{"id":"https://openalex.org/W4366721747","doi":"https://doi.org/10.1109/iccicc57084.2022.10101517","title":"Can Visual Linguistic Models become Knowledge Bases: A Prompt Learning Framework for Size Perception","display_name":"Can Visual Linguistic Models become Knowledge Bases: A Prompt Learning Framework for Size Perception","publication_year":2022,"publication_date":"2022-12-08","ids":{"openalex":"https://openalex.org/W4366721747","doi":"https://doi.org/10.1109/iccicc57084.2022.10101517"},"language":"en","primary_location":{"id":"doi:10.1109/iccicc57084.2022.10101517","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iccicc57084.2022.10101517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 21st International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100388367","display_name":"Yi Zhang","orcid":"https://orcid.org/0009-0007-7269-8187"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["Purdue University,Computer and Information Technology,West Lafayette,IN,USA","Computer and Information Technology, Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,Computer and Information Technology,West Lafayette,IN,USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Computer and Information Technology, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055392823","display_name":"Julia Taylor Rayz","orcid":"https://orcid.org/0000-0003-3786-2416"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julia Taylor Rayz","raw_affiliation_strings":["Purdue University,Computer and Information Technology,West Lafayette,IN,USA","Computer and Information Technology, Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,Computer and Information Technology,West Lafayette,IN,USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Computer and Information Technology, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24207048,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"56","last_page":"63"},"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":0.9980000257492065,"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/computer-science","display_name":"Computer science","score":0.7973741292953491},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.615818440914154},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5930374264717102},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5654995441436768},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5327214002609253},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5243787169456482},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4917609989643097},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.4605928659439087},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.43110254406929016},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4187442660331726},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11331793665885925}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7973741292953491},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.615818440914154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5930374264717102},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5654995441436768},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5327214002609253},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5243787169456482},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4917609989643097},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4605928659439087},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.43110254406929016},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4187442660331726},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11331793665885925},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccicc57084.2022.10101517","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iccicc57084.2022.10101517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 21st International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1889081078","https://openalex.org/W1933349210","https://openalex.org/W2121055260","https://openalex.org/W2250384498","https://openalex.org/W2263785794","https://openalex.org/W2316289542","https://openalex.org/W2560730294","https://openalex.org/W2802416800","https://openalex.org/W2966715458","https://openalex.org/W2970476646","https://openalex.org/W3100307207","https://openalex.org/W3126792443","https://openalex.org/W3185341429","https://openalex.org/W6766904570","https://openalex.org/W6789753369","https://openalex.org/W6798057236"],"related_works":["https://openalex.org/W1501776718","https://openalex.org/W2615136228","https://openalex.org/W657108774","https://openalex.org/W2390192952","https://openalex.org/W2373296418","https://openalex.org/W3213254966","https://openalex.org/W2377265617","https://openalex.org/W2156207377","https://openalex.org/W2094725091","https://openalex.org/W1515761309"],"abstract_inverted_index":{"Empowering":[0],"machines":[1],"to":[2,31,46,74,119],"understand":[3],"our":[4],"physical":[5],"world":[6],"should":[7],"go":[8],"beyond":[9],"models":[10,16,45,60,78,127],"with":[11,17],"only":[12,18],"natural":[13,36,69],"language":[14,22,37],"and":[15,21,39,68,111,113],"vision.":[19],"Vision":[20],"comprise":[23],"a":[24,101],"growing":[25],"field":[26],"of":[27,56,82,123,125,132],"study":[28,99],"that":[29,76],"attempts":[30],"bridge":[32],"the":[33,63,121,130],"gap":[34],"between":[35,65],"processing":[38],"computer":[40],"vision":[41],"communities":[42],"by":[43,92],"enabling":[44],"learn":[47],"visually":[48],"grounded":[49],"language.":[50],"However,":[51],"as":[52,89],"an":[53],"increasing":[54],"number":[55],"pre-trained":[57],"visual":[58,66,107],"linguistic":[59,108],"focus":[61],"on":[62],"alignment":[64],"regions":[67],"language,":[70],"it":[71],"is":[72],"difficult":[73],"claim":[75],"these":[77,126],"capture":[79],"certain":[80],"properties":[81],"objects":[83],"in":[84,95,128],"their":[85],"latent":[86],"space,":[87],"such":[88],"size.":[90],"Inspired":[91],"recent":[93],"trends":[94],"prompt":[96,102,117],"learning,":[97],"this":[98],"designed":[100],"learning":[103],"framework":[104],"for":[105],"two":[106],"models,":[109],"ViLBERT":[110],"ViLT,":[112],"used":[114],"manually":[115],"crafted":[116],"templates":[118],"evaluate":[120],"consistency":[122],"performance":[124],"comparing":[129],"size":[131],"objects.":[133]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}