{"id":"https://openalex.org/W4402521406","doi":"https://doi.org/10.1145/3677386.3682095","title":"TAGGAR: General-Purpose Task Guidance from Natural Language in Augmented Reality using Vision-Language Models","display_name":"TAGGAR: General-Purpose Task Guidance from Natural Language in Augmented Reality using Vision-Language Models","publication_year":2024,"publication_date":"2024-09-13","ids":{"openalex":"https://openalex.org/W4402521406","doi":"https://doi.org/10.1145/3677386.3682095"},"language":"en","primary_location":{"id":"doi:10.1145/3677386.3682095","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3677386.3682095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Symposium on Spatial User Interaction","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/10919/121532","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107185076","display_name":"Daniel Stover","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142372","display_name":"Human Media","ror":"https://ror.org/04072nk43","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210142372"]},{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel Stover","raw_affiliation_strings":["Center for Human-Computer Interaction, Virginia Tech, United States"],"raw_orcid":"https://orcid.org/0009-0004-5358-8423","affiliations":[{"raw_affiliation_string":"Center for Human-Computer Interaction, Virginia Tech, United States","institution_ids":["https://openalex.org/I4210142372","https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069853790","display_name":"Doug A. Bowman","orcid":"https://orcid.org/0000-0003-0491-5067"},"institutions":[{"id":"https://openalex.org/I4210142372","display_name":"Human Media","ror":"https://ror.org/04072nk43","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210142372"]},{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Doug Bowman","raw_affiliation_strings":["Center for Human-Computer Interaction, Virginia Tech, United States"],"raw_orcid":"https://orcid.org/0000-0003-0491-5067","affiliations":[{"raw_affiliation_string":"Center for Human-Computer Interaction, Virginia Tech, United States","institution_ids":["https://openalex.org/I4210142372","https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5107185076"],"corresponding_institution_ids":["https://openalex.org/I4210142372","https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":1.6665,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.85377197,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10888","display_name":"Augmented Reality Applications","score":0.9991999864578247,"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/T10888","display_name":"Augmented Reality Applications","score":0.9991999864578247,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T13382","display_name":"Robotics and Automated Systems","score":0.9818999767303467,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/augmented-reality","display_name":"Augmented reality","score":0.8151752948760986},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7787012457847595},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6403086185455322},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.616500735282898},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5913955569267273},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.5486429929733276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46965518593788147},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42338353395462036},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10086551308631897}],"concepts":[{"id":"https://openalex.org/C153715457","wikidata":"https://www.wikidata.org/wiki/Q254183","display_name":"Augmented reality","level":2,"score":0.8151752948760986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7787012457847595},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6403086185455322},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.616500735282898},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5913955569267273},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.5486429929733276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46965518593788147},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42338353395462036},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10086551308631897},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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":2,"locations":[{"id":"doi:10.1145/3677386.3682095","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3677386.3682095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Symposium on Spatial User Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/121532","is_oa":true,"landing_page_url":"https://hdl.handle.net/10919/121532","pdf_url":null,"source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/121532","is_oa":true,"landing_page_url":"https://hdl.handle.net/10919/121532","pdf_url":null,"source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1991520109","https://openalex.org/W2001863204","https://openalex.org/W2059527995","https://openalex.org/W2070294837","https://openalex.org/W2606829066","https://openalex.org/W2735210942","https://openalex.org/W2967595425","https://openalex.org/W2990295915","https://openalex.org/W3029159807","https://openalex.org/W3080919758","https://openalex.org/W3117951887","https://openalex.org/W3160976423","https://openalex.org/W4225711378","https://openalex.org/W4231109964","https://openalex.org/W4294068621","https://openalex.org/W4324128075","https://openalex.org/W4366549390","https://openalex.org/W4392248128","https://openalex.org/W4395443981"],"related_works":["https://openalex.org/W2172197285","https://openalex.org/W2991048842","https://openalex.org/W2750280393","https://openalex.org/W2355696739","https://openalex.org/W3158001554","https://openalex.org/W2771909920","https://openalex.org/W1990434954","https://openalex.org/W3196817267","https://openalex.org/W1976600725","https://openalex.org/W2894473080"],"abstract_inverted_index":{"Augmented":[0],"reality":[1],"(AR)":[2],"task":[3,22,56,78],"guidance":[4,14,23,57,95,105,160,171],"systems":[5,24],"provide":[6],"assistance":[7],"for":[8,46,59,80,121,161],"procedural":[9],"tasks":[10,48,60,162],"by":[11,62,87],"rendering":[12],"virtual":[13],"visuals":[15,172],"within":[16],"the":[17,88,170,175,180,186],"real-world":[18,41],"environment.":[19],"Current":[20],"AR":[21,31,55],"are":[25,85],"limited":[26,47],"in":[27,146],"that":[28,152],"they":[29],"require":[30,38],"system":[32,89,134],"experts":[33],"to":[34,70,90,93,157,168,173],"manually":[35],"place":[36,94],"visuals,":[37],"models":[39,120],"of":[40,73,179,185],"objects,":[42],"or":[43,49,111],"only":[44],"function":[45],"environments.":[50,112],"We":[51,130,150],"propose":[52],"a":[53,132,147],"general-purpose":[54],"approach":[58,66,114,139],"defined":[61],"natural":[63],"language.":[64],"Our":[65,113],"allows":[67],"an":[68,81,98],"operator":[69],"take":[71],"pictures":[72],"relevant":[74],"objects":[75,108],"and":[76,103,123,127,140,144,163],"write":[77],"instructions":[79],"end":[82,99,164],"user,":[83],"which":[84],"used":[86],"determine":[91],"where":[92],"visuals.":[96],"Then,":[97],"user":[100,148],"can":[101],"receive":[102],"follow":[104,169],"even":[106],"if":[107],"change":[109],"locations":[110],"utilizes":[115],"current":[116],"vision-language":[117],"machine":[118],"learning":[119],"text":[122],"image":[124],"semantic":[125],"understanding":[126],"object":[128],"localization.":[129],"built":[131],"proof-of-concept":[133],"called":[135],"TAGGAR":[136],"using":[137],"our":[138],"tested":[141],"its":[142],"accuracy":[143],"usability":[145],"study.":[149],"found":[151],"all":[153],"operators":[154],"were":[155,166],"able":[156,167],"generate":[158],"clear":[159],"users":[165],"complete":[174],"expected":[176],"action":[177],"85.7%":[178],"time":[181],"without":[182],"any":[183],"knowledge":[184],"tasks.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}