{"id":"https://openalex.org/W4392909798","doi":"https://doi.org/10.1109/icassp48485.2024.10447323","title":"Long-Term Social Interaction Context: The Key to Egocentric Addressee Detection","display_name":"Long-Term Social Interaction Context: The Key to Egocentric Addressee Detection","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909798","doi":"https://doi.org/10.1109/icassp48485.2024.10447323"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5084751425","display_name":"Deqian Kong","orcid":"https://orcid.org/0009-0001-3581-8836"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Deqian Kong","raw_affiliation_strings":["University of California,Los Angeles","University of California, Los Angeles"],"affiliations":[{"raw_affiliation_string":"University of California,Los Angeles","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"University of California, Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089586432","display_name":"Furqan Khan","orcid":"https://orcid.org/0000-0001-8333-5428"},"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":"Furqan Khan","raw_affiliation_strings":["Amazon AGI"],"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437225","display_name":"Xu Zhang","orcid":"https://orcid.org/0000-0002-3991-5748"},"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":"Xu Zhang","raw_affiliation_strings":["Amazon AGI"],"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103023794","display_name":"Prateek Singhal","orcid":"https://orcid.org/0000-0002-8776-0090"},"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":"Prateek Singhal","raw_affiliation_strings":["Amazon AGI"],"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101780958","display_name":"Ying Wu","orcid":"https://orcid.org/0009-0001-6768-5118"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Nian Wu","raw_affiliation_strings":["University of California,Los Angeles","University of California, Los Angeles"],"affiliations":[{"raw_affiliation_string":"University of California,Los Angeles","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"University of California, Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5084751425"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":0.5263,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61540569,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"8250","last_page":"8254"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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/T12031","display_name":"Speech and dialogue systems","score":0.9958000183105469,"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/T10028","display_name":"Topic Modeling","score":0.9947999715805054,"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":0.7841439247131348},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.6555194854736328},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.652458131313324},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6377739906311035},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6132277250289917},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.602759838104248},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.5771467685699463},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5463711023330688},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5004761219024658},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.45870646834373474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3225201666355133},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3224512040615082},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.18306031823158264},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.10470381379127502}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7841439247131348},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.6555194854736328},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.652458131313324},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6377739906311035},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6132277250289917},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.602759838104248},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5771467685699463},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5463711023330688},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5004761219024658},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.45870646834373474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3225201666355133},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3224512040615082},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.18306031823158264},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.10470381379127502},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1545326209","https://openalex.org/W1570557094","https://openalex.org/W2147806277","https://openalex.org/W2194775991","https://openalex.org/W2295794335","https://openalex.org/W2624871570","https://openalex.org/W2745199549","https://openalex.org/W2747419968","https://openalex.org/W2963323204","https://openalex.org/W2964222622","https://openalex.org/W2965373594","https://openalex.org/W3169129566","https://openalex.org/W3205786327","https://openalex.org/W3206008172","https://openalex.org/W4293363567","https://openalex.org/W4386113260","https://openalex.org/W6739365718","https://openalex.org/W6766673545","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2380179524","https://openalex.org/W4283365723","https://openalex.org/W2963001125","https://openalex.org/W2091233881","https://openalex.org/W2352366064","https://openalex.org/W4250820896","https://openalex.org/W2124102101","https://openalex.org/W4250305970","https://openalex.org/W1484550171","https://openalex.org/W2333383158"],"abstract_inverted_index":{"As":[0],"embodied":[1],"agents":[2,33],"learn":[3],"to":[4,11,16,34,38,43,47,127],"interact,":[5],"it":[6],"is":[7],"crucial":[8],"for":[9],"them":[10],"understand":[12],"when,":[13],"what,":[14],"and":[15,27,46,74],"whom":[17,48],"they":[18,40,49],"should":[19,50],"respond.":[20,51],"While":[21],"advances":[22],"in":[23,134],"natrual":[24],"language":[25],"processing":[26],"speech":[28],"technologies":[29],"have":[30],"enabled":[31],"conversational":[32],"focus":[35],"on":[36,71,107],"what":[37],"respond,":[39],"still":[41],"struggle":[42],"determine":[44],"when":[45],"In":[52],"this":[53],"paper,":[54],"we":[55,77],"address":[56],"the":[57,64,108,113,129,135],"addressee":[58],"detection":[59],"(Talking-To-Me,":[60],"TTM)":[61],"problem":[62],"under":[63],"egocentric":[65],"view.":[66],"Instead":[67],"of":[68,105,131],"relying":[69],"solely":[70],"short-term":[72],"audio":[73],"video":[75],"data,":[76],"propose":[78],"a":[79,100,123],"simple":[80],"architecture":[81],"SICNet":[82],"with":[83],"self/cross-modality":[84],"attention":[85],"that":[86],"leverages":[87],"long-term":[88,94,136],"social":[89,137],"interaction":[90,138],"context.":[91,139],"By":[92],"leveraging":[93],"information,":[95],"our":[96],"approach":[97],"has":[98],"achieved":[99],"mean":[101],"Average":[102],"Precision":[103],"(mAP)":[104],"68.98%":[106],"Ego4D":[109],"TTM":[110],"task,":[111],"surpassing":[112],"previous":[114],"state-of-the-art":[115],"single-task":[116],"model":[117],"by":[118],"10.07%.":[119],"We":[120],"also":[121],"conducted":[122],"detailed":[124],"ablation":[125],"study":[126],"demonstrate":[128],"effectiveness":[130],"each":[132],"component":[133]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}