{"id":"https://openalex.org/W2416987009","doi":"https://doi.org/10.1145/2910896.2910904","title":"PDFFigures 2.0","display_name":"PDFFigures 2.0","publication_year":2016,"publication_date":"2016-06-10","ids":{"openalex":"https://openalex.org/W2416987009","doi":"https://doi.org/10.1145/2910896.2910904","mag":"2416987009"},"language":"en","primary_location":{"id":"doi:10.1145/2910896.2910904","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2910896.2910904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM/IEEE-CS on Joint Conference on Digital Libraries","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/A5020085226","display_name":"Christopher Clark","orcid":"https://orcid.org/0009-0007-2558-7396"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Clark","raw_affiliation_strings":["University of Washington, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046849436","display_name":"Santosh Divvala","orcid":"https://orcid.org/0000-0003-4042-5874"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Santosh Divvala","raw_affiliation_strings":["University of Washington, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.4828,"has_fulltext":false,"cited_by_count":117,"citation_normalized_percentile":{"value":0.98396126,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"143","last_page":"152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9980999827384949,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9980999827384949,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9980999827384949,"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/T10028","display_name":"Topic Modeling","score":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8582125902175903},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7530616521835327},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7361674308776855},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5648396015167236},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5412305593490601},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5032829642295837},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.49862027168273926},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.46482613682746887},{"id":"https://openalex.org/keywords/section","display_name":"Section (typography)","score":0.4530075788497925},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.42626282572746277},{"id":"https://openalex.org/keywords/table-of-contents","display_name":"Table of contents","score":0.4211602807044983},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.41775599122047424},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3800387680530548},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.336810827255249},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.19008967280387878},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1739971935749054}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8582125902175903},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7530616521835327},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7361674308776855},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5648396015167236},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5412305593490601},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5032829642295837},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.49862027168273926},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.46482613682746887},{"id":"https://openalex.org/C2780129039","wikidata":"https://www.wikidata.org/wiki/Q1931107","display_name":"Section (typography)","level":2,"score":0.4530075788497925},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.42626282572746277},{"id":"https://openalex.org/C68476402","wikidata":"https://www.wikidata.org/wiki/Q1456936","display_name":"Table of contents","level":2,"score":0.4211602807044983},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.41775599122047424},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3800387680530548},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.336810827255249},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.19008967280387878},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1739971935749054},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2910896.2910904","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2910896.2910904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM/IEEE-CS on Joint Conference on Digital Libraries","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1559499673","https://openalex.org/W1603719052","https://openalex.org/W2027929866","https://openalex.org/W2031489346","https://openalex.org/W2064354603","https://openalex.org/W2139069711","https://openalex.org/W2168065722","https://openalex.org/W2189465200","https://openalex.org/W2306526421","https://openalex.org/W2415253009","https://openalex.org/W2577020101","https://openalex.org/W2731742681","https://openalex.org/W4252519526","https://openalex.org/W6687322159"],"related_works":["https://openalex.org/W2075768550","https://openalex.org/W3022218857","https://openalex.org/W2369178846","https://openalex.org/W2370289839","https://openalex.org/W2082716031","https://openalex.org/W2933494595","https://openalex.org/W4313347705","https://openalex.org/W1568049691","https://openalex.org/W4287688258","https://openalex.org/W3049211950"],"abstract_inverted_index":{"Figures":[0],"and":[1,23,47,68,73,77,113,155,207],"tables":[2,24,78],"are":[3],"key":[4],"sources":[5],"of":[6,21,60,70,97,109,133,150,166,179,193,199],"information":[7],"in":[8],"many":[9],"scholarly":[10],"documents.":[11],"However,":[12],"current":[13],"academic":[14,169],"search":[15,170],"engines":[16],"do":[17],"not":[18],"make":[19],"use":[20],"figures":[22,76,146,187],"when":[25],"semantically":[26],"parsing":[27],"documents":[28,50],"or":[29],"presenting":[30],"document":[31],"summaries":[32],"to":[33,144],"users.":[34],"To":[35,88],"facilitate":[36],"these":[37],"applications":[38],"we":[39,92,137,176],"develop":[40],"an":[41,191],"algorithm":[42,118],"that":[43,86],"extracts":[44],"figures,":[45,111],"tables,":[46,112],"captions":[48,114],"from":[49,147],"called":[51],"\"PDFFigures":[52],"2.0.\"":[53],"Our":[54,117],"proposed":[55],"approach":[56],"analyzes":[57],"the":[58,82,107,110,134,157,163,185,197],"structure":[59],"individual":[61],"pages":[62],"by":[63,79],"detecting":[64],"captions,":[65],"graphical":[66],"elements,":[67],"chunks":[69],"body":[71],"text,":[72],"then":[74],"locates":[75],"reasoning":[80],"about":[81],"empty":[83],"regions":[84],"within":[85,115],"text.":[87],"evaluate":[89],"our":[90,140,194,205,210],"work,":[91],"introduce":[93],"a":[94,148,167],"new":[95],"dataset":[96,129,206],"computer":[98],"science":[99],"papers,":[100,154],"along":[101],"with":[102],"ground":[103],"truth":[104],"labels":[105],"for":[106,196,213],"locations":[108],"them.":[116],"achieves":[119],"impressive":[120],"results":[121,178],"(94%":[122],"precision":[123],"at":[124],"90%":[125],"recall)":[126],"on":[127,184,209],"this":[128],"surpassing":[130],"previous":[131],"state":[132],"art.":[135],"Further,":[136],"show":[138],"how":[139,156],"framework":[141],"was":[142],"used":[143],"extract":[145],"corpus":[149],"over":[151],"one":[152],"million":[153],"resulting":[158],"extractions":[159],"were":[160],"integrated":[161],"into":[162],"user":[164],"interface":[165],"smart":[168],"engine,":[171],"Semantic":[172],"Scholar":[173],"(www.semanticscholar.org).":[174],"Finally,":[175],"present":[177],"exploratory":[180],"data":[181],"analysis":[182],"completed":[183],"extracted":[186],"as":[188,190],"well":[189],"extension":[192],"method":[195],"task":[198],"section":[200],"title":[201],"extraction.":[202],"We":[203],"release":[204],"code":[208],"project":[211],"webpage":[212],"enabling":[214],"future":[215],"research":[216],"(http://pdffigures2.allenai.org).":[217]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":8}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2016-06-24T00:00:00"}