{"id":"https://openalex.org/W4298140583","doi":"https://doi.org/10.1145/3565267","title":"PAV-SOD: A New Task towards Panoramic Audiovisual Saliency Detection","display_name":"PAV-SOD: A New Task towards Panoramic Audiovisual Saliency Detection","publication_year":2022,"publication_date":"2022-09-30","ids":{"openalex":"https://openalex.org/W4298140583","doi":"https://doi.org/10.1145/3565267"},"language":"en","primary_location":{"id":"doi:10.1145/3565267","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3565267","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-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/A5100388205","display_name":"Yi Zhang","orcid":"https://orcid.org/0000-0002-7110-5948"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I28221208","display_name":"Institut National des Sciences Appliqu\u00e9es de Rennes","ror":"https://ror.org/04xaa4j22","country_code":"FR","type":"education","lineage":["https://openalex.org/I28221208"]},{"id":"https://openalex.org/I4210100151","display_name":"Institut d'\u00c9lectronique et des Technologies du num\u00e9Rique","ror":"https://ror.org/013q33h79","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I28221208","https://openalex.org/I4210095849","https://openalex.org/I4210100151","https://openalex.org/I56067802","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["Univ Rennes, INSA Rennes, CNRS, IETR (UMR 6164), France"],"raw_orcid":"https://orcid.org/0000-0002-7110-5948","affiliations":[{"raw_affiliation_string":"Univ Rennes, INSA Rennes, CNRS, IETR (UMR 6164), France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I28221208","https://openalex.org/I4210100151","https://openalex.org/I56067802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025883253","display_name":"Fang-Yi Chao","orcid":"https://orcid.org/0000-0002-1212-1139"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Fang-Yi Chao","raw_affiliation_strings":["Trinity College Dublin, Ireland"],"raw_orcid":"https://orcid.org/0000-0002-1212-1139","affiliations":[{"raw_affiliation_string":"Trinity College Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084205574","display_name":"Wassim Hamidouche","orcid":"https://orcid.org/0000-0002-0143-1756"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I28221208","display_name":"Institut National des Sciences Appliqu\u00e9es de Rennes","ror":"https://ror.org/04xaa4j22","country_code":"FR","type":"education","lineage":["https://openalex.org/I28221208"]},{"id":"https://openalex.org/I4210100151","display_name":"Institut d'\u00c9lectronique et des Technologies du num\u00e9Rique","ror":"https://ror.org/013q33h79","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I28221208","https://openalex.org/I4210095849","https://openalex.org/I4210100151","https://openalex.org/I56067802","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Wassim Hamidouche","raw_affiliation_strings":["Univ Rennes, INSA Rennes, CNRS,IETR (UMR 6164), France"],"raw_orcid":"https://orcid.org/0000-0002-0143-1756","affiliations":[{"raw_affiliation_string":"Univ Rennes, INSA Rennes, CNRS,IETR (UMR 6164), France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I28221208","https://openalex.org/I4210100151","https://openalex.org/I56067802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031377954","display_name":"Olivier D\u00e9forges","orcid":"https://orcid.org/0000-0003-0750-0959"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I28221208","display_name":"Institut National des Sciences Appliqu\u00e9es de Rennes","ror":"https://ror.org/04xaa4j22","country_code":"FR","type":"education","lineage":["https://openalex.org/I28221208"]},{"id":"https://openalex.org/I4210100151","display_name":"Institut d'\u00c9lectronique et des Technologies du num\u00e9Rique","ror":"https://ror.org/013q33h79","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I28221208","https://openalex.org/I4210095849","https://openalex.org/I4210100151","https://openalex.org/I56067802","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier Deforges","raw_affiliation_strings":["Univ Rennes, INSA Rennes, CNRS,IETR (UMR 6164), France"],"raw_orcid":"https://orcid.org/0000-0003-0750-0959","affiliations":[{"raw_affiliation_string":"Univ Rennes, INSA Rennes, CNRS,IETR (UMR 6164), France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I28221208","https://openalex.org/I4210100151","https://openalex.org/I56067802"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5669,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.63130775,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"19","issue":"3","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":1.0,"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":1.0,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.9916999936103821,"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/T10971","display_name":"Olfactory and Sensory Function Studies","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/2809","display_name":"Sensory Systems"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8241703510284424},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.671522319316864},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6445310711860657},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5431089401245117},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.49595603346824646},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48718470335006714},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.45420145988464355},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4345962703227997},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3278734087944031}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8241703510284424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.671522319316864},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6445310711860657},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5431089401245117},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.49595603346824646},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48718470335006714},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.45420145988464355},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4345962703227997},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3278734087944031},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3565267","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3565267","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-04143186v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04143186","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications and Applications, 2023, 19 (3), pp.1-26. ⟨10.1145/3565267⟩","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":105,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1562683879","https://openalex.org/W1980120082","https://openalex.org/W2002781701","https://openalex.org/W2039313011","https://openalex.org/W2056135328","https://openalex.org/W2076756823","https://openalex.org/W2086791339","https://openalex.org/W2100470808","https://openalex.org/W2110019070","https://openalex.org/W2160613239","https://openalex.org/W2165371202","https://openalex.org/W2186222003","https://openalex.org/W2188365844","https://openalex.org/W2194775991","https://openalex.org/W2430408220","https://openalex.org/W2470139095","https://openalex.org/W2501148868","https://openalex.org/W2544224704","https://openalex.org/W2547489168","https://openalex.org/W2561270043","https://openalex.org/W2582117893","https://openalex.org/W2582998992","https://openalex.org/W2594112328","https://openalex.org/W2620871200","https://openalex.org/W2622036627","https://openalex.org/W2752782242","https://openalex.org/W2798665861","https://openalex.org/W2799064164","https://openalex.org/W2804610335","https://openalex.org/W2810323393","https://openalex.org/W2884414611","https://openalex.org/W2890855852","https://openalex.org/W2928165649","https://openalex.org/W2938260698","https://openalex.org/W2945809413","https://openalex.org/W2946520073","https://openalex.org/W2950388022","https://openalex.org/W2953050025","https://openalex.org/W2955060956","https://openalex.org/W2962865004","https://openalex.org/W2963112696","https://openalex.org/W2963115079","https://openalex.org/W2963529609","https://openalex.org/W2967085153","https://openalex.org/W2971242449","https://openalex.org/W2971680322","https://openalex.org/W2985335644","https://openalex.org/W2999222884","https://openalex.org/W3000351820","https://openalex.org/W3011305844","https://openalex.org/W3020127778","https://openalex.org/W3034287518","https://openalex.org/W3037994420","https://openalex.org/W3047800102","https://openalex.org/W3080686309","https://openalex.org/W3081459285","https://openalex.org/W3087221416","https://openalex.org/W3090469840","https://openalex.org/W3092603041","https://openalex.org/W3094502228","https://openalex.org/W3096182410","https://openalex.org/W3097053213","https://openalex.org/W3097336090","https://openalex.org/W3098389804","https://openalex.org/W3101834264","https://openalex.org/W3102351864","https://openalex.org/W3104836889","https://openalex.org/W3105290831","https://openalex.org/W3105352633","https://openalex.org/W3108948422","https://openalex.org/W3114848016","https://openalex.org/W3126725132","https://openalex.org/W3131182250","https://openalex.org/W3132018008","https://openalex.org/W3140428646","https://openalex.org/W3143835353","https://openalex.org/W3153167542","https://openalex.org/W3157043887","https://openalex.org/W3167142517","https://openalex.org/W3193033402","https://openalex.org/W3193915232","https://openalex.org/W3196679123","https://openalex.org/W3200224149","https://openalex.org/W3200689778","https://openalex.org/W3201519611","https://openalex.org/W3207718067","https://openalex.org/W3208569903","https://openalex.org/W3208937872","https://openalex.org/W4200436929","https://openalex.org/W4221167476","https://openalex.org/W4224330024","https://openalex.org/W4231358230","https://openalex.org/W4242177601","https://openalex.org/W4285072228","https://openalex.org/W4286851395","https://openalex.org/W4287684771","https://openalex.org/W4293665662","https://openalex.org/W4301409532","https://openalex.org/W4308663722","https://openalex.org/W4311415873","https://openalex.org/W6761176859","https://openalex.org/W6799779159","https://openalex.org/W6802635486","https://openalex.org/W6810980340"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W2086519370","https://openalex.org/W2028665553","https://openalex.org/W2087343574","https://openalex.org/W2535915176","https://openalex.org/W2732813147","https://openalex.org/W2143460112"],"abstract_inverted_index":{"Object-level":[0],"audiovisual":[1,228],"saliency":[2],"detection":[3,165],"in":[4,18,33,79],"360\u00b0":[5,80,193],"panoramic":[6,81],"real-life":[7,84],"dynamic":[8],"scenes":[9],"is":[10,242],"important":[11],"for":[12,22,101,130,280],"exploring":[13],"and":[14,29,41,124,134,144,189,227,241,263],"modeling":[15],"human":[16,77],"perception":[17],"immersive":[19,284],"environments,":[20],"also":[21],"aiding":[23],"the":[24,71,76,89,95,246],"development":[25],"of":[26,75,112,186,192,217],"virtual,":[27],"augmented,":[28],"mixed":[30],"reality":[31],"applications":[32],"fields":[34],"such":[35],"as":[36,276],"education,":[37],"social":[38],"network,":[39,182,222,226],"entertainment,":[40],"training.":[42],"To":[43,87],"this":[44],"end,":[45],"we":[46,91,177,256],"propose":[47,178],"a":[48,53,102,179,198,207,218,223,233,277],"new":[49,180,199],"task,":[50,90],"p":[51,97],"anoramic":[52,98],"udio":[54,103,208],"v":[55,104,209],"isual":[56,105,210],"s":[57,106],"alient":[58,107],"o":[59],"bject":[60],"d":[61],"etection,":[62],"(":[63],"PAV-SOD":[64,132,155,261,266],"1":[65],"),":[66],"which":[67,110,183],"aims":[68],"to":[69,244],"segment":[70],"objects":[72],"grasping":[73],"most":[74],"attention":[78],"videos":[82,116],"reflecting":[83],"daily":[85],"scenes.":[86],"support":[88],"collect":[92],"PAVS10K":[93,174,250],",":[94,133,215],"first":[96],"video":[99,138,194],"dataset":[100],"object":[108,164,167],"detection,":[109],"consists":[111,216],"67":[113],"4K-resolution":[114],"equirectangular":[115],"with":[117,140],"per-video":[118],"labels":[119],"including":[120],"hierarchical":[121],"scene":[122],"categories":[123],"associated":[125],"attributes":[126],"depicting":[127],"specific":[128],"challenges":[129,262],"conducting":[131],"10,465":[135],"uniformly":[136],"sampled":[137],"frames":[139,195],"manually":[141],"annotated":[142],"object-level":[143],"instance-level":[145],"pixel-wise":[146],"masks.":[147],"The":[148],"coarse-to-fine":[149],"annotations":[150],"enable":[151],"multi-perspective":[152],"analysis":[153],"regarding":[154],"modeling.":[156],"We":[157,269],"further":[158],"systematically":[159],"benchmark":[160],"13":[161],"state-of-the-art":[162],"salient":[163],"(SOD)/video":[166],"segmentation":[168,221],"(VOS)":[169],"methods":[170],"based":[171],"on":[172],"our":[173,235,272],".":[175,251],"Besides,":[176],"baseline":[181],"takes":[184],"advantage":[185],"both":[187],"visual":[188,220],"audio":[190],"cues":[191],"by":[196],"using":[197],"conditional":[200],"variational":[201],"auto-encoder":[202],"(CVAE).":[203],"Our":[204],"C":[205],"VAE-based":[206],"net":[211],"work,":[212],"namely,":[213],"CAV-Net":[214,236],"spatial-temporal":[219],"convolutional":[224],"audio-encoding":[225],"distribution":[229],"estimation":[230],"modules.":[231],"As":[232],"result,":[234],"outperforms":[237],"all":[238],"competing":[239],"models":[240],"able":[243],"estimate":[245],"aleatoric":[247],"uncertainties":[248],"within":[249],"With":[252],"extensive":[253],"experimental":[254],"results,":[255],"gain":[257],"several":[258],"findings":[259],"about":[260],"insights":[264],"towards":[265,283],"model":[267],"interpretability.":[268],"hope":[270],"that":[271],"work":[273],"could":[274],"serve":[275],"starting":[278],"point":[279],"advancing":[281],"SOD":[282],"media.":[285]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}