{"id":"https://openalex.org/W4383108766","doi":"https://doi.org/10.1109/icra48891.2023.10161545","title":"Operative Action Captioning for Estimating System Actions","display_name":"Operative Action Captioning for Estimating System Actions","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383108766","doi":"https://doi.org/10.1109/icra48891.2023.10161545"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10161545","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra48891.2023.10161545","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","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/A5104139092","display_name":"Taiki Nakamura","orcid":null},"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":"Taiki Nakamura","raw_affiliation_strings":["Guardian Robot Project, R-IH, RIKEN,Kyoto,Japan,6190288","Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guardian Robot Project, R-IH, RIKEN,Kyoto,Japan,6190288","institution_ids":[]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017261292","display_name":"Seiya Kawano","orcid":"https://orcid.org/0000-0002-5830-8169"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seiya Kawano","raw_affiliation_strings":["Guardian Robot Project, R-IH, RIKEN,Kyoto,Japan,6190288"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guardian Robot Project, R-IH, RIKEN,Kyoto,Japan,6190288","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072197023","display_name":"Akishige Yuguchi","orcid":"https://orcid.org/0000-0002-2985-1162"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Akishige Yuguchi","raw_affiliation_strings":["Guardian Robot Project, R-IH, RIKEN,Kyoto,Japan,6190288"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guardian Robot Project, R-IH, RIKEN,Kyoto,Japan,6190288","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027960360","display_name":"Yasutomo Kawanishi","orcid":"https://orcid.org/0000-0002-3799-4550"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yasutomo Kawanishi","raw_affiliation_strings":["Guardian Robot Project, R-IH, RIKEN,Kyoto,Japan,6190288"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guardian Robot Project, R-IH, RIKEN,Kyoto,Japan,6190288","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101880946","display_name":"Koichiro Yoshino","orcid":"https://orcid.org/0000-0001-6579-361X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koichiro Yoshino","raw_affiliation_strings":["Guardian Robot Project, R-IH, RIKEN,Kyoto,Japan,6190288"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guardian Robot Project, R-IH, RIKEN,Kyoto,Japan,6190288","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07174722,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6124","last_page":"6130"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9994000196456909,"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/T12031","display_name":"Speech and dialogue systems","score":0.9865999817848206,"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/closed-captioning","display_name":"Closed captioning","score":0.9311986565589905},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7821004986763},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.7176140546798706},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6972846984863281},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5699501037597656},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5412449836730957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5225721597671509},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5182952284812927},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.50160813331604},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4412974715232849},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34092843532562256},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.10381123423576355},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09429207444190979},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07320359349250793}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9311986565589905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7821004986763},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.7176140546798706},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6972846984863281},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5699501037597656},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5412449836730957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5225721597671509},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5182952284812927},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.50160813331604},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4412974715232849},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34092843532562256},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.10381123423576355},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09429207444190979},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07320359349250793},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10161545","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra48891.2023.10161545","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.46000000834465027,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2052173329","display_name":"Knowledge Inference System for Robots Bridging Commonsense Written by Language and Real World Observation","funder_award_id":"23K24910","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1769896327","https://openalex.org/W1948566616","https://openalex.org/W1956340063","https://openalex.org/W2154652894","https://openalex.org/W2194775991","https://openalex.org/W2302086703","https://openalex.org/W2463955103","https://openalex.org/W2558834163","https://openalex.org/W2793546384","https://openalex.org/W2862846329","https://openalex.org/W2885648612","https://openalex.org/W2891963134","https://openalex.org/W2963155035","https://openalex.org/W2963175879","https://openalex.org/W2963649796","https://openalex.org/W2964616647","https://openalex.org/W2970327218","https://openalex.org/W2979747405","https://openalex.org/W2988981892","https://openalex.org/W3034679267","https://openalex.org/W3034984754","https://openalex.org/W3036594286","https://openalex.org/W3080111863","https://openalex.org/W3090348690","https://openalex.org/W3099849198","https://openalex.org/W3103211586","https://openalex.org/W3145620595","https://openalex.org/W3157677932","https://openalex.org/W3168417280","https://openalex.org/W3173599944","https://openalex.org/W3203987209","https://openalex.org/W4224912544","https://openalex.org/W4312249162","https://openalex.org/W6682631176","https://openalex.org/W6775332673","https://openalex.org/W6801858185","https://openalex.org/W6810640255","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W3032998312","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W1503094549","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W2110944602","https://openalex.org/W3213722473"],"abstract_inverted_index":{"Human-assistive":[0],"systems,":[1],"such":[2],"as":[3,109,174],"robots,":[4],"need":[5],"to":[6,30,38,42,67,96,134,164,187],"correctly":[7],"understand":[8],"the":[9,17,27,40,65,71,93,97,113,117,127,131,135,158,179,183,188,199,207,217,221,224],"surrounding":[10],"situation":[11],"based":[12],"on":[13],"obser-vations":[14],"and":[15,34,46,63,116,122,209],"output":[16],"required":[18,37],"support":[19],"actions":[20,66,121,128,201],"for":[21],"humans.":[22],"Language":[23],"is":[24,162],"one":[25],"of":[26,57,86,106,223],"important":[28],"channels":[29],"communicate":[31],"with":[32],"humans,":[33],"robots":[35],"are":[36],"have":[39],"ability":[41],"express":[43,112],"their":[44],"understanding":[45],"action-planning":[47],"results.":[48,226],"In":[49],"this":[50],"study,":[51],"we":[52,145,169],"propose":[53],"a":[54,74,79,83,87,103,123,147,155],"new":[55],"task":[56,177],"operative":[58,89,152,159,200],"action":[59,90,153],"captioning":[60],"that":[61,81,91,125,129,149,194,202,215],"estimates":[62,150],"verbalizes":[64],"be":[68,204],"taken":[69],"by":[70,120,138,154],"system":[72,80,148,196],"in":[73,140,182],"human-assisting":[75],"domain.":[76],"We":[77,101],"constructed":[78,146],"outputs":[82],"verbal":[84],"description":[85],"possible":[88],"changes":[92],"current":[94,114,132,208],"state":[95,115,118,133,189],"given":[98],"target":[99,136,210],"state.":[100],"collected":[102],"dataset":[104],"consisting":[105],"two":[107],"images":[108],"observations,":[110],"which":[111],"changed":[119],"caption":[124,161],"describes":[126],"change":[130],"state,":[137],"crowdsourcing":[139],"daily":[141],"life":[142],"situations.":[143],"Then":[144],"an":[151,175],"caption.":[156],"Since":[157],"action's":[160],"expected":[163],"contain":[165],"some":[166],"state-changing":[167],"actions,":[168],"use":[170],"scene":[171,184,218],"graph":[172],"prediction":[173],"auxiliary":[176,213],"because":[178],"events":[180],"written":[181],"graphs":[185,219],"correspond":[186],"changes.":[190],"Experimental":[191],"results":[192],"showed":[193],"our":[195],"successfully":[197],"described":[198],"should":[203],"conducted":[205],"between":[206],"states.":[211],"The":[212],"tasks":[214],"predict":[216],"improved":[220],"quality":[222],"estimation":[225]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
