{"id":"https://openalex.org/W4416945619","doi":"https://doi.org/10.1145/3748522.3779780","title":"Structured Extraction from Business Process Diagrams Using Vision-Language Models","display_name":"Structured Extraction from Business Process Diagrams Using Vision-Language Models","publication_year":2025,"publication_date":"2025-11-27","ids":{"openalex":"https://openalex.org/W4416945619","doi":"https://doi.org/10.1145/3748522.3779780"},"language":null,"primary_location":{"id":"doi:10.1145/3748522.3779780","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748522.3779780","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3748522.3779780","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033721368","display_name":"Pritam Deka","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Deka, Pritam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5007017103","display_name":"Barry Devereux","orcid":"https://orcid.org/0000-0003-2128-8632"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Devereux, Barry","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5033721368"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.51055652,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"934","last_page":"943"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.8651999831199646,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.8651999831199646,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.012299999594688416,"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/T13287","display_name":"Robotic Process Automation Applications","score":0.008500000461935997,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/business-process-model-and-notation","display_name":"Business Process Model and Notation","score":0.7069000005722046},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.6424999833106995},{"id":"https://openalex.org/keywords/json","display_name":"JSON","score":0.5695000290870667},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5260000228881836},{"id":"https://openalex.org/keywords/business-process-modeling","display_name":"Business process modeling","score":0.4959999918937683},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.46549999713897705},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.4625999927520752},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.4555000066757202},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4528999924659729}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8065000176429749},{"id":"https://openalex.org/C179299601","wikidata":"https://www.wikidata.org/wiki/Q1017605","display_name":"Business Process Model and Notation","level":5,"score":0.7069000005722046},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6424999833106995},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.5695000290870667},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5260000228881836},{"id":"https://openalex.org/C207505557","wikidata":"https://www.wikidata.org/wiki/Q4374012","display_name":"Business process modeling","level":4,"score":0.4959999918937683},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.46549999713897705},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.4625999927520752},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.4555000066757202},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4528999924659729},{"id":"https://openalex.org/C76956256","wikidata":"https://www.wikidata.org/wiki/Q27610560","display_name":"Process modeling","level":3,"score":0.4481000006198883},{"id":"https://openalex.org/C85345410","wikidata":"https://www.wikidata.org/wiki/Q851587","display_name":"Business process","level":3,"score":0.439300000667572},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.428600013256073},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C145644426","wikidata":"https://www.wikidata.org/wiki/Q169411","display_name":"Unified Modeling Language","level":3,"score":0.39959999918937683},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3767000138759613},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3677999973297119},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3677999973297119},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35580000281333923},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C11066294","wikidata":"https://www.wikidata.org/wiki/Q1518244","display_name":"Business rule","level":4,"score":0.34439998865127563},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33559998869895935},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31150001287460327},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C40077939","wikidata":"https://www.wikidata.org/wiki/Q2336004","display_name":"Semi-structured data","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.2793000042438507},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.2768000066280365},{"id":"https://openalex.org/C72041958","wikidata":"https://www.wikidata.org/wiki/Q185092","display_name":"Flowchart","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C64219723","wikidata":"https://www.wikidata.org/wiki/Q423262","display_name":"Activity diagram","level":4,"score":0.2678000032901764},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C40713593","wikidata":"https://www.wikidata.org/wiki/Q16342","display_name":"XML Schema (W3C)","level":5,"score":0.2556999921798706},{"id":"https://openalex.org/C93453677","wikidata":"https://www.wikidata.org/wiki/Q1017580","display_name":"Business process discovery","level":5,"score":0.25519999861717224}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3748522.3779780","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748522.3779780","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.22448","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.22448","pdf_url":"https://arxiv.org/pdf/2511.22448","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.22448","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.22448","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1145/3748522.3779780","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748522.3779780","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Business":[0],"Process":[1],"Model":[2],"and":[3,76,110,135],"Notation":[4],"(BPMN)":[5],"is":[6,119],"a":[7,40,140],"widely":[8],"adopted":[9],"standard":[10],"for":[11,32,73,121],"representing":[12],"complex":[13],"business":[14],"workflows.":[15],"While":[16],"BPMN":[17,53],"diagrams":[18,54],"are":[19,104],"often":[20],"exchanged":[21],"as":[22],"visual":[23],"images,":[24,57],"existing":[25],"methods":[26,134],"primarily":[27],"rely":[28],"on":[29,146],"XML":[30,90],"representations":[31,51],"computational":[33],"analysis.":[34],"In":[35,124],"this":[36],"work,":[37],"we":[38,126],"present":[39],"pipeline":[41],"that":[42],"leverages":[43],"Vision-Language":[44],"Models":[45],"(VLMs)":[46],"to":[47],"extract":[48],"structured":[49],"JSON":[50],"of":[52,131,143],"directly":[55],"from":[56,87],"without":[58],"requiring":[59],"source":[60,89,102],"model":[61,147],"files":[62,103],"or":[63],"textual":[64,74],"annotations.":[65],"We":[66,106],"also":[67],"incorporate":[68],"optical":[69],"character":[70],"recognition":[71],"(OCR)":[72],"enrichment":[75,133],"evaluate":[77],"the":[78,88],"generated":[79],"element":[80],"lists":[81],"against":[82],"ground":[83],"truth":[84],"data":[85],"derived":[86],"files.":[91],"Our":[92],"approach":[93],"enables":[94],"robust":[95],"component":[96],"extraction":[97],"in":[98,114],"scenarios":[99],"where":[100],"original":[101],"unavailable.":[105],"benchmark":[107],"multiple":[108],"VLMs":[109],"observe":[111],"performance":[112],"improvements":[113],"several":[115],"models":[116],"when":[117],"OCR":[118],"used":[120],"text":[122],"enrichment.":[123],"addition,":[125],"conducted":[127],"extensive":[128],"statistical":[129],"analyses":[130],"OCR-based":[132],"prompt":[136],"ablation":[137],"studies,":[138],"providing":[139],"clearer":[141],"understanding":[142],"their":[144],"impact":[145],"performance.":[148]},"counts_by_year":[],"updated_date":"2026-06-10T14:10:52.464848","created_date":"2025-12-03T00:00:00"}