{"id":"https://openalex.org/W4416750056","doi":"https://doi.org/10.1109/iros60139.2025.11246615","title":"J-ORA: A Framework and Multimodal Dataset for Japanese Object Identification, Reference, Action Prediction in Robot Perception","display_name":"J-ORA: A Framework and Multimodal Dataset for Japanese Object Identification, Reference, Action Prediction in Robot Perception","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750056","doi":"https://doi.org/10.1109/iros60139.2025.11246615"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5094255317","display_name":"Jesse Atuhurra","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Jesse Atuhurra","raw_affiliation_strings":["NAIST,Division of Information Science,Nara,Japan"],"affiliations":[{"raw_affiliation_string":"NAIST,Division of Information Science,Nara,Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016936747","display_name":"Hidetaka Kamigaito","orcid":"https://orcid.org/0000-0002-5249-5813"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hidetaka Kamigaito","raw_affiliation_strings":["NAIST,Division of Information Science,Nara,Japan"],"affiliations":[{"raw_affiliation_string":"NAIST,Division of Information Science,Nara,Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102396915","display_name":"Taro Watanabe","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Taro Watanabe","raw_affiliation_strings":["NAIST,Division of Information Science,Nara,Japan"],"affiliations":[{"raw_affiliation_string":"NAIST,Division of Information Science,Nara,Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101880946","display_name":"Koichiro Yoshino","orcid":"https://orcid.org/0000-0001-6579-361X"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koichiro Yoshino","raw_affiliation_strings":["NAIST,Division of Information Science,Nara,Japan"],"affiliations":[{"raw_affiliation_string":"NAIST,Division of Information Science,Nara,Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5094255317"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40244268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2653","last_page":"2660"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.45410001277923584,"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":0.45410001277923584,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.2533999979496002,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.15060000121593475,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/affordance","display_name":"Affordance","score":0.871999979019165},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.7511000037193298},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.7329999804496765},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6137999892234802},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5727999806404114},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4690999984741211},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.35580000281333923}],"concepts":[{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.871999979019165},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.7511000037193298},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7329999804496765},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7279999852180481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.659600019454956},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6137999892234802},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5727999806404114},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4690999984741211},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41190001368522644},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.35580000281333923},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3449000120162964},{"id":"https://openalex.org/C53073257","wikidata":"https://www.wikidata.org/wiki/Q7075021","display_name":"Object-oriented design","level":3,"score":0.2980000078678131},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.2874999940395355},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2761000096797943},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.2727000117301941},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2718999981880188},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2712000012397766},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":27,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2028798328","https://openalex.org/W2032699694","https://openalex.org/W2049750909","https://openalex.org/W2098411764","https://openalex.org/W2277195237","https://openalex.org/W2471768434","https://openalex.org/W2520762063","https://openalex.org/W2950457956","https://openalex.org/W2964213933","https://openalex.org/W2970603850","https://openalex.org/W3034758614","https://openalex.org/W3093835562","https://openalex.org/W3143107425","https://openalex.org/W3152929911","https://openalex.org/W3156555225","https://openalex.org/W3172112830","https://openalex.org/W3203663566","https://openalex.org/W4249013746","https://openalex.org/W4312884538","https://openalex.org/W4386065350","https://openalex.org/W4391417118","https://openalex.org/W4391759936","https://openalex.org/W4402537874","https://openalex.org/W4402716224","https://openalex.org/W4405786410","https://openalex.org/W4405787695"],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"J-ORA,":[2],"a":[3,43,93],"novel":[4],"multimodal":[5,76],"dataset":[6],"that":[7,69,89],"bridges":[8],"the":[9,85,123],"gap":[10,94],"in":[11,110,130,134],"robot":[12,132],"perception":[13,32,77,133],"by":[14,41],"providing":[15],"detailed":[16,71],"object":[17,34,72,82,105,112],"attribute":[18,128],"annotations":[19,129],"within":[20],"Japanese":[21],"human-robot":[22],"dialogue":[23],"scenarios.":[24],"J-ORA":[25],"is":[26],"designed":[27],"to":[28,80],"support":[29],"three":[30],"critical":[31],"tasks,":[33],"identification,":[35],"reference":[36],"resolution,":[37],"and":[38,54,62,97,114,138],"next-action":[39],"prediction,":[40],"leveraging":[42],"comprehensive":[44],"template":[45],"of":[46,104,125],"attributes":[47,73],"(e.g.,":[48],"category,":[49],"color,":[50],"shape,":[51],"size,":[52],"material,":[53],"spatial":[55],"relations).":[56],"Extensive":[57],"evaluations":[58],"with":[59],"both":[60],"proprietary":[61,96],"open-source":[63,98],"Vision":[64],"Language":[65],"Models":[66],"(VLMs)":[67],"reveal":[68],"incorporating":[70],"substantially":[74],"improves":[75],"performance":[78],"compared":[79],"without":[81],"attributes.":[83],"Despite":[84],"improvement,":[86],"we":[87],"find":[88],"there":[90],"still":[91],"exists":[92],"between":[95],"VLMs.":[99,119],"In":[100],"addition,":[101],"our":[102],"analysis":[103],"affordances":[106],"demonstrates":[107],"varying":[108],"abilities":[109],"understanding":[111],"functionality":[113],"contextual":[115],"relationships":[116],"across":[117],"different":[118],"These":[120],"findings":[121],"underscore":[122],"importance":[124],"rich,":[126],"context-sensitive":[127],"advancing":[131],"dynamic":[135],"environments.":[136],"Code":[137],"data":[139],"available":[140],"at":[141],"https://github.com/jatuhurrra/J-ORA.":[142]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}