{"id":"https://openalex.org/W4225282857","doi":"https://doi.org/10.1145/3523111.3523120","title":"Simultaneous Integration of Multimodal Interfaces for Generating Structured and Reliable Robotic Task Configurations","display_name":"Simultaneous Integration of Multimodal Interfaces for Generating Structured and Reliable Robotic Task Configurations","publication_year":2022,"publication_date":"2022-02-18","ids":{"openalex":"https://openalex.org/W4225282857","doi":"https://doi.org/10.1145/3523111.3523120"},"language":"en","primary_location":{"id":"doi:10.1145/3523111.3523120","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3523111.3523120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 the 5th International Conference on Machine Vision and Applications (ICMVA)","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/A5045542140","display_name":"Shuvo Kumar Paul","orcid":"https://orcid.org/0000-0003-1791-3925"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shuvo Kumar Paul","raw_affiliation_strings":["Computer Science&Engineering, UNR, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science&Engineering, UNR, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060518998","display_name":"Pourya Hoseini","orcid":"https://orcid.org/0000-0003-3473-9906"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pourya Hoseini","raw_affiliation_strings":["Department of Ophthalmology, UCSD, USA"],"affiliations":[{"raw_affiliation_string":"Department of Ophthalmology, UCSD, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033832969","display_name":"Arjun Vettath Gopinath","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arjun Vettath Gopinath","raw_affiliation_strings":["Computer Science&Engineering, UNR, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science&Engineering, UNR, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112564167","display_name":"Mircea Nicolescu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mircea Nicolescu","raw_affiliation_strings":["Computer Science&Engineering, UNR, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science&Engineering, UNR, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043342974","display_name":"Monica Nicolescu","orcid":"https://orcid.org/0009-0009-8748-7918"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Monica Nicolescu","raw_affiliation_strings":["Computer Science&Engineering, UNR, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science&Engineering, UNR, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5045542140"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02580894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"61","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9970999956130981,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.996999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8081068992614746},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.793229877948761},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7590201497077942},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.6222277879714966},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5866060853004456},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5682506561279297},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5220437049865723},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5087605118751526},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4951542913913727},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4858357608318329},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4590076804161072},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.44973623752593994},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08775010704994202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8081068992614746},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.793229877948761},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7590201497077942},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6222277879714966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5866060853004456},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5682506561279297},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5220437049865723},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5087605118751526},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4951542913913727},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4858357608318329},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4590076804161072},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.44973623752593994},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08775010704994202},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3523111.3523120","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3523111.3523120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 the 5th International Conference on Machine Vision and Applications (ICMVA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1584239336","https://openalex.org/W1602500555","https://openalex.org/W1977995219","https://openalex.org/W2071008727","https://openalex.org/W2085261163","https://openalex.org/W2092534626","https://openalex.org/W2118988519","https://openalex.org/W2124120479","https://openalex.org/W2130054637","https://openalex.org/W2130805686","https://openalex.org/W2140235142","https://openalex.org/W2151103935"],"related_works":["https://openalex.org/W2066003895","https://openalex.org/W2902873204","https://openalex.org/W2185750513","https://openalex.org/W2010878661","https://openalex.org/W3147379364","https://openalex.org/W2026258298","https://openalex.org/W3204639664","https://openalex.org/W2970836791","https://openalex.org/W2805039731","https://openalex.org/W2989699735"],"abstract_inverted_index":{"This":[0,106],"paper":[1],"presents":[2],"a":[3,20],"framework":[4,141],"that":[5],"simultaneously":[6],"integrates":[7],"multiple":[8],"input":[9],"interfaces":[10,41],"and":[11,28,52,61,74,99,112],"extracts":[12],"task":[13,17,89,119,137,150],"parameters":[14,151],"suitable":[15],"for":[16,42,121,152],"execution":[18],"in":[19,78,101,146,157],"human-robot":[21,124],"collaborative":[22,125],"environment.":[23],"We":[24],"used":[25,116],"pointing":[26,49,54],"gestures":[27],"natural":[29,39],"language":[30],"instruction":[31],"as":[32,34,127,129],"inputs":[33],"they":[35],"provide":[36],"the":[37,45,48,53,62,70,75,79,82,91,102,122,148,153],"most":[38],"interaction":[40,160],"humans.":[43],"In":[44],"proposed":[46,140],"method,":[47],"gesture":[50,72,110],"type":[51],"direction":[55],"are":[56],"estimated":[57],"from":[58,69,109],"RGB":[59],"images,":[60],"object":[63,92],"being":[64],"pointed":[65],"at":[66],"is":[67,85,115],"inferred":[68],"prior":[71],"information":[73,108],"objects":[76],"detected":[77],"scene.":[80],"Subsequently,":[81],"verbal":[83,113],"command":[84,114],"parsed":[86],"to":[87,117,130],"extract":[88],"action,":[90],"of":[93],"interest":[94],"along":[95],"with":[96],"its":[97],"attributes":[98],"position":[100],"2D":[103],"image":[104],"frame.":[105],"extracted":[107],"recognition":[111],"form":[118],"configurations":[120],"desired":[123],"tasks":[126,156],"well":[128],"help":[131],"resolve":[132],"any":[133],"uncertain":[134],"or":[135],"missing":[136],"parameters.":[138],"The":[139],"shows":[142],"very":[143],"promising":[144],"results":[145],"identifying":[147],"relevant":[149],"intended":[154],"robotic":[155],"different":[158],"real-world":[159],"scenarios.":[161]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}