{"id":"https://openalex.org/W4405787828","doi":"https://doi.org/10.1109/iros58592.2024.10801583","title":"Latent Object Characteristics Recognition with Visual to Haptic-Audio Cross-modal Transfer Learning","display_name":"Latent Object Characteristics Recognition with Visual to Haptic-Audio Cross-modal Transfer Learning","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405787828","doi":"https://doi.org/10.1109/iros58592.2024.10801583"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10801583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5066028565","display_name":"Namiko Saito","orcid":"https://orcid.org/0000-0003-4140-7643"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Namiko Saito","raw_affiliation_strings":["The University of Edinburgh,School of Informatics,Edinburgh,U.K"],"affiliations":[{"raw_affiliation_string":"The University of Edinburgh,School of Informatics,Edinburgh,U.K","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090546247","display_name":"Jo\u00e3o Moura","orcid":"https://orcid.org/0000-0002-1812-7857"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jo\u00e3o Moura","raw_affiliation_strings":["The University of Edinburgh,School of Informatics,Edinburgh,U.K"],"affiliations":[{"raw_affiliation_string":"The University of Edinburgh,School of Informatics,Edinburgh,U.K","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046252297","display_name":"Hiroki Uchida","orcid":"https://orcid.org/0000-0002-8035-8146"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroki Uchida","raw_affiliation_strings":["Waseda University,Department of Intermedia Art and Science,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Intermedia Art and Science,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069715982","display_name":"Sethu Vijayakumar","orcid":"https://orcid.org/0000-0003-0649-7241"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sethu Vijayakumar","raw_affiliation_strings":["The University of Edinburgh,School of Informatics,Edinburgh,U.K"],"affiliations":[{"raw_affiliation_string":"The University of Edinburgh,School of Informatics,Edinburgh,U.K","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5066028565"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27109436,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8579","last_page":"8586"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.929099977016449,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.929099977016449,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.921999990940094,"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/T10860","display_name":"Speech and Audio Processing","score":0.9039999842643738,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.7685838937759399},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7231667041778564},{"id":"https://openalex.org/keywords/haptic-technology","display_name":"Haptic technology","score":0.677850604057312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6057498455047607},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5808183550834656},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5438327193260193},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.48796528577804565},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4777752161026001},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.47480645775794983},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4534764587879181},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.44297346472740173},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.29400771856307983}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7685838937759399},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7231667041778564},{"id":"https://openalex.org/C152086174","wikidata":"https://www.wikidata.org/wiki/Q3030571","display_name":"Haptic technology","level":2,"score":0.677850604057312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6057498455047607},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5808183550834656},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5438327193260193},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.48796528577804565},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4777752161026001},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47480645775794983},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4534764587879181},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.44297346472740173},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.29400771856307983},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10801583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2075673359","https://openalex.org/W2136275707","https://openalex.org/W2193145675","https://openalex.org/W2211722331","https://openalex.org/W2321135324","https://openalex.org/W2407545225","https://openalex.org/W2737661303","https://openalex.org/W2744653421","https://openalex.org/W2775635818","https://openalex.org/W2888704052","https://openalex.org/W2895085622","https://openalex.org/W2952866402","https://openalex.org/W2963037989","https://openalex.org/W2963956866","https://openalex.org/W2969180157","https://openalex.org/W3043995050","https://openalex.org/W3133344428","https://openalex.org/W3135705943","https://openalex.org/W4226146187","https://openalex.org/W4308180768","https://openalex.org/W4388904275","https://openalex.org/W6795494688"],"related_works":["https://openalex.org/W156716224","https://openalex.org/W2111871955","https://openalex.org/W3175380930","https://openalex.org/W1989694608","https://openalex.org/W2139876914","https://openalex.org/W1986738380","https://openalex.org/W2642061445","https://openalex.org/W4233260495","https://openalex.org/W3094485622","https://openalex.org/W3001080452"],"abstract_inverted_index":{"Recognising":[0],"the":[1,33,40,91,97,103,125,140,155,170],"characteristics":[2,129],"of":[3,24,127,143,163],"objects":[4,64,168],"while":[5],"a":[6,70,79,110],"robot":[7,29,172],"handles":[8],"them":[9],"is":[10,47,56,69],"crucial":[11],"for":[12,31,50,58],"adjusting":[13],"motions":[14,30],"that":[15],"ensure":[16],"stable":[17,26],"and":[18,27,117,152,166],"efficient":[19,28],"interactions":[20],"with":[21,93,115],"containers.":[22],"Ahead":[23],"realising":[25],"handling/transferring":[32],"containers,":[34],"this":[35,75],"work":[36],"aims":[37],"to":[38,86,109],"recognise":[39],"unobservable":[41],"latent":[42,104],"object":[43,51,128,156],"characteristics.":[44,157],"While":[45],"vision":[46,85,108],"commonly":[48],"used":[49],"recognition":[52,136,141,162],"by":[53],"robots,":[54],"it":[55],"ineffective":[57],"detecting":[59],"hidden":[60],"objects.":[61],"However,":[62],"recognising":[63],"indirectly":[65],"using":[66,130,169],"other":[67],"sensors":[68],"challenging":[71],"task.":[72],"To":[73],"address":[74],"challenge,":[76],"we":[77,101,148,159],"propose":[78],"cross-modal":[80],"transfer":[81,102,121],"learning":[82,122,146],"approach":[83],"from":[84,107],"haptic-audio.":[87],"We":[88],"initially":[89],"train":[90],"model":[92],"vision,":[94],"directly":[95],"observing":[96],"target":[98],"object.":[99],"Subsequently,":[100],"space":[105],"learned":[106],"second":[111],"module,":[112],"trained":[113,165],"only":[114],"haptic-audio":[116],"motor":[118],"data.":[119],"This":[120],"framework":[123,147],"facilitates":[124],"representation":[126],"indirect":[131],"sensor":[132],"data,":[133],"thereby":[134],"improving":[135],"accuracy.":[137],"For":[138],"evaluating":[139],"accuracy":[142],"our":[144,176],"proposed":[145],"selected":[149],"shape,":[150],"position,":[151],"orientation":[153],"as":[154],"Finally,":[158],"demonstrate":[160],"online":[161],"both":[164],"untrained":[167],"humanoid":[171],"Nextage":[173],"Open.":[174],"See":[175],"accompanying":[177],"video":[178],"here:":[179],"https://www.youtube.com/watch?v=sOHqPC1uusg":[180]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}