{"id":"https://openalex.org/W3156624167","doi":"https://doi.org/10.3390/s21092911","title":"Vision\u2013Language\u2013Knowledge Co-Embedding for Visual Commonsense Reasoning","display_name":"Vision\u2013Language\u2013Knowledge Co-Embedding for Visual Commonsense Reasoning","publication_year":2021,"publication_date":"2021-04-21","ids":{"openalex":"https://openalex.org/W3156624167","doi":"https://doi.org/10.3390/s21092911","mag":"3156624167","pmid":"https://pubmed.ncbi.nlm.nih.gov/33919196"},"language":"en","primary_location":{"id":"doi:10.3390/s21092911","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s21092911","pdf_url":"https://www.mdpi.com/1424-8220/21/9/2911/pdf?version=1619000920","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/21/9/2911/pdf?version=1619000920","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079908074","display_name":"JaeYun Lee","orcid":"https://orcid.org/0000-0003-4913-3691"},"institutions":[{"id":"https://openalex.org/I28615091","display_name":"Kyonggi University","ror":"https://ror.org/032xf8h46","country_code":"KR","type":"education","lineage":["https://openalex.org/I28615091"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"JaeYun Lee","raw_affiliation_strings":["Department of Computer Science, Kyonggi University, Suwon-si 16227, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Kyonggi University, Suwon-si 16227, Korea","institution_ids":["https://openalex.org/I28615091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066676430","display_name":"Incheol Kim","orcid":"https://orcid.org/0000-0002-5754-133X"},"institutions":[{"id":"https://openalex.org/I28615091","display_name":"Kyonggi University","ror":"https://ror.org/032xf8h46","country_code":"KR","type":"education","lineage":["https://openalex.org/I28615091"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Incheol Kim","raw_affiliation_strings":["Department of Computer Science, Kyonggi University, Suwon-si 16227, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Kyonggi University, Suwon-si 16227, Korea","institution_ids":["https://openalex.org/I28615091"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5066676430"],"corresponding_institution_ids":["https://openalex.org/I28615091"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":0.6782,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.70577272,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"21","issue":"9","first_page":"2911","last_page":"2911"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9944000244140625,"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":0.9865000247955322,"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/commonsense-knowledge","display_name":"Commonsense knowledge","score":0.8292841911315918},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7871395349502563},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7814874649047852},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7363046407699585},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.7008176445960999},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6443324089050293},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.5985248684883118},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5848573446273804},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.551559567451477},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5381859540939331},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.5109997987747192},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4447574019432068},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.42285069823265076},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34414803981781006},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.20680126547813416}],"concepts":[{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.8292841911315918},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7871395349502563},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7814874649047852},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7363046407699585},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.7008176445960999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6443324089050293},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.5985248684883118},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5848573446273804},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.551559567451477},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5381859540939331},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.5109997987747192},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4447574019432068},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.42285069823265076},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34414803981781006},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.20680126547813416}],"mesh":[{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011340","descriptor_name":"Problem Solving","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011340","descriptor_name":"Problem Solving","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011340","descriptor_name":"Problem Solving","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.3390/s21092911","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s21092911","pdf_url":"https://www.mdpi.com/1424-8220/21/9/2911/pdf?version=1619000920","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:33919196","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33919196","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:doaj.org/article:ce0d717431c54abd8eac7944752ce3d7","is_oa":true,"landing_page_url":"https://doaj.org/article/ce0d717431c54abd8eac7944752ce3d7","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 21, Iss 9, p 2911 (2021)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/21/9/2911/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s21092911","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors; Volume 21; Issue 9; Pages: 2911","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:8122639","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8122639","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s21092911","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s21092911","pdf_url":"https://www.mdpi.com/1424-8220/21/9/2911/pdf?version=1619000920","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3156624167.pdf","grobid_xml":"https://content.openalex.org/works/W3156624167.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W102708294","https://openalex.org/W639708223","https://openalex.org/W1498436455","https://openalex.org/W2016089260","https://openalex.org/W2080133951","https://openalex.org/W2094728533","https://openalex.org/W2147800946","https://openalex.org/W2154851992","https://openalex.org/W2194775991","https://openalex.org/W2438044634","https://openalex.org/W2519887557","https://openalex.org/W2563399268","https://openalex.org/W2768661419","https://openalex.org/W2804243936","https://openalex.org/W2947312908","https://openalex.org/W2951210508","https://openalex.org/W2952402334","https://openalex.org/W2962756421","https://openalex.org/W2963115613","https://openalex.org/W2963150697","https://openalex.org/W2964303913","https://openalex.org/W2966317026","https://openalex.org/W2966715458","https://openalex.org/W2967593235","https://openalex.org/W2968124245","https://openalex.org/W2970641692","https://openalex.org/W2970869018","https://openalex.org/W2970986510","https://openalex.org/W2998356391","https://openalex.org/W3000571196","https://openalex.org/W3034578524","https://openalex.org/W3104097132","https://openalex.org/W3107069568","https://openalex.org/W3108144224","https://openalex.org/W3172675210","https://openalex.org/W3174690404","https://openalex.org/W4249013746","https://openalex.org/W6604189946","https://openalex.org/W6752083267"],"related_works":["https://openalex.org/W4313191056","https://openalex.org/W2928107702","https://openalex.org/W3190822525","https://openalex.org/W4320086306","https://openalex.org/W3091195047","https://openalex.org/W2943368643","https://openalex.org/W4327927978","https://openalex.org/W181868102","https://openalex.org/W2968908603","https://openalex.org/W3175270222"],"abstract_inverted_index":{"Visual":[0],"commonsense":[1,41],"reasoning":[2],"is":[3],"an":[4,27,75],"intelligent":[5],"task":[6],"performed":[7],"to":[8,14,54,71,88,137,149],"decide":[9],"the":[10,19,24,44,49,72,85,90,120,124,127,131,139,153,164,171],"most":[11],"appropriate":[12],"answer":[13,25,89],"a":[15,29,60,96,114],"question":[16,73],"while":[17],"providing":[18],"rationale":[20],"or":[21],"reason":[22],"for":[23],"when":[26],"image,":[28],"natural":[30,107,156],"language":[31,108,157],"question,":[32],"and":[33,48,80,110,143,155,161],"candidate":[34],"responses":[35],"are":[36,167],"given.":[37],"For":[38],"effective":[39],"visual":[40],"reasoning,":[42],"both":[43],"knowledge":[45,68,77,111,125,140],"acquisition":[46],"problem":[47,52],"multimodal":[50,103],"alignment":[51],"need":[53],"be":[55],"solved.":[56],"Therefore,":[57],"we":[58],"propose":[59],"novel":[61],"Vision-Language-Knowledge":[62],"Co-embedding":[63],"(ViLaKC)":[64],"model":[65,94,129,166],"that":[66],"extracts":[67],"graphs":[69,112],"relevant":[70],"from":[74],"external":[76],"base,":[78],"ConceptNet,":[79],"uses":[81,95,130,145],"them":[82],"together":[83],"with":[84,152],"input":[86],"image":[87,154],"question.":[91,158],"The":[92,159],"proposed":[93,128,165],"pretrained":[97],"vision-language-knowledge":[98],"embedding":[99],"module,":[100],"which":[101],"co-embeds":[102],"data":[104],"including":[105],"images,":[106],"texts,":[109],"into":[113],"single":[115],"feature":[116],"vector.":[117],"To":[118],"reflect":[119],"structural":[121],"information":[122],"of":[123,163],"graph,":[126],"graph":[132,141],"convolutional":[133],"neural":[134],"network":[135],"layer":[136],"embed":[138],"first":[142],"then":[144],"multi-head":[146],"self-attention":[147],"layers":[148],"co-embed":[150],"it":[151],"effectiveness":[160],"performance":[162],"experimentally":[168],"validated":[169],"using":[170],"VCR":[172],"v1.0":[173],"benchmark":[174],"dataset.":[175]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}