{"id":"https://openalex.org/W4404953824","doi":"https://doi.org/10.1109/humanoids58906.2024.10769848","title":"Robotic State Recognition with Image-to-Text Retrieval Task of Pre-Trained Vision-Language Model and Black-Box Optimization","display_name":"Robotic State Recognition with Image-to-Text Retrieval Task of Pre-Trained Vision-Language Model and Black-Box Optimization","publication_year":2024,"publication_date":"2024-11-22","ids":{"openalex":"https://openalex.org/W4404953824","doi":"https://doi.org/10.1109/humanoids58906.2024.10769848"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids58906.2024.10769848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids58906.2024.10769848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE-RAS 23rd 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":["The University of Tokyo 7-3-1 Hongo, Bunkyo-ku,Graduate School of Information Science and Technology,Department of Mechano-Informatics,Tokyo,Japan,113-8656"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo 7-3-1 Hongo, Bunkyo-ku,Graduate School of Information Science and Technology,Department of Mechano-Informatics,Tokyo,Japan,113-8656","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":["The University of Tokyo 7-3-1 Hongo, Bunkyo-ku,Graduate School of Information Science and Technology,Department of Mechano-Informatics,Tokyo,Japan,113-8656"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo 7-3-1 Hongo, Bunkyo-ku,Graduate School of Information Science and Technology,Department of Mechano-Informatics,Tokyo,Japan,113-8656","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":["The University of Tokyo 7-3-1 Hongo, Bunkyo-ku,Graduate School of Information Science and Technology,Department of Mechano-Informatics,Tokyo,Japan,113-8656"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo 7-3-1 Hongo, Bunkyo-ku,Graduate School of Information Science and Technology,Department of Mechano-Informatics,Tokyo,Japan,113-8656","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":["The University of Tokyo 7-3-1 Hongo, Bunkyo-ku,Graduate School of Information Science and Technology,Department of Mechano-Informatics,Tokyo,Japan,113-8656"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo 7-3-1 Hongo, Bunkyo-ku,Graduate School of Information Science and Technology,Department of Mechano-Informatics,Tokyo,Japan,113-8656","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":["The University of Tokyo 7-3-1 Hongo, Bunkyo-ku,Graduate School of Information Science and Technology,Department of Mechano-Informatics,Tokyo,Japan,113-8656"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo 7-3-1 Hongo, Bunkyo-ku,Graduate School of Information Science and Technology,Department of Mechano-Informatics,Tokyo,Japan,113-8656","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22523196,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"934","last_page":"940"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8898000121116638,"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":0.8898000121116638,"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/T13382","display_name":"Robotics and Automated Systems","score":0.8281999826431274,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.8263000249862671,"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":0.8148314952850342},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6453762054443359},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5277850031852722},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5136065483093262},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5066040754318237},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4332270622253418},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.42859748005867004},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4160645306110382},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3419184684753418},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.331514835357666},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09662434458732605}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8148314952850342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6453762054443359},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5277850031852722},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5136065483093262},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5066040754318237},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4332270622253418},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.42859748005867004},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4160645306110382},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3419184684753418},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.331514835357666},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09662434458732605},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/humanoids58906.2024.10769848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids58906.2024.10769848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE-RAS 23rd International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W1979174748","https://openalex.org/W2163267929","https://openalex.org/W2766093809","https://openalex.org/W2949209865","https://openalex.org/W3038288066","https://openalex.org/W3091891304","https://openalex.org/W4383108320","https://openalex.org/W4386071707","https://openalex.org/W4390480939","https://openalex.org/W4403448419","https://openalex.org/W6676279030","https://openalex.org/W6704906208","https://openalex.org/W6791353385","https://openalex.org/W6802517928","https://openalex.org/W6809938868","https://openalex.org/W6810327023","https://openalex.org/W6839015040","https://openalex.org/W6849914806","https://openalex.org/W6857733129"],"related_works":["https://openalex.org/W4321487865","https://openalex.org/W4313906399","https://openalex.org/W4239306820","https://openalex.org/W4391266461","https://openalex.org/W2590798552","https://openalex.org/W2811106690","https://openalex.org/W2947043951","https://openalex.org/W3213722473","https://openalex.org/W2110944602","https://openalex.org/W3098003361"],"abstract_inverted_index":{"State":[0],"recognition":[1,34,71,123],"of":[2,12,17,81,90,138,188,193,208],"the":[3,9,15,50,96,102,113,185,191,205],"environment":[4],"and":[5,14,28,101,107,158,203],"objects,":[6],"such":[7],"as":[8],"open/closed":[10,186],"state":[11,33,70,109,122,139,187,192,207],"doors":[13],"on/off":[16],"lights,":[18],"is":[19,79,169,181,196,212],"indispensable":[20],"for":[21,49,165],"robots":[22],"that":[23,132],"perform":[24,108],"daily":[25],"life":[26],"support":[27],"security":[29],"tasks.":[30,85],"Until":[31],"now,":[32],"methods":[35],"have":[36,217],"been":[37,218],"based":[38],"on":[39],"training":[40],"neural":[41,148],"networks":[42,149],"from":[43,58,200],"manual":[44,151],"annotations,":[45],"preparing":[46,143],"special":[47],"sensors":[48],"recognition,":[51],"or":[52,61,150,198,214],"manually":[53],"programming":[54],"to":[55,116,162,172,183],"extract":[56],"features":[57],"point":[59],"clouds":[60],"raw":[62],"images.":[63],"In":[64,153],"contrast,":[65],"we":[66],"propose":[67],"a":[68,74,136,201,210],"robotic":[69],"method":[72],"using":[73,119],"pre-trained":[75],"vision-language":[76],"model,":[77],"which":[78,176,216],"capable":[80],"Image-to-Text":[82],"Retrieval":[83],"(ITR)":[84],"We":[86],"prepare":[87,173],"several":[88],"kinds":[89],"language":[91],"prompts":[92,100,145,157],"in":[93],"advance,":[94],"calculate":[95],"similarity":[97],"between":[98],"these":[99],"current":[103],"image":[104],"by":[105,141],"ITR,":[106],"recognition.":[110],"By":[111],"applying":[112],"optimal":[114],"weighting":[115],"each":[117,166],"prompt":[118],"black-box":[120],"optimization,":[121],"can":[124],"be":[125,163],"performed":[126],"with":[127],"higher":[128],"accuracy.":[129],"Experiments":[130],"show":[131],"this":[133],"theory":[134],"enables":[135],"variety":[137],"recognitions":[140],"simply":[142],"multiple":[144,174],"without":[146],"retraining":[147],"programming.":[152],"addition,":[154],"since":[155],"only":[156],"their":[159],"weights":[160],"need":[161,171],"prepared":[164],"recognizer,":[167],"there":[168],"no":[170],"models,":[175],"facilitates":[177],"resource":[178],"management.":[179],"It":[180],"possible":[182],"recognize":[184],"transparent":[189],"doors,":[190],"whether":[194,209],"water":[195],"running":[197],"not":[199],"faucet,":[202],"even":[204],"qualitative":[206],"kitchen":[211],"clean":[213],"not,":[215],"challenging":[219],"so":[220],"far,":[221],"through":[222],"language.":[223]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}