{"id":"https://openalex.org/W4403488648","doi":"https://doi.org/10.3233/faia240473","title":"FlowLearn: Evaluating Large Vision-Language Models on Flowchart Understanding","display_name":"FlowLearn: Evaluating Large Vision-Language Models on Flowchart Understanding","publication_year":2024,"publication_date":"2024-10-16","ids":{"openalex":"https://openalex.org/W4403488648","doi":"https://doi.org/10.3233/faia240473"},"language":"en","primary_location":{"id":"doi:10.3233/faia240473","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240473","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240473","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240473","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101205186","display_name":"Huitong Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Huitong Pan","raw_affiliation_strings":["Dept. of Computer and Information Sciences, Temple University, Philadelphia"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer and Information Sciences, Temple University, Philadelphia","institution_ids":["https://openalex.org/I84392919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100360395","display_name":"Qi Zhang","orcid":"https://orcid.org/0000-0003-0235-1333"},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qi Zhang","raw_affiliation_strings":["Dept. of Computer and Information Sciences, Temple University, Philadelphia"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer and Information Sciences, Temple University, Philadelphia","institution_ids":["https://openalex.org/I84392919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089085275","display_name":"Cornelia Caragea","orcid":"https://orcid.org/0000-0002-5664-2163"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cornelia Caragea","raw_affiliation_strings":["Dept. of Computer Science, University of Illinois Chicago"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, University of Illinois Chicago","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057346703","display_name":"Eduard Dragut","orcid":"https://orcid.org/0000-0002-3103-054X"},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eduard Dragut","raw_affiliation_strings":["Dept. of Computer and Information Sciences, Temple University, Philadelphia"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer and Information Sciences, Temple University, Philadelphia","institution_ids":["https://openalex.org/I84392919"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064854962","display_name":"Longin Jan Latecki","orcid":"https://orcid.org/0000-0002-5102-8244"},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Longin Jan Latecki","raw_affiliation_strings":["Dept. of Computer and Information Sciences, Temple University, Philadelphia"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer and Information Sciences, Temple University, Philadelphia","institution_ids":["https://openalex.org/I84392919"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101205186"],"corresponding_institution_ids":["https://openalex.org/I84392919"],"apc_list":null,"apc_paid":null,"fwci":1.3493,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.87635296,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.859499990940094,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.859499990940094,"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":0.8234000205993652,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.7792999744415283,"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/flowchart","display_name":"Flowchart","score":0.7718093991279602},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6067066788673401},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48314327001571655},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.40491506457328796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39366066455841064},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3905373811721802},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2685253620147705},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2518593668937683},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.13152757287025452}],"concepts":[{"id":"https://openalex.org/C72041958","wikidata":"https://www.wikidata.org/wiki/Q185092","display_name":"Flowchart","level":2,"score":0.7718093991279602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6067066788673401},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48314327001571655},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.40491506457328796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39366066455841064},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3905373811721802},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2685253620147705},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2518593668937683},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.13152757287025452}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia240473","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240473","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240473","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia240473","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240473","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240473","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4403488648.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2115906794","https://openalex.org/W2109215547","https://openalex.org/W2131878319","https://openalex.org/W1992202691","https://openalex.org/W2323840003","https://openalex.org/W2188108885","https://openalex.org/W2381593765","https://openalex.org/W2798420800","https://openalex.org/W1199175235","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Flowcharts":[0],"are":[1],"graphical":[2],"tools":[3],"for":[4,63,131,183],"representing":[5],"complex":[6,29],"concepts":[7],"in":[8,83,90,115,134,141,152,165,173],"concise":[9],"visual":[10,64,85],"representations.":[11],"This":[12],"paper":[13],"introduces":[14],"the":[15,23,46,75,111,148,154,161,177],"FlowLearn":[16,27,104,178],"dataset,":[17],"a":[18,54,129],"resource":[19],"tailored":[20],"to":[21,99,109],"enhance":[22],"understanding":[24,86],"of":[25,78,95,113,156],"flowcharts.":[26,34],"contains":[28,38,49],"scientific":[30,36,43,96],"flowcharts":[31,40,51],"and":[32,45,70,127],"simulated":[33,47,144],"The":[35,57,103],"subset":[37,48],"3,858":[39],"sourced":[41],"from":[42],"literature":[44],"10,000":[50],"created":[52],"using":[53],"customizable":[55],"script.":[56],"dataset":[58],"is":[59,107],"enriched":[60],"with":[61],"annotations":[62],"components,":[65],"OCR,":[66],"Mermaid":[67],"code":[68],"representation,":[69],"VQA":[71],"question-answer":[72],"pairs.":[73],"Despite":[74],"proven":[76],"capabilities":[77],"Large":[79],"Vision-Language":[80],"Models":[81],"(LVLMs)":[82],"various":[84],"tasks,":[87],"their":[88],"effectiveness":[89],"decoding":[91],"flowcharts\u2014a":[92],"crucial":[93],"element":[94],"communication\u2014has":[97],"yet":[98],"be":[100],"thoroughly":[101,120],"investigated.":[102],"test":[105],"set":[106],"crafted":[108],"assess":[110],"performance":[112],"LVLMs":[114],"flowchart":[116],"comprehension.":[117],"Our":[118],"study":[119],"evaluates":[121],"state-of-the-art":[122],"LVLMs,":[123],"identifying":[124],"existing":[125],"limitations":[126],"establishing":[128],"foundation":[130],"future":[132],"enhancements":[133],"this":[135],"relatively":[136],"underexplored":[137],"domain.":[138],"For":[139],"instance,":[140],"tasks":[142,175],"involving":[143],"flowcharts,":[145],"GPT-4V":[146],"achieved":[147],"highest":[149,162],"accuracy":[150,163],"(58%)":[151],"counting":[153],"number":[155],"nodes,":[157],"while":[158],"Claude":[159],"recorded":[160],"(83%)":[164],"OCR":[166],"tasks.":[167],"Notably,":[168],"no":[169],"single":[170],"model":[171],"excels":[172],"all":[174],"within":[176],"framework,":[179],"highlighting":[180],"significant":[181],"opportunities":[182],"further":[184],"development.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}
