{"id":"https://openalex.org/W4415251845","doi":"https://doi.org/10.1109/wacv61042.2026.00120","title":"CommonForms: A Large, Diverse Dataset for Form Field Detection","display_name":"CommonForms: A Large, Diverse Dataset for Form Field Detection","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4415251845","doi":"https://doi.org/10.1109/wacv61042.2026.00120"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.16506","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034286014","display_name":"Joe Barrow","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Joe Barrow","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5034286014"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00348432,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1170","last_page":"1179"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11006","display_name":"BIM and Construction Integration","score":0.9646000266075134,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11006","display_name":"BIM and Construction Integration","score":0.9646000266075134,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11159","display_name":"Manufacturing Process and Optimization","score":0.9261999726295471,"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"}},{"id":"https://openalex.org/T12190","display_name":"Innovations in Concrete and Construction Materials","score":0.9175999760627747,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/field","display_name":"Field (mathematics)","score":0.6694999933242798},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5756999850273132},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.512499988079071},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4738999903202057},{"id":"https://openalex.org/keywords/signature","display_name":"Signature (topology)","score":0.46860000491142273},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4268999993801117},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.420199990272522}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6798999905586243},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.6694999933242798},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5756999850273132},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.512499988079071},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49939998984336853},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4738999903202057},{"id":"https://openalex.org/C2779696439","wikidata":"https://www.wikidata.org/wiki/Q7512811","display_name":"Signature (topology)","level":2,"score":0.46860000491142273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4408000111579895},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4268999993801117},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.420199990272522},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3783000111579895},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3377000093460083},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.16506","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.16506","pdf_url":"https://arxiv.org/pdf/2509.16506","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.16506","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.16506","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.16506","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.16506","pdf_url":"https://arxiv.org/pdf/2509.16506","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,216],"paper":[1,120],"introduces":[2],"CommonForms,":[3],"a":[4,26,69,88,122,133],"large":[5],"dataset":[6,42,71,86,224],"for":[7,159,226],"form":[8,16,39,125,161,196,227],"field":[9,17,126,162,228],"detection.":[10],"It":[11],"casts":[12],"the":[13,29,61,85,98,104,116,139,166,190,199,221,233],"problem":[14],"of":[15,25,38,72,91,97,115,124,193],"detection":[18],"as":[19,230,232],"object":[20],"detection:":[21],"given":[22],"an":[23],"image":[24],"page,":[27],"predict":[28,207],"location":[30],"and":[31,93,102,129,164,213,240],"type":[32],"(Text":[33],"Input,":[34],"Choice":[35],"Button,":[36],"Signature)":[37],"fields.":[40,215],"The":[41,237],"is":[43,64],"constructed":[44],"by":[45],"filtering":[46,62],"Common":[47,181],"Crawl":[48],"to":[49,66,149,211,218],"find":[50],"PDFs":[51,175],"that":[52,76,84,154,165,176,187],"have":[53,77,177],"fillable":[54,178],"elements.":[55],"Starting":[56],"with":[57],"8":[58],"million":[59],"documents,":[60],"process":[63,168],"used":[65],"arrive":[67],"at":[68],"final":[70],"roughly":[73],"59k":[74],"documents":[75],"more":[78,112],"than":[79,113,147],"450k":[80],"pages.":[81],"Analysis":[82],"shows":[83,186],"contains":[87],"diverse":[89],"mixture":[90],"languages":[92],"domains;":[94],"one":[95],"third":[96],"pages":[99],"are":[100,157,242],"non-English,":[101],"among":[103],"14":[105],"classified":[106],"domains,":[107],"no":[108],"domain":[109],"makes":[110],"up":[111],"25%":[114],"dataset.In":[117],"addition,":[118],"this":[119],"presents":[121],"family":[123],"detectors,":[127],"FFDNet-Small":[128],"FFDNet-Large,":[130],"which":[131],"attain":[132],"very":[134],"high":[135],"average":[136],"precision":[137],"on":[138],"CommonForms":[140],"test":[141],"set.":[142],"Each":[143],"model":[144],"cost":[145],"less":[146],"$500":[148],"train.":[150],"Ablation":[151],"results":[152],"show":[153],"high-resolution":[155],"inputs":[156],"crucial":[158],"high-quality":[160],"detection,":[163,229],"cleaning":[167],"improves":[169],"data":[170],"efficiency":[171],"over":[172],"using":[173],"all":[174],"fields":[179],"in":[180,209],"Crawl.":[182],"A":[183],"qualitative":[184],"analysis":[185],"they":[188],"outperform":[189],"2025":[191],"version":[192],"Adobe":[194],"Acrobat\u2019s":[195],"preparation.":[197],"Unlike":[198],"most":[200],"popular":[201],"commercially":[202],"available":[203,243],"solutions,":[204],"FFDNet":[205],"can":[206],"checkboxes":[208],"addition":[210],"text":[212],"signature":[214],"is,":[217],"our":[219],"knowledge,":[220],"first":[222,234],"large-scale":[223],"released":[225],"well":[231],"open-source":[235],"models.":[236],"dataset,":[238],"models,":[239],"code":[241],"at:":[244],"https://github.com/jbarrow/commonforms.":[245]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-16T00:00:00"}