{"id":"https://openalex.org/W4390480939","doi":"https://doi.org/10.1109/humanoids57100.2023.10375211","title":"Robotic Applications of Pre-Trained Vision-Language Models to Various Recognition Behaviors","display_name":"Robotic Applications of Pre-Trained Vision-Language Models to Various Recognition Behaviors","publication_year":2023,"publication_date":"2023-12-12","ids":{"openalex":"https://openalex.org/W4390480939","doi":"https://doi.org/10.1109/humanoids57100.2023.10375211"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids57100.2023.10375211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids57100.2023.10375211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE-RAS 22nd International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-article"},"type":"article","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/A5087094940","display_name":"Kento Kawaharazuka","orcid":"https://orcid.org/0000-0002-7464-7187"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kento Kawaharazuka","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Bunkyo-ku,Tokyo,Japan,113\u20138656"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Bunkyo-ku,Tokyo,Japan,113\u20138656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048932127","display_name":"Yoshiki Obinata","orcid":"https://orcid.org/0000-0003-1429-4401"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiki Obinata","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Bunkyo-ku,Tokyo,Japan,113\u20138656"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Bunkyo-ku,Tokyo,Japan,113\u20138656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050690629","display_name":"Naoaki Kanazawa","orcid":"https://orcid.org/0009-0002-3527-3087"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoaki Kanazawa","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Bunkyo-ku,Tokyo,Japan,113\u20138656"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Bunkyo-ku,Tokyo,Japan,113\u20138656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101836795","display_name":"Kei Okada","orcid":"https://orcid.org/0000-0001-6606-6692"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kei Okada","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Bunkyo-ku,Tokyo,Japan,113\u20138656"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Bunkyo-ku,Tokyo,Japan,113\u20138656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047218430","display_name":"Masayuki Inaba","orcid":"https://orcid.org/0000-0003-1273-1567"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masayuki Inaba","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Bunkyo-ku,Tokyo,Japan,113\u20138656"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo,Department of Mechano- Informatics,Bunkyo-ku,Tokyo,Japan,113\u20138656","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5087094940"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":1.9678,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88804793,"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":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9943000078201294,"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":0.9943000078201294,"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":0.9797000288963318,"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":0.7698221206665039},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.761725127696991},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7366012334823608},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6403073072433472},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6393622756004333},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.6321839094161987},{"id":"https://openalex.org/keywords/affordance","display_name":"Affordance","score":0.5567166209220886},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.502903401851654},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4986879825592041},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.47704261541366577},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4723851680755615},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4668104648590088},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39320117235183716},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3397521376609802},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33671027421951294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7698221206665039},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.761725127696991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7366012334823608},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6403073072433472},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6393622756004333},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.6321839094161987},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.5567166209220886},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.502903401851654},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4986879825592041},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.47704261541366577},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4723851680755615},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4668104648590088},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39320117235183716},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3397521376609802},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33671027421951294},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/humanoids57100.2023.10375211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids57100.2023.10375211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE-RAS 22nd International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1524405667","https://openalex.org/W1933349210","https://openalex.org/W2602856279","https://openalex.org/W2618530766","https://openalex.org/W2950697717","https://openalex.org/W2962716343","https://openalex.org/W2963166639","https://openalex.org/W2970641574","https://openalex.org/W3166396011","https://openalex.org/W4221167444","https://openalex.org/W4281633595","https://openalex.org/W4292779060","https://openalex.org/W4293860330","https://openalex.org/W4383108320","https://openalex.org/W4387764390","https://openalex.org/W6778883912","https://openalex.org/W6791353385","https://openalex.org/W6801810553","https://openalex.org/W6802517928","https://openalex.org/W6809938868","https://openalex.org/W6811433417","https://openalex.org/W6839015040"],"related_works":["https://openalex.org/W1972718289","https://openalex.org/W1791514435","https://openalex.org/W2346831895","https://openalex.org/W2248634132","https://openalex.org/W2295809616","https://openalex.org/W3049116993","https://openalex.org/W1854403911","https://openalex.org/W4297703863","https://openalex.org/W2573606541","https://openalex.org/W2912559722"],"abstract_inverted_index":{"A":[0],"number":[1],"of":[2,23,80,86,96,156,168,184,207],"models":[3,19,58,115,140],"that":[4,33,43,122,190],"learn":[5],"the":[6,52,78,81,84,108,112,123,150,166,182,204],"relations":[7],"between":[8,54],"vision":[9],"and":[10,38,59,83,89,98,106,117,145,164,177,196],"language":[11],"from":[12],"large":[13],"datasets":[14],"have":[15],"been":[16],"released.":[17],"These":[18],"perform":[20],"a":[21,93,120],"variety":[22],"tasks,":[24],"such":[25],"as":[26,198,200],"answering":[27],"questions":[28],"about":[29],"images,":[30,37],"retrieving":[31],"sentences":[32],"best":[34],"correspond":[35,44],"to":[36,45,69,77,92,110,131,137,158,203],"finding":[39],"regions":[40],"in":[41,101,119],"images":[42],"phrases.":[46],"Although":[47],"there":[48],"are":[49,66],"some":[50],"examples,":[51],"connection":[53],"these":[55,139,185],"pre-trained":[56,113],"vision-language":[57,114],"robotics":[60],"is":[61],"still":[62],"weak.":[63],"If":[64],"they":[65,72],"directly":[67,128],"connected":[68],"robot":[70,82,124,132,142],"motions,":[71],"lose":[73],"their":[74],"versatility":[75],"due":[76],"embodiment":[79],"difficulty":[85],"data":[87],"collection,":[88],"become":[90],"inapplicable":[91],"wide":[94],"range":[95],"bodies":[97],"situations.":[99],"Therefore,":[100],"this":[102,191],"study,":[103],"we":[104],"categorize":[105],"summarize":[107],"methods":[109,157],"utilize":[111],"flexibly":[116],"easily":[118],"way":[121],"can":[125],"understand,":[126],"without":[127,148],"connecting":[129],"them":[130],"motions.":[133],"We":[134,152,188],"discuss":[135],"how":[136],"use":[138],"for":[141,162],"motion":[143,146],"selection":[144],"planning":[147],"re-training":[149],"models.":[151],"consider":[153],"five":[154,186],"types":[155],"extract":[159],"information":[160],"understandable":[161],"robots,":[163],"show":[165],"examples":[167],"state":[169],"recognition,":[170,172,174,176],"object":[171],"affordance":[173],"relation":[175],"anomaly":[178],"detection":[179],"based":[180],"on":[181],"combination":[183],"methods.":[187],"expect":[189],"study":[192],"will":[193],"add":[194],"flexibility":[195],"ease-of-use,":[197],"well":[199],"new":[201],"applications,":[202],"recognition":[205],"behavior":[206],"existing":[208],"robots.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2024-01-02T00:00:00"}
