{"id":"https://openalex.org/W4312987214","doi":"https://doi.org/10.1109/mmsp55362.2022.9949120","title":"Multi-modal Human-machine Conversation System for Real Physical World","display_name":"Multi-modal Human-machine Conversation System for Real Physical World","publication_year":2022,"publication_date":"2022-09-26","ids":{"openalex":"https://openalex.org/W4312987214","doi":"https://doi.org/10.1109/mmsp55362.2022.9949120"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp55362.2022.9949120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp55362.2022.9949120","pdf_url":null,"source":{"id":"https://openalex.org/S4363605768","display_name":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","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/A5101768547","display_name":"Yitao Chen","orcid":"https://orcid.org/0009-0007-7454-1802"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yitao Chen","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Pattern Recognition and Intelligent Systems Lab.,China","Pattern Recognition and Intelligent Systems Lab., Beijing University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Pattern Recognition and Intelligent Systems Lab.,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Pattern Recognition and Intelligent Systems Lab., Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033506083","display_name":"Shibo Nie","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shibo Nie","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Pattern Recognition and Intelligent Systems Lab.,China","Pattern Recognition and Intelligent Systems Lab., Beijing University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Pattern Recognition and Intelligent Systems Lab.,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Pattern Recognition and Intelligent Systems Lab., Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038977357","display_name":"Mandan Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mandan Guan","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Pattern Recognition and Intelligent Systems Lab.,China","Pattern Recognition and Intelligent Systems Lab., Beijing University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Pattern Recognition and Intelligent Systems Lab.,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Pattern Recognition and Intelligent Systems Lab., Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440047","display_name":"Jie Wang","orcid":"https://orcid.org/0000-0002-1262-6719"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Pattern Recognition and Intelligent Systems Lab.,China","Pattern Recognition and Intelligent Systems Lab., Beijing University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Pattern Recognition and Intelligent Systems Lab.,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Pattern Recognition and Intelligent Systems Lab., Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011876517","display_name":"Ruoyi Du","orcid":"https://orcid.org/0000-0001-8372-5637"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruoyi Du","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Pattern Recognition and Intelligent Systems Lab.,China","Pattern Recognition and Intelligent Systems Lab., Beijing University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Pattern Recognition and Intelligent Systems Lab.,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Pattern Recognition and Intelligent Systems Lab., Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007417490","display_name":"Dongliang Chang","orcid":"https://orcid.org/0000-0002-4081-3001"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongliang Chang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Pattern Recognition and Intelligent Systems Lab.,China","Pattern Recognition and Intelligent Systems Lab., Beijing University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Pattern Recognition and Intelligent Systems Lab.,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Pattern Recognition and Intelligent Systems Lab., Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077313814","display_name":"Kongming Liang","orcid":"https://orcid.org/0000-0002-4726-093X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kongming Liang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Pattern Recognition and Intelligent Systems Lab.,China","Pattern Recognition and Intelligent Systems Lab., Beijing University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Pattern Recognition and Intelligent Systems Lab.,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Pattern Recognition and Intelligent Systems Lab., Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039812471","display_name":"Zhanyu Ma","orcid":"https://orcid.org/0000-0003-2950-2488"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanyu Ma","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Pattern Recognition and Intelligent Systems Lab.,China","Pattern Recognition and Intelligent Systems Lab., Beijing University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Pattern Recognition and Intelligent Systems Lab.,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Pattern Recognition and Intelligent Systems Lab., Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101768547"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.0602,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.32867532,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"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":0.9980999827384949,"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":0.9976999759674072,"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/conversation","display_name":"Conversation","score":0.8609147071838379},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7200019359588623},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6304525136947632},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5069844722747803},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.48285990953445435},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4598906636238098},{"id":"https://openalex.org/keywords/human\u2013machine-system","display_name":"Human\u2013machine system","score":0.4318233132362366},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16969457268714905},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.08885470032691956}],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.8609147071838379},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7200019359588623},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6304525136947632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5069844722747803},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.48285990953445435},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4598906636238098},{"id":"https://openalex.org/C146047270","wikidata":"https://www.wikidata.org/wiki/Q469666","display_name":"Human\u2013machine system","level":2,"score":0.4318233132362366},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16969457268714905},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.08885470032691956},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/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/mmsp55362.2022.9949120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp55362.2022.9949120","pdf_url":null,"source":{"id":"https://openalex.org/S4363605768","display_name":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2115667691","https://openalex.org/W2194775991","https://openalex.org/W2963037989"],"related_works":["https://openalex.org/W2496949096","https://openalex.org/W2071912017","https://openalex.org/W2274593003","https://openalex.org/W1853743098","https://openalex.org/W2281963941","https://openalex.org/W1491653398","https://openalex.org/W1519529778","https://openalex.org/W2045456578","https://openalex.org/W2968261452","https://openalex.org/W2131757771"],"abstract_inverted_index":{"Enabling":[0],"machines":[1],"to":[2,16,29],"process":[3],"multi-modal":[4,55],"information":[5,43],"and":[6,40,80,95],"understand":[7],"the":[8,49,92,109],"real":[9],"physical":[10],"world":[11],"is":[12],"an":[13,69,82],"important":[14],"step":[15],"achieving":[17],"free":[18],"human-machine":[19,23,56],"conversation.":[20],"However,":[21],"previous":[22],"conversation":[24,57],"systems":[25],"are":[26],"mostly":[27],"limited":[28],"single-modal":[30],"(e.g.,":[31,35,44],"chat":[32],"robot),":[33],"single-round":[34],"visual":[36,42,45,71,100],"Q":[37],"&":[38],"A),":[39],"static":[41],"dialogue).":[46],"To":[47],"address":[48],"above":[50],"problem,":[51],"we":[52],"develop":[53],"a":[54],"system":[58,64,107],"for":[59,98],"specific":[60],"application":[61],"scenarios.":[62],"The":[63],"includes":[65],"two":[66],"modules:":[67],"(i)":[68],"interactive":[70,83],"grounding":[72],"module":[73,86],"that":[74,87],"can":[75,88,113],"actively":[76,96],"disambiguate":[77],"user's":[78],"queries,":[79],"(ii)":[81],"fine-grained":[84],"recognition":[85],"model":[89],"objects":[90],"in":[91],"3D":[93],"environment":[94],"ask":[97],"missing":[99],"information.":[101],"A":[102],"video":[103],"demo":[104],"of":[105],"our":[106],"under":[108],"automobile":[110],"sales":[111],"scenario":[112],"be":[114],"found":[115],"here":[116],"<sup":[117,120],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[118,121],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[119,122],"https://drive.google.com/file/d/1IfBsMKq55ryLOZchIT6G-R5CyWnC3Skiew?usp=sharing.":[123]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
