{"id":"https://openalex.org/W2074615241","doi":"https://doi.org/10.1145/1101149.1101224","title":"Recognition of hands-free speech and hand pointing action for conversational TV","display_name":"Recognition of hands-free speech and hand pointing action for conversational TV","publication_year":2005,"publication_date":"2005-11-06","ids":{"openalex":"https://openalex.org/W2074615241","doi":"https://doi.org/10.1145/1101149.1101224","mag":"2074615241"},"language":"en","primary_location":{"id":"doi:10.1145/1101149.1101224","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1101149.1101224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th annual ACM international conference on Multimedia","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/A5040766342","display_name":"Yasuo Ariki","orcid":"https://orcid.org/0000-0003-3473-2026"},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yasuo Ariki","raw_affiliation_strings":["Kobe University, Kobe, Japan","[Kobe University, Kobe, JAPAN]"],"affiliations":[{"raw_affiliation_string":"Kobe University, Kobe, Japan","institution_ids":["https://openalex.org/I65837984"]},{"raw_affiliation_string":"[Kobe University, Kobe, JAPAN]","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009283470","display_name":"Tetsuya Takiguchi","orcid":"https://orcid.org/0000-0001-5005-7679"},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Takiguchi","raw_affiliation_strings":["Kobe University, Kobe, Japan","[Kobe University, Kobe, JAPAN]"],"affiliations":[{"raw_affiliation_string":"Kobe University, Kobe, Japan","institution_ids":["https://openalex.org/I65837984"]},{"raw_affiliation_string":"[Kobe University, Kobe, JAPAN]","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109409177","display_name":"Atsushi Sako","orcid":null},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Sako","raw_affiliation_strings":["Kobe University, Kobe, Japan","[Kobe University, Kobe, JAPAN]"],"affiliations":[{"raw_affiliation_string":"Kobe University, Kobe, Japan","institution_ids":["https://openalex.org/I65837984"]},{"raw_affiliation_string":"[Kobe University, Kobe, JAPAN]","institution_ids":["https://openalex.org/I65837984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5040766342"],"corresponding_institution_ids":["https://openalex.org/I65837984"],"apc_list":null,"apc_paid":null,"fwci":0.9538,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75197216,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"355","last_page":"358"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9990000128746033,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8239400386810303},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5770368576049805},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5527464747428894},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5332517027854919},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.46428051590919495},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.448533833026886},{"id":"https://openalex.org/keywords/ask-price","display_name":"Ask price","score":0.44611436128616333},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4439474046230316},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4185386300086975},{"id":"https://openalex.org/keywords/front","display_name":"Front (military)","score":0.4108961820602417},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3941378891468048},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38283318281173706},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3711101710796356},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33937227725982666},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08293581008911133}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8239400386810303},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5770368576049805},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5527464747428894},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5332517027854919},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.46428051590919495},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.448533833026886},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.44611436128616333},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4439474046230316},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4185386300086975},{"id":"https://openalex.org/C2777551076","wikidata":"https://www.wikidata.org/wiki/Q842332","display_name":"Front (military)","level":2,"score":0.4108961820602417},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3941378891468048},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38283318281173706},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3711101710796356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33937227725982666},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08293581008911133},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1101149.1101224","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1101149.1101224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th annual ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2113416157","https://openalex.org/W2128552633","https://openalex.org/W2130432819","https://openalex.org/W4247773827","https://openalex.org/W6678974005"],"related_works":["https://openalex.org/W2168627904","https://openalex.org/W2515552481","https://openalex.org/W1570348318","https://openalex.org/W2015444353","https://openalex.org/W3013494979","https://openalex.org/W156769215","https://openalex.org/W4308101915","https://openalex.org/W3194047734","https://openalex.org/W2251005117","https://openalex.org/W2396112788"],"abstract_inverted_index":{"In":[0,49,75],"this":[1,99],"paper,":[2],"we":[3,16],"propose":[4],"a":[5,10],"structure":[6,72],"and":[7,24,45,60,64,70,82,116],"components":[8],"of":[9,37,40,66],"conversational":[11,33,100],"television":[12],"set(TV)":[13],"to":[14,87],"which":[15],"can":[17],"ask":[18],"anything":[19],"on":[20],"the":[21,26,30,50,67,71,76,89],"broadcasted":[22,54],"contents":[23,55],"receive":[25],"interesting":[27],"information":[28,110],"from":[29],"TV.":[31],"The":[32],"TV":[34,101],"is":[35],"composed":[36],"two":[38],"types":[39],"processing;":[41],"back":[42,51],"end":[43,47,52,78],"processing":[44],"front":[46,77],"processing.":[48],"processing,":[53,79],"are":[56,73,85],"analyzed":[57],"using":[58],"speech":[59,81],"video":[61,118],"recognition":[62],"techniques":[63],"both":[65],"meta":[68],"data":[69],"extracted.":[74],"human":[80,109],"hand":[83],"action":[84],"recognized":[86],"understand":[88],"user":[90],"intention.":[91],"We":[92],"show":[93],"some":[94],"applications,":[95],"being":[96],"developed":[97],"in":[98,114],"with":[102,120],"multi-modal":[103],"interactions,":[104],"such":[105],"as":[106],"word":[107],"explanation,":[108],"retrieval,":[111],"event":[112],"retrieval":[113],"soccer":[115],"baseball":[117],"games":[119],"contextual":[121],"awareness.":[122]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
