{"id":"https://openalex.org/W4210437318","doi":"https://doi.org/10.1109/asru51503.2021.9688143","title":"Human-Agent Collaboration Strategies for Vision-Grounded Instruction Following","display_name":"Human-Agent Collaboration Strategies for Vision-Grounded Instruction Following","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4210437318","doi":"https://doi.org/10.1109/asru51503.2021.9688143"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688143","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688143","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5069665298","display_name":"Guan-Lin Chao","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Guan-Lin Chao","raw_affiliation_strings":["Carnegie Mellon University,Electrical and Computer Engineering","Electrical and Computer Engineering, Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Electrical and Computer Engineering","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Electrical and Computer Engineering, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028182466","display_name":"Ian Lane","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Lane","raw_affiliation_strings":["Language and Technologies Institute, Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Language and Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5069665298"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1922523,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"877","last_page":"884"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9962999820709229,"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":0.9962999820709229,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9922000169754028,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9915000200271606,"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/computer-science","display_name":"Computer science","score":0.7989755272865295},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7132925391197205},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.6917166113853455},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6194935441017151},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6070918440818787},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5562781095504761},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4832656979560852},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.41306206583976746},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3942829668521881},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3836320638656616},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11118832230567932},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07542893290519714},{"id":"https://openalex.org/keywords/pedagogy","display_name":"Pedagogy","score":0.07411551475524902}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7989755272865295},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7132925391197205},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.6917166113853455},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6194935441017151},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6070918440818787},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5562781095504761},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4832656979560852},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.41306206583976746},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3942829668521881},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3836320638656616},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11118832230567932},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07542893290519714},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.07411551475524902},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688143","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688143","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1924762813","https://openalex.org/W2020218605","https://openalex.org/W2070935310","https://openalex.org/W2111526438","https://openalex.org/W2122223050","https://openalex.org/W2236233024","https://openalex.org/W2256388387","https://openalex.org/W2293350124","https://openalex.org/W2296073425","https://openalex.org/W2605102758","https://openalex.org/W2749928749","https://openalex.org/W2751516180","https://openalex.org/W2767050701","https://openalex.org/W2805984364","https://openalex.org/W2907923173","https://openalex.org/W2927819804","https://openalex.org/W2950697717","https://openalex.org/W2951954464","https://openalex.org/W2963800628","https://openalex.org/W2964339842","https://openalex.org/W2994943647","https://openalex.org/W3101442004","https://openalex.org/W3153133376","https://openalex.org/W4297798492","https://openalex.org/W6676947618","https://openalex.org/W6690047748","https://openalex.org/W6691895530","https://openalex.org/W6696831953","https://openalex.org/W6736179038","https://openalex.org/W6739847781","https://openalex.org/W6743660412","https://openalex.org/W6743802245","https://openalex.org/W6746518932","https://openalex.org/W6751885507","https://openalex.org/W6760278398","https://openalex.org/W6780225908","https://openalex.org/W6793857347"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,120],"explore":[4],"two":[5],"human-agent":[6,13],"collaboration":[7],"strate-gies":[8],"(human-designed":[9],"curriculum":[10,92,112,165],"learning":[11],"and":[12,81,89,144,153,183,197],"dialogue)":[14],"to":[15,35,47,60,132],"boost":[16],"Reinforcement":[17],"Learning":[18],"agent's":[19,193],"training":[20,68,114,159,178],"in":[21,49,98],"the":[22,37,56,62,69,83,91,95,104,110,116,122,130,158,168,172,180,192],"context":[23],"of":[24,79,94,101,141,148],"vision-grounded":[25],"instruction":[26,34],"following.":[27],"The":[28,44],"agent":[29,45,70,105,123,131],"is":[30,67,106],"given":[31],"a":[32,50,72,77,125,134,138,161,185],"text":[33],"fetch":[36],"described":[38],"object":[39],"or":[40],"switch":[41],"an":[42],"appliance.":[43],"needs":[46],"navigate":[48],"simulated":[51],"multi-room":[52],"environment,":[53],"interacts":[54],"with":[55,71,124,160,176],"objects,":[57],"furniture,":[58],"appliances":[59],"follow":[61],"instruction.":[63],"Our":[64],"first":[65,107],"strategy":[66],"human-designed":[73,111],"curriculum.":[74],"We":[75],"create":[76],"series":[78],"subtasks":[80,88],"let":[82],"human":[84,135,186],"advisor":[85],"select":[86],"several":[87],"design":[90],"composed":[93],"selected":[96],"tasks":[97],"increasing":[99],"order":[100],"complexity.":[102],"Then":[103],"trained":[108],"on":[109,115,171,179],"before":[113],"target":[117,173,181],"task.":[118],"Secondly,":[119],"enhance":[121],"dialogue":[126,142,188],"module,":[127],"which":[128],"allows":[129],"query":[133],"collaborator":[136,187],"(with":[137],"limit":[139],"number":[140],"exchanges)":[143],"obtain":[145],"three":[146],"types":[147],"hints:":[149],"action":[150],"selection,":[151],"navigation":[152],"recognition.":[154],"Experiments":[155],"show":[156],"that":[157],"properly":[162],"designed":[163],"subtask":[164],"can":[166],"accelerate":[167],"performance":[169],"growth":[170],"task":[174,194],"compared":[175],"directly":[177],"task,":[182],"incorporating":[184],"mod-ule":[189],"further":[190],"improves":[191],"success":[195],"rate":[196],"route":[198],"efficiency.":[199]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}