{"id":"https://openalex.org/W2464551156","doi":"https://doi.org/10.1145/2928294.2928305","title":"Scalable algorithms for scholarly figure mining and semantics","display_name":"Scalable algorithms for scholarly figure mining and semantics","publication_year":2016,"publication_date":"2016-06-02","ids":{"openalex":"https://openalex.org/W2464551156","doi":"https://doi.org/10.1145/2928294.2928305","mag":"2464551156"},"language":"en","primary_location":{"id":"doi:10.1145/2928294.2928305","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2928294.2928305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on Semantic Big Data","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"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100422410","display_name":"Shuting Wang","orcid":"https://orcid.org/0000-0003-1461-3898"},"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":"Shuting Wang","raw_affiliation_strings":["Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","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":"C. Lee. Giles","raw_affiliation_strings":["Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112500027"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":1.7139,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.88817653,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9993000030517578,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9961000084877014,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9937000274658203,"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":0.7957577705383301},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7460333108901978},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6803626418113708},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.596204936504364},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5290074944496155},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5083114504814148},{"id":"https://openalex.org/keywords/graph-database","display_name":"Graph database","score":0.4554370045661926},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.416698157787323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39757588505744934},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3422848880290985},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3193037807941437},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2533784508705139},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20670145750045776},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.17264866828918457}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7957577705383301},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7460333108901978},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6803626418113708},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.596204936504364},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5290074944496155},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5083114504814148},{"id":"https://openalex.org/C176225458","wikidata":"https://www.wikidata.org/wiki/Q595971","display_name":"Graph database","level":3,"score":0.4554370045661926},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.416698157787323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39757588505744934},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3422848880290985},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3193037807941437},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2533784508705139},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20670145750045776},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.17264866828918457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2928294.2928305","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2928294.2928305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on Semantic Big Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G608555560","display_name":null,"funder_award_id":"4-029-1-007","funder_id":"https://openalex.org/F4320332753","funder_display_name":"Qatar National Research Fund"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309085","display_name":"Center for Selective C-H Functionalization, National Science Foundation","ror":"https://ror.org/02h8v7m77"},{"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1848909379","https://openalex.org/W1896628871","https://openalex.org/W1986860025","https://openalex.org/W2027929866","https://openalex.org/W2028657008","https://openalex.org/W2042014073","https://openalex.org/W2053604034","https://openalex.org/W2091344457","https://openalex.org/W2103558289","https://openalex.org/W2136445095","https://openalex.org/W2160517426","https://openalex.org/W2222512263","https://openalex.org/W2296287566","https://openalex.org/W2407369602","https://openalex.org/W2577020101"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2095118173","https://openalex.org/W2382021449","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W2501188010","https://openalex.org/W3115442681","https://openalex.org/W4386112722","https://openalex.org/W2391000461"],"abstract_inverted_index":{"Most":[0],"scholarly":[1,47],"papers":[2],"contain":[3],"one":[4],"or":[5,83,98],"multiple":[6],"figures.":[7,60],"Often":[8],"these":[9],"figures":[10,30,78,92],"show":[11],"experimental":[12],"results,":[13],"e.g,":[14],"line":[15,94,105],"graphs":[16,106],"are":[17,130],"used":[18],"to":[19,24,107],"compare":[20],"various":[21],"methods.":[22],"Compared":[23],"the":[25,28,125],"text":[26],"of":[27,69,77,89,104],"paper,":[29],"and":[31,72,100],"their":[32],"semantics":[33],"have":[34],"received":[35],"relatively":[36],"less":[37],"attention.":[38],"This":[39],"has":[40,63,136],"significantly":[41],"limited":[42],"semantic":[43,57],"search":[44,48],"capabilities":[45],"in":[46],"engines.":[49],"Here,":[50],"we":[51],"report":[52],"scalable":[53,131],"algorithms":[54,129],"for":[55,59],"generating":[56],"metadata":[58,116],"Our":[61],"system":[62],"four":[64],"sequential":[65],"modules:":[66],"1.":[67],"Extraction":[68],"figure,":[70],"caption":[71],"mention;":[73],"2.":[74],"Binary":[75],"classification":[76,88],"as":[79,93],"compound":[80,91],"(contains":[81],"sub-figures)":[82],"not;":[84],"3.":[85],"Three":[86],"class":[87],"non":[90],"graph,":[95],"bar":[96],"graph":[97],"others;":[99],"4.":[101],"Automatic":[102],"processing":[103],"generate":[108],"a":[109,115],"textual":[110],"summary.":[111],"In":[112],"each":[113,120,133],"step":[114,135],"file":[117],"is":[118],"generated,":[119],"having":[121],"richer":[122],"information":[123],"than":[124,140],"previous":[126],"one.":[127],"The":[128],"yet":[132],"individual":[134],"an":[137],"accuracy":[138],"greater":[139],"80%.":[141]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}