{"id":"https://openalex.org/W4367318798","doi":"https://doi.org/10.1145/3543873.3584655","title":"Visual Item Selection With Voice Assistants","display_name":"Visual Item Selection With Voice Assistants","publication_year":2023,"publication_date":"2023-04-28","ids":{"openalex":"https://openalex.org/W4367318798","doi":"https://doi.org/10.1145/3543873.3584655"},"language":"en","primary_location":{"id":"doi:10.1145/3543873.3584655","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543873.3584655","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543873.3584655","source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3543873.3584655","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081500689","display_name":"Prashan Wanigasekara","orcid":"https://orcid.org/0000-0002-9453-9933"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prashan Wanigasekara","raw_affiliation_strings":["Amazon, USA"],"raw_orcid":"https://orcid.org/0000-0002-9453-9933","affiliations":[{"raw_affiliation_string":"Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086673828","display_name":"Rafid Al-Humaimidi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rafid Al-Humaimidi","raw_affiliation_strings":["Amazon, Canada"],"raw_orcid":"https://orcid.org/0000-0001-8141-2629","affiliations":[{"raw_affiliation_string":"Amazon, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061554003","display_name":"Turan Gojayev","orcid":"https://orcid.org/0000-0002-2233-4568"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Turan Gojayev","raw_affiliation_strings":["Amazon, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2233-4568","affiliations":[{"raw_affiliation_string":"Amazon, Germany","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028484716","display_name":"Niloofar Gheissari","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Niloofar Gheissari","raw_affiliation_strings":["Amazon, USA"],"raw_orcid":"https://orcid.org/0000-0002-8219-507X","affiliations":[{"raw_affiliation_string":"Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045047925","display_name":"Achal Dave","orcid":"https://orcid.org/0000-0003-1948-5629"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Achal Dave","raw_affiliation_strings":["Amazon, USA"],"raw_orcid":"https://orcid.org/0000-0003-1948-5629","affiliations":[{"raw_affiliation_string":"Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046697900","display_name":"Stephen Rawls","orcid":"https://orcid.org/0000-0001-8716-2528"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen Rawls","raw_affiliation_strings":["Amazon, USA"],"raw_orcid":"https://orcid.org/0000-0001-8716-2528","affiliations":[{"raw_affiliation_string":"Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021881595","display_name":"Fan Yang","orcid":"https://orcid.org/0000-0001-5924-6935"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":["Amazon, USA"],"raw_orcid":"https://orcid.org/0000-0001-5924-6935","affiliations":[{"raw_affiliation_string":"Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011353616","display_name":"Kechen Qin","orcid":"https://orcid.org/0000-0003-3169-575X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kechen Qin","raw_affiliation_strings":["Amazon, USA"],"raw_orcid":"https://orcid.org/0000-0003-3169-575X","affiliations":[{"raw_affiliation_string":"Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033852016","display_name":"Nalin Gupta","orcid":"https://orcid.org/0000-0001-8294-1514"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nalin Gupta","raw_affiliation_strings":["Amazon, USA"],"raw_orcid":"https://orcid.org/0000-0001-8294-1514","affiliations":[{"raw_affiliation_string":"Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001337410","display_name":"Spurthi Sandiri","orcid":"https://orcid.org/0000-0002-2034-6207"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Spurthi Sandiri","raw_affiliation_strings":["Amazon, USA"],"raw_orcid":"https://orcid.org/0000-0002-2034-6207","affiliations":[{"raw_affiliation_string":"Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028417753","display_name":"Chevanthie Dissanayake","orcid":"https://orcid.org/0000-0003-4790-5328"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chevanthie Dissanayake","raw_affiliation_strings":["Amazon, USA"],"raw_orcid":"https://orcid.org/0000-0003-4790-5328","affiliations":[{"raw_affiliation_string":"Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030676855","display_name":"Zeynab Raeesy","orcid":"https://orcid.org/0000-0002-7153-1963"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeynab Raeesy","raw_affiliation_strings":["Amazon, USA"],"raw_orcid":"https://orcid.org/0000-0002-7153-1963","affiliations":[{"raw_affiliation_string":"Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017523558","display_name":"Emre Barut","orcid":"https://orcid.org/0000-0003-3064-6227"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emre Barut","raw_affiliation_strings":["Amazon, USA"],"raw_orcid":"https://orcid.org/0000-0003-3064-6227","affiliations":[{"raw_affiliation_string":"Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043281010","display_name":"Chengwei Su","orcid":"https://orcid.org/0000-0003-1492-723X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chengwei Su","raw_affiliation_strings":["Amazon, USA"],"raw_orcid":"https://orcid.org/0000-0003-1492-723X","affiliations":[{"raw_affiliation_string":"Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":14,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1123,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.3638093,"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":"500","last_page":"507"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"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":0.9993000030517578,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9771999716758728,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9768999814987183,"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/selection","display_name":"Selection (genetic algorithm)","score":0.7260547280311584},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7170461416244507},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4551127552986145},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39052578806877136},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3631414473056793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33844155073165894},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3202403783798218}],"concepts":[{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.7260547280311584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7170461416244507},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4551127552986145},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39052578806877136},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3631414473056793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33844155073165894},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3202403783798218}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3543873.3584655","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543873.3584655","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543873.3584655","source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3543873.3584655","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543873.3584655","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543873.3584655","source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4367318798.pdf","grobid_xml":"https://content.openalex.org/works/W4367318798.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2157364932","https://openalex.org/W2471768434","https://openalex.org/W2767026327","https://openalex.org/W2783914869","https://openalex.org/W2792276797","https://openalex.org/W2897905870","https://openalex.org/W2908510526","https://openalex.org/W2948667103","https://openalex.org/W2950339971","https://openalex.org/W2966944438","https://openalex.org/W3026458074","https://openalex.org/W3172514680","https://openalex.org/W4200632403","https://openalex.org/W4213308103","https://openalex.org/W4229042118","https://openalex.org/W4287330208","https://openalex.org/W4290927857","https://openalex.org/W4292828970","https://openalex.org/W4310749372","https://openalex.org/W4312781034","https://openalex.org/W4312940158","https://openalex.org/W4312956471","https://openalex.org/W6912494966"],"related_works":["https://openalex.org/W4205762803","https://openalex.org/W2535856026","https://openalex.org/W2265065644","https://openalex.org/W2134699697","https://openalex.org/W3017188156","https://openalex.org/W2322875716","https://openalex.org/W2383516975","https://openalex.org/W2374878784","https://openalex.org/W2147679489","https://openalex.org/W2371642785"],"abstract_inverted_index":{"Interacting":[0],"with":[1,133],"voice":[2,22,54,87],"assistants,":[3],"such":[4],"as":[5,225],"Amazon":[6,129],"Alexa":[7,227,231],"to":[8,27,34,66,124,206],"aid":[9],"in":[10,18,103,208,229],"day-to-day":[11],"tasks":[12],"has":[13],"become":[14],"a":[15,79,113,134,139,213],"ubiquitous":[16],"phenomenon":[17],"modern-day":[19],"households.":[20],"These":[21],"assistants":[23,55],"often":[24],"have":[25,178],"screens":[26],"provide":[28],"visual":[29,64,82,93,192,220],"content":[30,68,94],"(e.g.,":[31,72],"images,":[32],"videos)":[33],"their":[35],"users.":[36],"There":[37],"is":[38,89,223],"an":[39,128,189,226],"increasing":[40],"trend":[41],"of":[42,91,204],"users":[43],"shopping":[44,83,193,221],"or":[45,60],"searching":[46],"for":[47,162,182],"products":[48],"using":[49,106],"these":[50,53,160],"devices,":[51],"yet,":[52],"do":[56],"not":[57],"support":[58],"commands":[59],"queries":[61],"that":[62,167,217],"contain":[63],"references":[65],"the":[67,86,92,97,101,163,183,198,230],"shown":[69,95],"on":[70,96,127,188],"screen":[71,98],"\u201cblue":[73],"one\u201d,":[74],"\u201cred":[75],"dress\u201d).":[76],"We":[77,111,136,165],"introduce":[78],"novel":[80],"multi-modal":[81,109,154],"experience":[84],"where":[85],"assistant":[88,222],"aware":[90],"and":[99,145,156,175],"assists":[100],"user":[102],"item":[104],"selection":[105],"natural":[107],"language":[108],"interactions.":[110],"detail":[112],"practical,":[114],"lightweight":[115],"end-to-end":[116],"system":[117],"architecture":[118],"spanning":[119],"from":[120,159],"model":[121],"fine-tuning,":[122],"deployment,":[123],"skill":[125],"invocation":[126],"Echo":[130],"family":[131],"device":[132],"screen.":[135],"also":[137],"define":[138],"niche":[140],"\u201cVisual":[141,184],"Item":[142,185],"Selection\u201d":[143,186],"task":[144,187],"evaluate":[146],"whether":[147],"we":[148,200],"can":[149],"effectively":[150],"leverage":[151],"publicly":[152],"available":[153,224],"models,":[155],"embeddings":[157,171],"produced":[158],"models":[161],"task.":[164],"show":[166],"open":[168],"source":[169],"contrastive":[170],"like":[172],"CLIP":[173],"[30]":[174],"ALBEF":[176],"[24]":[177],"zero-shot":[179],"accuracy":[180,210],"above":[181],"internally":[190],"collected":[191],"dataset.":[194],"By":[195],"further":[196,202],"fine-tuning":[197],"embeddings,":[199],"obtain":[201],"gains":[203],"8.6%":[205],"24.0%":[207],"relative":[209],"improvement":[211],"over":[212],"baseline.":[214],"The":[215],"technology":[216],"enables":[218],"our":[219],"Skill":[228],"Skills":[232],"store.":[233]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
