{"id":"https://openalex.org/W2897604988","doi":"https://doi.org/10.1145/3266302.3268997","title":"Bipolar Disorder Recognition via Multi-scale Discriminative Audio Temporal Representation","display_name":"Bipolar Disorder Recognition via Multi-scale Discriminative Audio Temporal Representation","publication_year":2018,"publication_date":"2018-10-15","ids":{"openalex":"https://openalex.org/W2897604988","doi":"https://doi.org/10.1145/3266302.3268997","mag":"2897604988"},"language":"en","primary_location":{"id":"doi:10.1145/3266302.3268997","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3266302.3268997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 on Audio/Visual Emotion Challenge and Workshop","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/A5023256496","display_name":"Zhengyin Du","orcid":"https://orcid.org/0000-0003-0338-4225"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhengyin Du","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100662467","display_name":"Weixin Li","orcid":"https://orcid.org/0000-0002-5093-5635"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weixin Li","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056972984","display_name":"Di Huang","orcid":"https://orcid.org/0000-0002-2412-9330"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Huang","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100398953","display_name":"Yunhong Wang","orcid":"https://orcid.org/0000-0001-8001-2703"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhong Wang","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023256496"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":3.468,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.93814228,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955000281333923,"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/T10860","display_name":"Speech and Audio Processing","score":0.9948999881744385,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.8897658586502075},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.888563871383667},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6696686744689941},{"id":"https://openalex.org/keywords/bipolar-disorder","display_name":"Bipolar disorder","score":0.5939635038375854},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5035519003868103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49302026629447937},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4758067727088928},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.42678070068359375},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4245380163192749},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4120280146598816},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40923601388931274},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.2314642369747162},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.21143320202827454},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1843353807926178}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8897658586502075},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.888563871383667},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6696686744689941},{"id":"https://openalex.org/C2776174506","wikidata":"https://www.wikidata.org/wiki/Q131755","display_name":"Bipolar disorder","level":3,"score":0.5939635038375854},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5035519003868103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49302026629447937},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4758067727088928},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.42678070068359375},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4245380163192749},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4120280146598816},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40923601388931274},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.2314642369747162},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.21143320202827454},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1843353807926178},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3266302.3268997","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3266302.3268997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 on Audio/Visual Emotion Challenge and Workshop","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G2386418191","display_name":null,"funder_award_id":"- 61673033","funder_id":"https://openalex.org/F4320335595","funder_display_name":"National Natural Science Foundation of China-Yunnan Joint Fund"}],"funders":[{"id":"https://openalex.org/F4320335595","display_name":"National Natural Science Foundation of China-Yunnan Joint Fund","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1935978687","https://openalex.org/W1966268437","https://openalex.org/W1976066595","https://openalex.org/W1988088279","https://openalex.org/W2000149402","https://openalex.org/W2005876975","https://openalex.org/W2013993289","https://openalex.org/W2016430603","https://openalex.org/W2052307027","https://openalex.org/W2056403322","https://openalex.org/W2071908578","https://openalex.org/W2085662862","https://openalex.org/W2097117768","https://openalex.org/W2102505790","https://openalex.org/W2104266187","https://openalex.org/W2106053110","https://openalex.org/W2117579057","https://openalex.org/W2150355110","https://openalex.org/W2183341477","https://openalex.org/W2239141610","https://openalex.org/W2530421149","https://openalex.org/W2530450399","https://openalex.org/W2531271152","https://openalex.org/W2531418142","https://openalex.org/W2531648894","https://openalex.org/W2746419079","https://openalex.org/W2766415998","https://openalex.org/W2767030624","https://openalex.org/W2767043218","https://openalex.org/W2767088461","https://openalex.org/W2894305195","https://openalex.org/W2897444637","https://openalex.org/W2919115771","https://openalex.org/W2949117887","https://openalex.org/W2953384591","https://openalex.org/W3098431772","https://openalex.org/W3099206234","https://openalex.org/W3134891749","https://openalex.org/W4236965008","https://openalex.org/W4256269049"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4378510483","https://openalex.org/W3040691452"],"abstract_inverted_index":{"Bipolar":[0],"disorder":[1],"(BD)":[2],"is":[3],"a":[4,10,45,78,86],"prevalent":[5],"mental":[6],"illness":[7],"which":[8,51],"has":[9],"negative":[11],"impact":[12],"on":[13,61,91,128],"work":[14],"and":[15,56,136],"social":[16],"function.":[17],"However,":[18],"bipolar":[19],"symptoms":[20],"are":[21,126],"episodic,":[22],"especially":[23],"with":[24],"irregular":[25],"variations":[26],"among":[27],"different":[28],"episodes,":[29],"making":[30],"BD":[31,71,82,106],"very":[32],"difficult":[33],"to":[34,65,76,95,108,118],"be":[35],"diagnosed":[36],"accurately.":[37],"To":[38],"solve":[39],"this":[40,42],"problem,":[41],"paper":[43],"presents":[44],"novel":[46,87],"audio-based":[47],"approach,":[48],"called":[49],"IncepLSTM,":[50],"effectively":[52],"integrates":[53],"Inception":[54],"module":[55],"Long":[57],"Short-Term":[58],"Memory":[59],"(LSTM)":[60],"the":[62,92,97,101,120,129,137,142],"feature":[63],"sequence":[64],"capture":[66],"multi-scale":[67],"temporal":[68],"information":[69],"for":[70],"recognition.":[72],"Moreover,":[73],"in":[74],"order":[75],"obtain":[77],"discriminative":[79],"representation":[80],"of":[81,104,115,122,144],"severity,":[83],"we":[84,111],"propose":[85],"severity-sensitive":[88],"loss":[89,94],"based":[90],"triplet":[93],"model":[96],"inter-severity":[98],"relationship.":[99],"Considering":[100],"small":[102],"scale":[103],"existing":[105],"corpus,":[107],"avoid":[109],"overfitting,":[110],"also":[112],"make":[113],"use":[114],"$L^1$":[116],"regulation":[117],"improve":[119],"sparsity":[121],"IncepLSTM.":[123],"The":[124],"evaluations":[125],"conducted":[127],"Audio/Visual":[130],"Emotion":[131],"Challenge":[132],"(AVEC)":[133],"2018":[134],"Dataset":[135],"experimental":[138],"results":[139],"clearly":[140],"demonstrate":[141],"effectiveness":[143],"our":[145],"method.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}