{"id":"https://openalex.org/W6968252874","doi":"https://doi.org/10.5281/zenodo.14907473","title":"PatFigVQA Dataset - Patent Figure Visual Question Answering Dataset","display_name":"PatFigVQA Dataset - Patent Figure Visual Question Answering Dataset","publication_year":2025,"publication_date":"2025-02-21","ids":{"openalex":"https://openalex.org/W6968252874","doi":"https://doi.org/10.5281/zenodo.14907473"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14907473","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14907473","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.14907473","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Awale, Sushil","orcid":"https://orcid.org/0000-0003-2575-0134"},"institutions":[{"id":"https://openalex.org/I2802635041","display_name":"Technische Informationsbibliothek (TIB)","ror":"https://ror.org/04aj4c181","country_code":"DE","type":"archive","lineage":["https://openalex.org/I2802635041","https://openalex.org/I315704651"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Awale, Sushil","raw_affiliation_strings":["Technische Informationsbibliothek (TIB)"],"raw_orcid":"https://orcid.org/0000-0003-2575-0134","affiliations":[{"raw_affiliation_string":"Technische Informationsbibliothek (TIB)","institution_ids":["https://openalex.org/I2802635041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"M\u00fcller-Budack, Eric","orcid":"https://orcid.org/0000-0002-6802-1241"},"institutions":[{"id":"https://openalex.org/I2802635041","display_name":"Technische Informationsbibliothek (TIB)","ror":"https://ror.org/04aj4c181","country_code":"DE","type":"archive","lineage":["https://openalex.org/I2802635041","https://openalex.org/I315704651"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"M\u00fcller-Budack, Eric","raw_affiliation_strings":["Technische Informationsbibliothek (TIB)"],"raw_orcid":"https://orcid.org/0000-0002-6802-1241","affiliations":[{"raw_affiliation_string":"Technische Informationsbibliothek (TIB)","institution_ids":["https://openalex.org/I2802635041"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ewerth, Ralph","orcid":"https://orcid.org/0000-0003-0918-6297"},"institutions":[{"id":"https://openalex.org/I2802635041","display_name":"Technische Informationsbibliothek (TIB)","ror":"https://ror.org/04aj4c181","country_code":"DE","type":"archive","lineage":["https://openalex.org/I2802635041","https://openalex.org/I315704651"]},{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ewerth, Ralph","raw_affiliation_strings":["Technische Informationsbibliothek (TIB)","L3S Research Center"],"raw_orcid":"https://orcid.org/0000-0003-0918-6297","affiliations":[{"raw_affiliation_string":"Technische Informationsbibliothek (TIB)","institution_ids":["https://openalex.org/I2802635041"]},{"raw_affiliation_string":"L3S Research Center","institution_ids":["https://openalex.org/I4210136150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2802635041"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.7465000152587891},{"id":"https://openalex.org/keywords/lambda","display_name":"Lambda","score":0.5734999775886536},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.515999972820282},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4797999858856201},{"id":"https://openalex.org/keywords/data-source","display_name":"Data source","score":0.45840001106262207},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.40869998931884766}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7465000152587891},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6658999919891357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5861999988555908},{"id":"https://openalex.org/C2778113609","wikidata":"https://www.wikidata.org/wiki/Q10897","display_name":"Lambda","level":2,"score":0.5734999775886536},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5257999897003174},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.515999972820282},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5094000101089478},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4797999858856201},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.45840001106262207},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.40869998931884766},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.35199999809265137},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3181999921798706},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3109000027179718},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.3021000027656555},{"id":"https://openalex.org/C171730128","wikidata":"https://www.wikidata.org/wiki/Q5227290","display_name":"Data file","level":2,"score":0.29100000858306885}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14907473","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14907473","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.14907473","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14907473","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"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":{"Dataset":[0],"Summary":[1],"The":[2,21,48,67,82,163,242],"PatFigVQA":[3,49],"dataset":[4,22,50,55,68,83,200,249,258],"is":[5,23,51,59,69,84,166,173,259],"introduced":[6],"in":[7,34,86,123,134],"the":[8,120,129,135,139,168],"paper":[9],"Patent":[10],"Figure":[11],"Classification":[12],"using":[13,167],"Large":[14,30],"Vision-language":[15,31],"Models":[16,32],"accepted":[17],"at":[18,253],"ECIR":[19],"2025.":[20],"designed":[24],"specifically":[25],"for":[26,61,89,128,138],"fine-tuning":[27],"and":[28,45,65,78,91,158],"evaluating":[29],"(LVLMs)":[33],"few-shot":[35],"learning":[36],"setting":[37],"across":[38],"multiple":[39,147],"aspects,":[40],"including":[41],"type,":[42],"projection,":[43],"objects":[44],"USPC":[46],"class.":[47],"used":[52,245],"alongside":[53],"another":[54],"called":[56],"PatFigCLS,":[57],"which":[58],"intended":[60],"patent":[62,102,136],"figure":[63,103,124,137],"classification":[64],"evaluation.":[66],"sourced":[70],"from":[71,179,183,192],"two":[72],"exisiting":[73],"datasets:":[74],"Extended":[75],"CLEF-IP":[76],"2011,":[77],"DeepPatent2":[79],"Data":[80,95,142],"Format":[81],"stored":[85],".tar":[87],"files":[88],"fast":[90],"efficient":[92],"read":[93],"access.":[94],"Fields":[96],"__key__:":[97],"unique":[98],"sample":[99],"id":[100],"image.png:":[101],"file":[104],"task.txt:":[105],"type":[106],"of":[107],"question":[108,117,130],"(e.g.":[109],"binary,":[110],"multiple-choice":[111],"or":[112],"open-ended)":[113],"question.txt:":[114],"natural":[115],"language":[116],"asking":[118],"about":[119],"concept":[121,132],"depicted":[122,133],"answer.txt:":[125],"textual":[126],"answer":[127],"concept.txt:":[131],"given":[140],"aspect":[141],"Splits":[143],"For":[144],"each":[145],"aspect,":[146],"data":[148],"splits":[149],"exist:":[150],"train_9,":[151],"train_18,":[152],"train_27,":[153],"train_54,":[154],"train_81,":[155],"train_150,":[156],"val":[157],"test.":[159],"How":[160],"to":[161,246],"Use":[162],"recommended":[164],"approach":[165],"Python":[169],"library":[170],"`webdataset`.":[171],"Below":[172],"an":[174],"example":[175],"code.":[176],"import":[177,181,185,188,194],"io":[178],"PIL":[180],"Image":[182],"torchvision.transforms":[184],"Compose,":[186],"ToTensor":[187],"webdataset":[189],"as":[190],"wds":[191],"braceexpand":[193,195],"def":[196],"transform(image):":[197],"return":[198],"Compose([ToTensor()])(image)":[199],"=":[201,238],"(":[202],"wds.WebDataset(":[203],"braceexpand('PatFigVQA/object/train_150/shard-{000000..000042}.tar'),":[204],"shardshuffle=1000,":[205],")":[206,215,235,236],".shuffle(1000)":[207],".to_tuple(":[208],"'__key__',":[209],"'image.png',":[210],"'concept.txt',":[211],"'task.txt',":[212],"'question.txt',":[213],"'answer.txt',":[214],".map_tuple(":[216],"lambda":[217,220,223,226,229,232],"key:":[218],"key,":[219],"image:":[221],"transform(Image.open(io.BytesIO(image))),":[222],"concept:":[224],"concept.decode('utf-8'),":[225],"task:":[227],"task.decode('utf-8'),":[228],"question:":[230],"question.decode('utf-8'),":[231],"answer:":[233],"answer.decode('utf-8'),":[234],"dataloder":[237],"wds.WebLoader(dataset)":[239],"Source":[240],"Code":[241],"source":[243],"code":[244],"produce":[247],"this":[248],"can":[250],"be":[251],"found":[252],"https://github.com/TIBHannover/patent-figure-classification":[254],"Licensing":[255],"Information":[256],"PatFigCLS":[257],"released":[260],"under":[261],"GNU":[262],"General":[263],"Public":[264],"License":[265],"v3.0.":[266]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}