{"id":"https://openalex.org/W4226136952","doi":"https://doi.org/10.1007/978-3-031-04083-2_5","title":"CLEVR-X: A Visual Reasoning Dataset for\u00a0Natural Language Explanations","display_name":"CLEVR-X: A Visual Reasoning Dataset for\u00a0Natural Language Explanations","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4226136952","doi":"https://doi.org/10.1007/978-3-031-04083-2_5"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-04083-2_5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-04083-2_5","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-04083-2_5.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-04083-2_5.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041381909","display_name":"Leonard Salewski","orcid":"https://orcid.org/0000-0001-8531-3011"},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Leonard Salewski","raw_affiliation_strings":["University of T\u00fcbingen, T\u00fcbingen, Germany"],"raw_orcid":"https://orcid.org/0000-0001-8531-3011","affiliations":[{"raw_affiliation_string":"University of T\u00fcbingen, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001366802","display_name":"A. Sophia Koepke","orcid":"https://orcid.org/0000-0002-5807-0576"},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"A. Sophia Koepke","raw_affiliation_strings":["University of T\u00fcbingen, T\u00fcbingen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-5807-0576","affiliations":[{"raw_affiliation_string":"University of T\u00fcbingen, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036948222","display_name":"Hendrik P. A. Lensch","orcid":"https://orcid.org/0000-0003-3616-8668"},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hendrik P. A. Lensch","raw_affiliation_strings":["University of T\u00fcbingen, T\u00fcbingen, Germany"],"raw_orcid":"https://orcid.org/0000-0003-3616-8668","affiliations":[{"raw_affiliation_string":"University of T\u00fcbingen, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040372929","display_name":"Zeynep Akata","orcid":"https://orcid.org/0000-0002-1432-7747"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]},{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]},{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zeynep Akata","raw_affiliation_strings":["MPI for Informatics, Saarbr\u00fccken, Germany","MPI for Intelligent Systems, T\u00fcbingen, Germany","University of T\u00fcbingen, T\u00fcbingen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-1432-7747","affiliations":[{"raw_affiliation_string":"MPI for Informatics, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]},{"raw_affiliation_string":"MPI for Intelligent Systems, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I4210135521"]},{"raw_affiliation_string":"University of T\u00fcbingen, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041381909"],"corresponding_institution_ids":["https://openalex.org/I8087733"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":1.294,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.87373324,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"69","last_page":"88"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9817000031471252,"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/T10028","display_name":"Topic Modeling","score":0.9814000129699707,"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/computer-science","display_name":"Computer science","score":0.8277764916419983},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7682698369026184},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.7104264497756958},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6855117082595825},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6472048163414001},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6401050090789795},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.6029618978500366},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4979231357574463},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4459211230278015},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.4360211193561554},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.4319417178630829},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3762877881526947},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3337402641773224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8277764916419983},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7682698369026184},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.7104264497756958},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6855117082595825},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6472048163414001},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6401050090789795},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.6029618978500366},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4979231357574463},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4459211230278015},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.4360211193561554},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.4319417178630829},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3762877881526947},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3337402641773224},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-031-04083-2_5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-04083-2_5","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-04083-2_5.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:2204.02380","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.02380","pdf_url":"https://arxiv.org/pdf/2204.02380","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"}],"best_oa_location":{"id":"doi:10.1007/978-3-031-04083-2_5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-04083-2_5","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-04083-2_5.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1562512020","display_name":null,"funder_award_id":"206/4-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G233922387","display_name":null,"funder_award_id":"EXC number 2064/1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G3089048743","display_name":null,"funder_award_id":"project number 390727645).","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7907426250","display_name":"EXC 2064: Maschinelles Lernen: Neue Perspektiven f\u00fcr die Wissenschaft","funder_award_id":"390727645","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G817300853","display_name":null,"funder_award_id":"SFB1233","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4226136952.pdf","grobid_xml":"https://content.openalex.org/works/W4226136952.grobid-xml"},"referenced_works_count":70,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1603565383","https://openalex.org/W1787224781","https://openalex.org/W1849277567","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2108598243","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2194775991","https://openalex.org/W2560730294","https://openalex.org/W2561715562","https://openalex.org/W2563399268","https://openalex.org/W2606462007","https://openalex.org/W2745461083","https://openalex.org/W2760103357","https://openalex.org/W2776207810","https://openalex.org/W2778748054","https://openalex.org/W2785578203","https://openalex.org/W2788527488","https://openalex.org/W2883512601","https://openalex.org/W2885138528","https://openalex.org/W2907143950","https://openalex.org/W2912371042","https://openalex.org/W2920847544","https://openalex.org/W2950188512","https://openalex.org/W2950297087","https://openalex.org/W2951936329","https://openalex.org/W2962716332","https://openalex.org/W2962749469","https://openalex.org/W2962851944","https://openalex.org/W2962858109","https://openalex.org/W2963191264","https://openalex.org/W2963260436","https://openalex.org/W2963383024","https://openalex.org/W2963518342","https://openalex.org/W2963609017","https://openalex.org/W2963644680","https://openalex.org/W2963656855","https://openalex.org/W2963847595","https://openalex.org/W2963890019","https://openalex.org/W2963954913","https://openalex.org/W2963991868","https://openalex.org/W2969679616","https://openalex.org/W2973009097","https://openalex.org/W2981731882","https://openalex.org/W2988157455","https://openalex.org/W3010535384","https://openalex.org/W3015608264","https://openalex.org/W3101609372","https://openalex.org/W3105391665","https://openalex.org/W3161801106","https://openalex.org/W3212053370","https://openalex.org/W4214634898","https://openalex.org/W4287322030","https://openalex.org/W4287552728","https://openalex.org/W4287645701","https://openalex.org/W4287995219","https://openalex.org/W4288091250","https://openalex.org/W4288286281","https://openalex.org/W4297749157","https://openalex.org/W4300235091","https://openalex.org/W4300737232","https://openalex.org/W4306982992","https://openalex.org/W4312407344","https://openalex.org/W4394639892","https://openalex.org/W6634089356","https://openalex.org/W6676167930","https://openalex.org/W6819490522"],"related_works":["https://openalex.org/W3034800807","https://openalex.org/W3035130722","https://openalex.org/W4287758468","https://openalex.org/W4310731959","https://openalex.org/W3113264705","https://openalex.org/W2964061310","https://openalex.org/W2963477107","https://openalex.org/W2231285690","https://openalex.org/W3093385053","https://openalex.org/W2386843486"],"abstract_inverted_index":{"Abstract":[0],"Providing":[1],"explanations":[2,29,60,73,101,119,161],"in":[3,15,51,102,120],"the":[4,23,34,40,52,65,71,78,99,121,130,140,153,163],"context":[5,122],"of":[6,25,123,139,155,159,165],"Visual":[7],"Question":[8],"Answering":[9],"(VQA)":[10],"presents":[11],"a":[12,88,93,136],"fundamental":[13],"problem":[14],"machine":[16],"learning.":[17],"To":[18],"obtain":[19],"detailed":[20,137],"insights":[21],"into":[22],"process":[24],"generating":[26,116],"natural":[27,44,117,166],"language":[28,45,118,167],"for":[30,115,144],"VQA,":[31],"we":[32,134,151],"introduce":[33],"large-scale":[35],"CLEVR-X":[36,55,72,131,172],"dataset":[37,42,105,173],"that":[38,83,98],"extends":[39],"CLEVR":[41,53],"with":[43],"explanations.":[46],"For":[47],"each":[48],"image-question":[49],"pair":[50],"dataset,":[54],"contains":[56],"multiple":[57],"structured":[58],"textual":[59],"which":[61],"are":[62,74,106],"derived":[63],"from":[64],"original":[66],"scene":[67],"graphs.":[68],"By":[69],"construction,":[70],"correct":[75],"and":[76,80,109,147],"describe":[77],"reasoning":[79],"visual":[81],"information":[82],"is":[84,174],"necessary":[85],"to":[86,96],"answer":[87,148],"given":[89],"question.":[90],"We":[91,111],"conducted":[92],"user":[94],"study":[95,152],"confirm":[97],"ground-truth":[100,160],"our":[103],"proposed":[104],"indeed":[107],"complete":[108],"relevant.":[110],"present":[112],"baseline":[113],"results":[114],"VQA":[124],"using":[125,156],"two":[126],"state-of-the-art":[127],"frameworks":[128],"on":[129,162],"dataset.":[132],"Furthermore,":[133],"provide":[135],"analysis":[138],"explanation":[141],"generation":[142,168],"quality":[143],"different":[145,157],"question":[146],"types.":[149],"Additionally,":[150],"influence":[154],"numbers":[158],"convergence":[164],"(NLG)":[169],"metrics.":[170],"The":[171],"publicly":[175],"available":[176],"at":[177],"https://github.com/ExplainableML/CLEVR-X":[178],".":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}