{"id":"https://openalex.org/W4392667247","doi":"https://doi.org/10.1109/lra.2024.3375257","title":"Continuous Object State Recognition for Cooking Robots Using Pre-Trained Vision-Language Models and Black-Box Optimization","display_name":"Continuous Object State Recognition for Cooking Robots Using Pre-Trained Vision-Language Models and Black-Box Optimization","publication_year":2024,"publication_date":"2024-03-11","ids":{"openalex":"https://openalex.org/W4392667247","doi":"https://doi.org/10.1109/lra.2024.3375257"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3375257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3375257","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.08239","any_repository_has_fulltext":true},"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":["Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","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":["Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","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":["Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","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":["Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","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":["Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","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":3.3758,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.93289409,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"9","issue":"5","first_page":"4059","last_page":"4066"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9911999702453613,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9911999702453613,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9847000241279602,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.902999997138977,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6495798826217651},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6189783811569214},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5782109498977661},{"id":"https://openalex.org/keywords/sigmoid-function","display_name":"Sigmoid function","score":0.5523159503936768},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5344976782798767},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5179144740104675},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.46559107303619385},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.4616813063621521},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4343239963054657},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4265345633029938},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38881248235702515},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18668296933174133},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.16995137929916382},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13991695642471313},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08014428615570068}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6495798826217651},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6189783811569214},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5782109498977661},{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.5523159503936768},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5344976782798767},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5179144740104675},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.46559107303619385},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.4616813063621521},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4343239963054657},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4265345633029938},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38881248235702515},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18668296933174133},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.16995137929916382},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13991695642471313},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08014428615570068},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","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},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2024.3375257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3375257","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2403.08239","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.08239","pdf_url":"https://arxiv.org/pdf/2403.08239","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"pmh:oai:arXiv.org:2403.08239","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.08239","pdf_url":"https://arxiv.org/pdf/2403.08239","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392667247.pdf","grobid_xml":"https://content.openalex.org/works/W4392667247.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2026311529","https://openalex.org/W2109042184","https://openalex.org/W2156047221","https://openalex.org/W2766093809","https://openalex.org/W2803384328","https://openalex.org/W3000256909","https://openalex.org/W4221167444","https://openalex.org/W4287285031","https://openalex.org/W4294554731","https://openalex.org/W4312283726","https://openalex.org/W4381894803","https://openalex.org/W4383108320","https://openalex.org/W4386071707","https://openalex.org/W4390480939","https://openalex.org/W6676279030","https://openalex.org/W6751726483","https://openalex.org/W6751850592","https://openalex.org/W6778883912","https://openalex.org/W6791353385","https://openalex.org/W6791436904","https://openalex.org/W6809938868","https://openalex.org/W6839015040","https://openalex.org/W6856915207"],"related_works":["https://openalex.org/W4385957115","https://openalex.org/W2061372042","https://openalex.org/W3047779762","https://openalex.org/W1520030019","https://openalex.org/W2071654592","https://openalex.org/W3104477175","https://openalex.org/W2088157920","https://openalex.org/W2180954594","https://openalex.org/W4283785902","https://openalex.org/W4313324256"],"abstract_inverted_index":{"The":[0],"state":[1,19,28,56,79,114,152],"recognition":[2,153,169],"of":[3,16,30,58,81,116,128,163,170],"the":[4,14,17,25,55,77,87,101,113,126,135,159,168],"environment":[5],"and":[6,36,62,105,142,149,161,177],"objects":[7],"by":[8,67,124,166],"robots":[9,85],"is":[10],"generally":[11],"based":[12,132],"on":[13,133],"judgement":[15],"current":[18],"as":[20],"a":[21,44,73,139],"classification":[22],"problem.":[23],"On":[24],"other":[26],"hand,":[27],"changes":[29,57,80,115,137],"food":[31,59,82,117],"in":[32],"cooking":[33,84],"happen":[34],"continuously":[35,50,107],"need":[37],"to":[38,75,138],"be":[39,64,155],"captured":[40],"not":[41],"only":[42],"at":[43],"certain":[45],"time":[46],"point":[47],"but":[48],"also":[49,121],"over":[51,108],"time.":[52],"In":[53],"addition,":[54],"are":[60],"complex":[61],"cannot":[63],"easily":[65],"described":[66],"manual":[68],"programming.":[69],"Therefore,":[70],"we":[71,110],"propose":[72],"method":[74,165],"recognize":[76],"continuous":[78,151],"for":[83],"through":[86],"spoken":[88],"language":[89],"using":[90,96],"pre-trained":[91],"large-scale":[92],"vision-language":[93],"models.":[94],"By":[95],"models":[97],"that":[98,123],"can":[99,111,154],"compute":[100],"similarity":[102,136],"between":[103],"images":[104],"texts":[106],"time,":[109],"capture":[112],"while":[118],"cooking.":[119],"We":[120,157],"show":[122],"adjusting":[125],"weighting":[127],"each":[129],"text":[130],"prompt":[131],"fitting":[134],"sigmoid":[140],"function":[141],"then":[143],"performing":[144,167],"black-box":[145],"optimization,":[146],"more":[147],"accurate":[148],"robust":[150],"achieved.":[156],"demonstrate":[158],"effectiveness":[160],"limitations":[162],"this":[164],"water":[171],"boiling,":[172],"butter":[173],"melting,":[174],"egg":[175],"cooking,":[176],"onion":[178],"stir-frying.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2024-03-12T00:00:00"}