{"id":"https://openalex.org/W2511336212","doi":"https://doi.org/10.1145/2960811.2967165","title":"Bayesian Mixture Models on Connected Components for Newspaper Article Segmentation","display_name":"Bayesian Mixture Models on Connected Components for Newspaper Article Segmentation","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2511336212","doi":"https://doi.org/10.1145/2960811.2967165","mag":"2511336212"},"language":"en","primary_location":{"id":"doi:10.1145/2960811.2967165","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2960811.2967165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 ACM Symposium on Document Engineering","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/A5039126972","display_name":"Giorgos Sfikas","orcid":"https://orcid.org/0000-0002-7305-2886"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Giorgos Sfikas","raw_affiliation_strings":["NCSR, Athens, Greece"],"affiliations":[{"raw_affiliation_string":"NCSR, Athens, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057141895","display_name":"Georgios Louloudis","orcid":"https://orcid.org/0000-0003-4127-3796"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georgios Louloudis","raw_affiliation_strings":["NCSR, Athens, Greece"],"affiliations":[{"raw_affiliation_string":"NCSR, Athens, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031191307","display_name":"Nikolaos Stamatopoulos","orcid":"https://orcid.org/0000-0001-8785-5156"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikolaos Stamatopoulos","raw_affiliation_strings":["NCSR, Athens, Greece"],"affiliations":[{"raw_affiliation_string":"NCSR, Athens, Greece","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006291450","display_name":"Basilis Gatos","orcid":"https://orcid.org/0000-0001-9873-0826"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Basilis Gatos","raw_affiliation_strings":["NCSR, Athens, Greece"],"affiliations":[{"raw_affiliation_string":"NCSR, Athens, Greece","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5039126972"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.07546041,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"143","last_page":"146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9993000030517578,"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":0.9986000061035156,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9950000047683716,"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/newspaper","display_name":"Newspaper","score":0.7689087986946106},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.7610759735107422},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7047910690307617},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.6976097226142883},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6680041551589966},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6230100393295288},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5657134652137756},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.5360761880874634},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5263941287994385},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.43592825531959534},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43573689460754395},{"id":"https://openalex.org/keywords/connected-component","display_name":"Connected component","score":0.4122008681297302},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4118732511997223},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.4027754068374634},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19205516576766968}],"concepts":[{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.7689087986946106},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.7610759735107422},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7047910690307617},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6976097226142883},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6680041551589966},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6230100393295288},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5657134652137756},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.5360761880874634},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5263941287994385},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.43592825531959534},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43573689460754395},{"id":"https://openalex.org/C193435613","wikidata":"https://www.wikidata.org/wiki/Q2997928","display_name":"Connected component","level":2,"score":0.4122008681297302},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4118732511997223},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.4027754068374634},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19205516576766968},{"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/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.0},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2960811.2967165","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2960811.2967165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 ACM Symposium on Document Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1491504963","https://openalex.org/W1506806321","https://openalex.org/W1999183701","https://openalex.org/W2005173844","https://openalex.org/W2025384595","https://openalex.org/W2041835707","https://openalex.org/W2089298206","https://openalex.org/W2127319406","https://openalex.org/W2131448412","https://openalex.org/W2139821942","https://openalex.org/W2144496905","https://openalex.org/W2154032543","https://openalex.org/W2155619922","https://openalex.org/W2162431081","https://openalex.org/W2212155099","https://openalex.org/W2594443378","https://openalex.org/W2605170521","https://openalex.org/W2734798343"],"related_works":["https://openalex.org/W2888805565","https://openalex.org/W4312773271","https://openalex.org/W4315588616","https://openalex.org/W2769501189","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W4293863151","https://openalex.org/W2497860580","https://openalex.org/W2891616219","https://openalex.org/W3204672119"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,73],"propose":[4],"a":[5,22,34,57,70,92],"new":[6],"method":[7,88],"for":[8],"automated":[9],"segmentation":[10],"of":[11,24,82,94],"scanned":[12],"newspaper":[13],"pages":[14],"into":[15,48,65],"articles.":[16],"Article":[17],"regions":[18],"are":[19,74,102],"produced":[20],"as":[21],"result":[23],"merging":[25],"sub-article":[26,49],"level":[27],"content":[28],"and":[29,45,67,84],"title":[30,83],"regions.":[31,86],"We":[32],"use":[33],"Bayesian":[35,52],"Gaussian":[36],"mixture":[37],"model":[38,40,53],"to":[39,76],"page":[41],"Connected":[42],"Component":[43],"information":[44],"cluster":[46],"input":[47],"components.":[50],"The":[51,87],"is":[54,89],"conditioned":[55],"on":[56,91],"prior":[58,72],"distribution":[59],"over":[60],"region":[61],"features,":[62],"aiding":[63],"classification":[64],"titles":[66],"content.":[68],"Using":[69],"Dirichlet":[71],"able":[75],"automatically":[77],"estimate":[78],"correctly":[79],"the":[80],"number":[81],"article":[85],"tested":[90],"dataset":[93],"digitized":[95],"historical":[96],"newspapers,":[97],"where":[98],"visual":[99],"experimental":[100],"results":[101],"very":[103],"promising.":[104]},"counts_by_year":[{"year":2024,"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"}