{"id":"https://openalex.org/W4375854264","doi":"https://doi.org/10.1109/cbs55922.2023.10115355","title":"Cross-modal Task Understanding and Execution of Voice-fingertip Reading Instruction by Using Small Family Service Robotic","display_name":"Cross-modal Task Understanding and Execution of Voice-fingertip Reading Instruction by Using Small Family Service Robotic","publication_year":2023,"publication_date":"2023-03-24","ids":{"openalex":"https://openalex.org/W4375854264","doi":"https://doi.org/10.1109/cbs55922.2023.10115355"},"language":"en","primary_location":{"id":"doi:10.1109/cbs55922.2023.10115355","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cbs55922.2023.10115355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Cyborg and Bionic Systems (CBS)","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/A5087948659","display_name":"Zhihui Zhou","orcid":"https://orcid.org/0000-0002-3040-567X"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhihui Zhou","raw_affiliation_strings":["Zhejiang Lab,Intelligent Robotic Research Center,Hangzhou,Zhejiang,China,310000"],"affiliations":[{"raw_affiliation_string":"Zhejiang Lab,Intelligent Robotic Research Center,Hangzhou,Zhejiang,China,310000","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039356472","display_name":"Shiqiang Zhu","orcid":"https://orcid.org/0000-0002-5687-4001"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiqiang Zhu","raw_affiliation_strings":["Zhejiang Lab,Intelligent Robotic Research Center,Hangzhou,Zhejiang,China,310000","Zhejiang University, Hangzhou, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Lab,Intelligent Robotic Research Center,Hangzhou,Zhejiang,China,310000","institution_ids":["https://openalex.org/I4210123185"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101021753","display_name":"Kaiyuan Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiyuan Zhu","raw_affiliation_strings":["Zhejiang Lab,Intelligent Robotic Research Center,Hangzhou,Zhejiang,China,310000"],"affiliations":[{"raw_affiliation_string":"Zhejiang Lab,Intelligent Robotic Research Center,Hangzhou,Zhejiang,China,310000","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114047301","display_name":"Chao Cheng","orcid":"https://orcid.org/0000-0002-9380-3296"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Cheng","raw_affiliation_strings":["Zhejiang Lab,Intelligent Robotic Research Center,Hangzhou,Zhejiang,China,310000"],"affiliations":[{"raw_affiliation_string":"Zhejiang Lab,Intelligent Robotic Research Center,Hangzhou,Zhejiang,China,310000","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010340252","display_name":"Jason Gu","orcid":"https://orcid.org/0000-0002-7626-1077"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jason Gu","raw_affiliation_strings":["Dalhousie University,Department of Electrical and Computer Engineering,Halifax,Nova Scotia,Canada","Department of Electrical and Computer Engineering, Dalhousie University, Halifax, Nova Scotia, Canada"],"affiliations":[{"raw_affiliation_string":"Dalhousie University,Department of Electrical and Computer Engineering,Halifax,Nova Scotia,Canada","institution_ids":["https://openalex.org/I129902397"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Dalhousie University, Halifax, Nova Scotia, Canada","institution_ids":["https://openalex.org/I129902397"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5087948659"],"corresponding_institution_ids":["https://openalex.org/I4210123185"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03797569,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"315","last_page":"319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9975000023841858,"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":0.9975000023841858,"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":0.9855999946594238,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9787999987602234,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.844760000705719},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7198331356048584},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6441372632980347},{"id":"https://openalex.org/keywords/service-robot","display_name":"Service robot","score":0.5551328659057617},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.520412802696228},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5012722015380859},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.49334898591041565},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4670497477054596},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4081350862979889},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36165356636047363},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35786113142967224},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32287847995758057}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.844760000705719},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7198331356048584},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6441372632980347},{"id":"https://openalex.org/C2776228582","wikidata":"https://www.wikidata.org/wiki/Q7455797","display_name":"Service robot","level":3,"score":0.5551328659057617},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.520412802696228},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5012722015380859},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.49334898591041565},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4670497477054596},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4081350862979889},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36165356636047363},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35786113142967224},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32287847995758057},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cbs55922.2023.10115355","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cbs55922.2023.10115355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Cyborg and Bionic Systems (CBS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2107525312","https://openalex.org/W2120515362","https://openalex.org/W2125201599","https://openalex.org/W2512580430","https://openalex.org/W2560920409","https://openalex.org/W2565591417","https://openalex.org/W2619328388","https://openalex.org/W2753027569","https://openalex.org/W2955657017","https://openalex.org/W2963631961","https://openalex.org/W3005881764","https://openalex.org/W3009337785","https://openalex.org/W3038597925","https://openalex.org/W3044683644","https://openalex.org/W3086837474","https://openalex.org/W3124671614","https://openalex.org/W3156800342","https://openalex.org/W3173223111","https://openalex.org/W3193767255","https://openalex.org/W3200627326","https://openalex.org/W3200998783","https://openalex.org/W4206396243","https://openalex.org/W4285183690"],"related_works":["https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W8302103","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W2737719445","https://openalex.org/W2362990116","https://openalex.org/W2025208083","https://openalex.org/W2109596994","https://openalex.org/W4323870231"],"abstract_inverted_index":{"The":[0,158],"correct":[1],"understanding":[2,56,196],"of":[3,32,64,78,90,114,140,146,154,160,199,210],"human":[4],"task":[5,55,100,169,195],"instructions":[6],"is":[7,69,72,103,172],"an":[8],"important":[9],"basic":[10],"condition":[11],"for":[12,193,206],"family":[13,23,211],"service":[14,212],"robots":[15,38],"to":[16,40,45,111,126,174],"carry":[17],"out":[18],"their":[19],"work.":[20],"In":[21,48],"daily":[22],"scenarios,":[24],"single-modal":[25],"voice":[26],"commands":[27],"often":[28],"have":[29],"the":[30,42,62,75,86,91,94,98,106,109,112,115,120,128,133,135,138,141,147,151,155,166,176,183,188,208],"problem":[31],"missing":[33],"pronoun":[34],"references,":[35],"which":[36,71],"makes":[37],"unable":[39],"identify":[41],"target":[43,129],"object":[44,123],"be":[46,191,204],"operated.":[47],"this":[49],"paper,":[50],"a":[51],"novel":[52],"cross-modal":[53,200],"instruction":[54,143],"and":[57,66,81,144,149,165,197,202],"execution":[58,198],"framework":[59,189],"based":[60,73],"on":[61,74],"fusion":[63],"speech":[65,87],"visual":[67,122,142,156,161],"information":[68,159],"proposed,":[70],"computing":[76],"architecture":[77],"robot":[79,194],"terminal":[80],"cloud":[82],"server.":[83],"By":[84,118],"inputting":[85],"recognition":[88],"results":[89,185],"sound":[92,116],"into":[93],"pre-trained":[95],"Bert":[96],"model,":[97],"first-level":[99],"classification":[101,170,180],"label":[102,153,164,171],"obtained.":[104],"Then,":[105],"robotic":[107,136],"turns":[108],"camera":[110],"location":[113],"source.":[117],"using":[119],"lightweight":[121],"detection":[124],"model":[125],"obtain":[127,175],"area":[130],"pointed":[131],"by":[132],"finger,":[134],"completes":[137],"confirmation":[139],"entity":[145,162],"object,":[148],"obtains":[150],"semantic":[152,163],"entity.":[157],"first":[167],"level":[168,178],"fused":[173],"second":[177],"subtask":[179],"label.":[181],"Finally,":[182],"experimental":[184],"confirm":[186],"that":[187],"can":[190],"used":[192],"instructions,":[201],"will":[203],"helpful":[205],"promoting":[207],"application":[209],"robots.":[213]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}