708511353},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.6795459389686584},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6187558770179749},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5847834944725037},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5699774622917175},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5069403648376465},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.49647122621536255},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4899236559867859},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3734372556209564},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.26842573285102844},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2672833800315857},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1741039752960205}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8444289565086365},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6830297708511353},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.6795459389686584},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6187558770179749},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5847834944725037},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5699774622917175},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5069403648376465},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.49647122621536255},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4899236559867859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3734372556209564},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26842573285102844},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2672833800315857},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1741039752960205},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1135777.1135951","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","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":3,"referenced_works":["https://openalex.org/W8079469","https://openalex.org/W2125570474","https://openalex.org/W2138047800"],"related_works":["https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W4252555497","https://openalex.org/W3121175838","https://openalex.org/W3016293053","https://openalex.org/W1690653314","https://openalex.org/W2401723157","https://openalex.org/W2065055572","https://openalex.org/W2784269775","https://openalex.org/W2952904874"],"abstract_inverted_index":{"In":[0],"the":[1,17,26],"AllRight":[2],"project,":[3],"we":[4],"are":[5],"developing":[6],"an":[7],"algorithm":[8,30],"for":[9],"unsupervised":[10],"table":[11],"detection":[12],"and":[13,41,52],"segmentation":[14],"that":[15],"uses":[16,42],"visual":[18],"rendition":[19],"of":[20,45],"a":[21,43,53],"Web":[22,59],"page":[23],"rather":[24],"than":[25],"HTML":[27],"code.":[28],"Our":[29],"works":[31],"bottom-up":[32],"by":[33],"grouping":[34],"word":[35],"bounding":[36],"boxes":[37],"into":[38],"larger":[39],"groups":[40],"set":[44],"heuristics.":[46],"It":[47],"has":[48,61],"already":[49],"been":[50,62],"implemented":[51],"preliminary":[54],"evaluation":[55],"on":[56],"about":[57],"6000":[58],"documents":[60],"carried":[63],"out.":[64]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
