{"id":"https://openalex.org/W3170655219","doi":"https://doi.org/10.1109/icme51207.2021.9428415","title":"Lavs: A Lightweight Audio-Visual Saliency Prediction Model","display_name":"Lavs: A Lightweight Audio-Visual Saliency Prediction Model","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3170655219","doi":"https://doi.org/10.1109/icme51207.2021.9428415","mag":"3170655219"},"language":"en","primary_location":{"id":"doi:10.1109/icme51207.2021.9428415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","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/A5002554183","display_name":"Dandan Zhu","orcid":"https://orcid.org/0000-0003-0329-6321"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dandan Zhu","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence","MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112669161","display_name":"Defang Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I97750245","display_name":"Software (Spain)","ror":"https://ror.org/02ethns06","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210087817","https://openalex.org/I97750245"]},{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN","ES"],"is_corresponding":false,"raw_author_name":"Defang Zhao","raw_affiliation_strings":["Tongji University,School of Software Engineering","School of Software Engineering, Tongji University"],"affiliations":[{"raw_affiliation_string":"Tongji University,School of Software Engineering","institution_ids":["https://openalex.org/I116953780","https://openalex.org/I97750245"]},{"raw_affiliation_string":"School of Software Engineering, Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043405654","display_name":"Xiongkuo Min","orcid":"https://orcid.org/0000-0001-5693-0416"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiongkuo Min","raw_affiliation_strings":["Shanghai Jiao Tong University,Institute of Image Communication and Network Engineering","Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Institute of Image Communication and Network Engineering","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101662991","display_name":"Tian Han","orcid":"https://orcid.org/0000-0001-8080-3791"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tian Han","raw_affiliation_strings":["Stevens Institute of Technology,Department of Computer Science","Department of Computer Science, Stevens Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Stevens Institute of Technology,Department of Computer Science","institution_ids":["https://openalex.org/I108468826"]},{"raw_affiliation_string":"Department of Computer Science, Stevens Institute of Technology","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085080585","display_name":"Qiangqiang Zhou","orcid":"https://orcid.org/0000-0002-5717-3290"},"institutions":[{"id":"https://openalex.org/I53592917","display_name":"Jiangxi Normal University","ror":"https://ror.org/05nkgk822","country_code":"CN","type":"education","lineage":["https://openalex.org/I53592917"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiangqiang Zhou","raw_affiliation_strings":["Jiangxi Normal University,School of Software","School of Software, Jiangxi Normal University"],"affiliations":[{"raw_affiliation_string":"Jiangxi Normal University,School of Software","institution_ids":["https://openalex.org/I53592917"]},{"raw_affiliation_string":"School of Software, Jiangxi Normal University","institution_ids":["https://openalex.org/I53592917"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055576349","display_name":"Shaobo Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaobo Yu","raw_affiliation_strings":["East China Normal University,Information Technology Services","Information Technology Services, East China Normal University"],"affiliations":[{"raw_affiliation_string":"East China Normal University,Information Technology Services","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"Information Technology Services, East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101823236","display_name":"Yongqing Chen","orcid":"https://orcid.org/0000-0002-8502-1809"},"institutions":[{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqing Chen","raw_affiliation_strings":["Hainan University,College of Information and Communication","College of Information and Communication, Hainan University"],"affiliations":[{"raw_affiliation_string":"Hainan University,College of Information and Communication","institution_ids":["https://openalex.org/I20942203"]},{"raw_affiliation_string":"College of Information and Communication, Hainan University","institution_ids":["https://openalex.org/I20942203"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064168853","display_name":"Guangtao Zhai","orcid":"https://orcid.org/0000-0001-8165-9322"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangtao Zhai","raw_affiliation_strings":["Shanghai Jiao Tong University,Institute of Image Communication and Network Engineering","Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Institute of Image Communication and Network Engineering","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019708391","display_name":"Xiaokang Yang","orcid":"https://orcid.org/0000-0003-4029-3322"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaokang Yang","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence","MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5002554183"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.7685,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.73202614,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9987000226974487,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9987000226974487,"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/T12032","display_name":"Multisensory perception and integration","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.986299991607666,"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/computer-science","display_name":"Computer science","score":0.8611580729484558},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7639865875244141},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6455800533294678},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5771301984786987},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5122608542442322},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.502356767654419},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.48510515689849854},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.45816949009895325},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4503915011882782},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4440813660621643},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.435655802488327},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4313771724700928},{"id":"https://openalex.org/keywords/fixation","display_name":"Fixation (population genetics)","score":0.42707839608192444},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42195719480514526},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.41933396458625793},{"id":"https://openalex.org/keywords/sensory-cue","display_name":"Sensory cue","score":0.41872987151145935},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37326857447624207},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.373086541891098}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8611580729484558},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7639865875244141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6455800533294678},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5771301984786987},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5122608542442322},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.502356767654419},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.48510515689849854},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.45816949009895325},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4503915011882782},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4440813660621643},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.435655802488327},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4313771724700928},{"id":"https://openalex.org/C146249460","wikidata":"https://www.wikidata.org/wiki/Q2914991","display_name":"Fixation (population genetics)","level":3,"score":0.42707839608192444},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42195719480514526},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.41933396458625793},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.41872987151145935},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37326857447624207},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.373086541891098},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","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/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme51207.2021.9428415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2004294009","https://openalex.org/W2015394094","https://openalex.org/W2094432440","https://openalex.org/W2099329509","https://openalex.org/W2212216676","https://openalex.org/W2213100575","https://openalex.org/W2533370895","https://openalex.org/W2558906385","https://openalex.org/W2583180462","https://openalex.org/W2777280533","https://openalex.org/W2962965915","https://openalex.org/W2963604034","https://openalex.org/W2964114039","https://openalex.org/W2980565715","https://openalex.org/W2986131415","https://openalex.org/W3011154664","https://openalex.org/W3034873438","https://openalex.org/W3095348033","https://openalex.org/W3099561715","https://openalex.org/W3101840568","https://openalex.org/W3122238731","https://openalex.org/W6704477683","https://openalex.org/W6732940373","https://openalex.org/W6746123559","https://openalex.org/W6761548112","https://openalex.org/W6764953915","https://openalex.org/W6771491623","https://openalex.org/W6788940246"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W2027566071","https://openalex.org/W3196745875","https://openalex.org/W2020038037"],"abstract_inverted_index":{"Audio":[0],"information":[1],"is":[2],"essential":[3],"for":[4],"guiding":[5],"human":[6],"attention":[7,37,49],"and":[8,110,114,146,158],"visual":[9,30,36,42,48,113,134],"perception,":[10],"which":[11,131,166],"has":[12,24],"been":[13,25],"verified":[14],"by":[15],"many":[16],"comprehensive":[17],"psychological":[18],"studies.":[19],"However,":[20],"the":[21,34,85,93,102,112,156,162,168],"audio":[22,115,138],"modality":[23],"rather":[26],"neglected":[27],"in":[28,90,121],"modeling":[29],"attention,":[31],"most":[32],"of":[33,87,95,128,161],"current":[35,45],"models":[38,50],"heavily":[39],"depend":[40],"on":[41,52],"information.":[43],"Additionally,":[44],"existing":[46],"high-performing":[47],"rely":[51],"deeper":[53],"convolution":[54],"neural":[55],"networks":[56],"(CNNs),":[57],"benefiting":[58],"from":[59],"their":[60],"extraordinary":[61],"feature":[62],"learning":[63],"ability":[64],"but":[65],"incurring":[66],"high":[67],"computational":[68],"cost.":[69],"To":[70,92],"this":[71],"end,":[72],"we":[73],"propose":[74],"a":[75,107],"novel":[76],"lightweight":[77,108],"audio-visual":[78,147],"saliency":[79,119,135,148],"(LAVS)":[80],"model":[81,100,126],"to":[82,105,117],"efficiently":[83],"address":[84],"problem":[86],"fixation":[88],"prediction":[89],"videos.":[91,122],"best":[94],"our":[96,98,124],"knowledge,":[97],"proposed":[99,125,163],"constitutes":[101],"first":[103],"attempt":[104],"exploit":[106],"network":[109],"combines":[111],"cues":[116],"perform":[118],"estimation":[120,136],"Specifically,":[123],"consists":[127],"four":[129],"modules,":[130],"are":[132],"spatial-temporal":[133],"module,":[137,141,145],"features":[139],"extraction":[140],"source":[142],"sound":[143],"localization":[144],"fusion":[149],"module.":[150],"Extensive":[151],"experiments":[152],"across":[153],"datasets":[154],"validate":[155],"effectiveness":[157],"real-time":[159],"performance":[160],"LAVS":[164],"model,":[165],"outperforms":[167],"other":[169],"state-of-the-art":[170],"methods.":[171]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
