{"id":"https://openalex.org/W6892994129","doi":"https://doi.org/10.5281/zenodo.14905551","title":"PatFigCLS Dataset - Patent Figure Classification Dataset","display_name":"PatFigCLS Dataset - Patent Figure Classification Dataset","publication_year":2025,"publication_date":"2025-02-21","ids":{"openalex":"https://openalex.org/W6892994129","doi":"https://doi.org/10.5281/zenodo.14905551"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14905551","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14905551","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.14905551","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":0.7817999720573425},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5314000248908997},{"id":"https://openalex.org/keywords/mit-license","display_name":"MIT License","score":0.48350000381469727},{"id":"https://openalex.org/keywords/license","display_name":"License","score":0.4381999969482422},{"id":"https://openalex.org/keywords/data-source","display_name":"Data source","score":0.4237000048160553},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.39899998903274536},{"id":"https://openalex.org/keywords/data-file","display_name":"Data file","score":0.31859999895095825}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7817999720573425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6597999930381775},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5314000248908997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.516700029373169},{"id":"https://openalex.org/C174183944","wikidata":"https://www.wikidata.org/wiki/Q334661","display_name":"MIT License","level":3,"score":0.48350000381469727},{"id":"https://openalex.org/C2780560020","wikidata":"https://www.wikidata.org/wiki/Q79719","display_name":"License","level":2,"score":0.4381999969482422},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42969998717308044},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.4237000048160553},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4187000095844269},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.39899998903274536},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33009999990463257},{"id":"https://openalex.org/C171730128","wikidata":"https://www.wikidata.org/wiki/Q5227290","display_name":"Data file","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C2988504005","wikidata":"https://www.wikidata.org/wiki/Q379942","display_name":"Document image processing","level":4,"score":0.31029999256134033},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C2778113609","wikidata":"https://www.wikidata.org/wiki/Q10897","display_name":"Lambda","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.266400009393692}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14905551","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14905551","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.14905551","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14905551","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":[2,21,42,73,88,131,196],"PatFigCLS":[3,43,211],"dataset":[4,22,44,49,74,89,168,203,212],"is":[5,23,45,53,75,90,134,141,213],"introduced":[6],"in":[7,63,92],"the":[8,136],"paper":[9],"Patent":[10],"Figure":[11],"Classification":[12],"using":[13,135],"Large":[14,59],"Vision-language":[15,60],"Models":[16,61],"accepted":[17],"at":[18,207],"ECIR":[19],"2025.":[20],"designed":[24],"specifically":[25],"for":[26,55,67,95],"patent":[27,68,108],"figure":[28,69,109],"classification":[29,112,118],"and":[30,39,57,84,97,126],"evaluation":[31],"across":[32],"multiple":[33],"aspects,":[34],"including":[35],"type,":[36],"projection,":[37],"objects":[38],"USPC":[40],"class.":[41],"used":[46,199],"alongside":[47],"another":[48],"called":[50],"PatFigVQA,":[51],"which":[52],"intended":[54],"fine-tuning":[56],"evaluating":[58],"(LVLMs)":[62],"few-shot":[64],"learning":[65],"setting":[66],"visual":[70],"question":[71],"answering.":[72],"sourced":[76],"from":[77,147,151,160],"two":[78],"exisiting":[79],"datasets:":[80],"Extended":[81],"CLEF-IP":[82],"2011,":[83],"DeepPatent2":[85],"Data":[86,101,114],"Format":[87],"stored":[91],".tar":[93],"files":[94],"fast":[96],"efficient":[98],"read":[99],"access.":[100],"Fields":[102],"__key__:":[103],"unique":[104],"sample":[105],"id":[106],"image.png:":[107],"file":[110],"label.txt:":[111],"label":[113],"Splits":[115],"For":[116],"each":[117],"aspect,":[119],"three":[120],"data":[121],"splits":[122],"exist:":[123],"`train_150`,":[124],"`val`":[125],"`test`.":[127],"How":[128],"to":[129,200],"Use":[130],"recommended":[132],"approach":[133],"Python":[137],"library":[138],"`webdataset`.":[139],"Below":[140],"an":[142],"example":[143],"code.":[144],"import":[145,149,153,156,162],"io":[146],"PIL":[148],"Image":[150],"torchvision.transforms":[152],"Compose,":[154],"ToTensor":[155],"webdataset":[157],"as":[158],"wds":[159],"braceexpand":[161,163],"def":[164],"transform(image):":[165],"return":[166],"Compose([ToTensor()])(image)":[167],"=":[169,192],"(":[170],"wds.WebDataset(":[171],"braceexpand('PatFigCLS/object/train_150/shard-{000000..000042}.tar'),":[172],"shardshuffle=1000":[173],")":[174,189,190],".shuffle(1000)":[175],".to_tuple('__key__',":[176],"'image.png',":[177],"'label.txt')":[178],".map_tuple(":[179],"lambda":[180,183,186],"key:":[181],"key,":[182],"image:":[184],"transform(Image.open(io.BytesIO(image))),":[185],"label:":[187],"label.decode('utf-8'),":[188],"dataloder":[191],"wds.WebLoader(dataset)":[193],"Source":[194],"Code":[195],"source":[197],"code":[198],"produce":[201],"this":[202],"can":[204],"be":[205],"found":[206],"https://github.com/TIBHannover/patent-figure-classification":[208],"Licensing":[209],"Information":[210],"released":[214],"under":[215],"GNU":[216],"General":[217],"Public":[218],"License":[219],"v3.0.":[220]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}
