{"id":"https://openalex.org/W2103558289","doi":"https://doi.org/10.1145/2740908.2741712","title":"An Architecture for Information Extraction from Figures in Digital Libraries","display_name":"An Architecture for Information Extraction from Figures in Digital Libraries","publication_year":2015,"publication_date":"2015-05-18","ids":{"openalex":"https://openalex.org/W2103558289","doi":"https://doi.org/10.1145/2740908.2741712","mag":"2103558289"},"language":"en","primary_location":{"id":"doi:10.1145/2740908.2741712","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2740908.2741712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th 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/A5112500027","display_name":"Sagnik Ray Choudhury","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sagnik Ray Choudhury","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Clyde Lee Giles","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5112500027"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":2.9455,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.9414425,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"667","last_page":"672"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9990000128746033,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9990000128746033,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9984999895095825,"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":0.9983999729156494,"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":0.850961446762085},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7994108200073242},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5740207433700562},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5638022422790527},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5597469806671143},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.5285954475402832},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5251376628875732},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.5038248896598816},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.49255070090293884},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.45348188281059265},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4515411853790283},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4254024028778076},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.41939088702201843},{"id":"https://openalex.org/keywords/scalable-vector-graphics","display_name":"Scalable Vector Graphics","score":0.41639241576194763},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3010477125644684},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29069092869758606},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.23610249161720276},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2167586386203766},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.19219326972961426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.850961446762085},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7994108200073242},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5740207433700562},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5638022422790527},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5597469806671143},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.5285954475402832},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5251376628875732},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.5038248896598816},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.49255070090293884},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.45348188281059265},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4515411853790283},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4254024028778076},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.41939088702201843},{"id":"https://openalex.org/C202629362","wikidata":"https://www.wikidata.org/wiki/Q2078","display_name":"Scalable Vector Graphics","level":2,"score":0.41639241576194763},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3010477125644684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29069092869758606},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.23610249161720276},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2167586386203766},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.19219326972961426},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2740908.2741712","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2740908.2741712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on World Wide Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309815","display_name":"Qatar Foundation","ror":"https://ror.org/01cawbq05"},{"id":"https://openalex.org/F4320332753","display_name":"Qatar National Research Fund","ror":"https://ror.org/01svaqq28"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W8079469","https://openalex.org/W51997014","https://openalex.org/W109704159","https://openalex.org/W1511676561","https://openalex.org/W1602715074","https://openalex.org/W1976316416","https://openalex.org/W1996457856","https://openalex.org/W2028657008","https://openalex.org/W2053604034","https://openalex.org/W2060928565","https://openalex.org/W2085361026","https://openalex.org/W2091344457","https://openalex.org/W2097817347","https://openalex.org/W2113227937","https://openalex.org/W2118858186","https://openalex.org/W2139175872","https://openalex.org/W2147698110","https://openalex.org/W2282529174","https://openalex.org/W2583417751","https://openalex.org/W4244214432"],"related_works":["https://openalex.org/W2358969090","https://openalex.org/W3183425535","https://openalex.org/W2354624479","https://openalex.org/W2394137533","https://openalex.org/W2362190996","https://openalex.org/W2385461408","https://openalex.org/W2119089902","https://openalex.org/W2387643967","https://openalex.org/W2393464257","https://openalex.org/W2352713710"],"abstract_inverted_index":{"Scholarly":[0],"documents":[1,107],"contain":[2],"multiple":[3],"figures":[4,9,43,61,75,148],"representing":[5],"experimental":[6],"findings.":[7],"These":[8],"are":[10],"generated":[11],"from":[12,51,73,105,147],"data":[13,71,145],"which":[14,149],"is":[15,131,150],"not":[16],"reported":[17],"anywhere":[18],"else":[19],"in":[20,94],"the":[21,36,59,74,85,88,92,118,121,128],"paper.":[22],"We":[23,90,138],"propose":[24],"a":[25,109,141],"modular":[26],"architecture":[27,33],"for":[28,42,69,112,144],"analyzing":[29],"such":[30],"figures.":[31,113],"Our":[32,114],"consists":[34],"of":[35,87,120],"following":[37],"modules:":[38],"1.":[39],"An":[40,65],"extractor":[41,99,115],"and":[44,49,62,76,108,127],"associated":[45],"metadata":[46],"(figure":[47],"captions":[48],"mentions)":[50],"PDF":[52],"documents;":[53],"2.":[54],"A":[55,78],"Search":[56],"engine":[57,155],"on":[58],"extracted":[60],"metadata;":[63],"3.":[64],"image":[66],"processing":[67,81],"module":[68,82],"automated":[70],"extraction":[72,146],"4.":[77],"natural":[79],"language":[80],"to":[83,101,156],"understand":[84],"semantics":[86],"figure.":[89],"discuss":[91],"challenges":[93],"each":[95],"step,":[96],"report":[97],"an":[98],"algorithm":[100,111,116],"extract":[102],"vector":[103],"graphics":[104],"scholarly":[106],"classification":[110,129],"improves":[117],"state":[119],"art":[122],"by":[123],"more":[124],"than":[125],"10%":[126],"process":[130],"very":[132],"scalable,":[133],"yet":[134],"achieves":[135],"85\\%":[136],"accuracy.":[137],"also":[139],"describe":[140],"semi-automatic":[142],"system":[143],"integrated":[151],"with":[152],"our":[153],"search":[154],"improve":[157],"user":[158],"experience.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}