{"id":"https://openalex.org/W4403791363","doi":"https://doi.org/10.1145/3664647.3681070","title":"Instance-Level Panoramic Audio-Visual Saliency Detection and Ranking","display_name":"Instance-Level Panoramic Audio-Visual Saliency Detection and Ranking","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791363","doi":"https://doi.org/10.1145/3664647.3681070"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681070","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd 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/A5088611866","display_name":"Ruohao Guo","orcid":"https://orcid.org/0000-0002-1091-272X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruohao Guo","raw_affiliation_strings":["National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1091-272X","affiliations":[{"raw_affiliation_string":"National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021184639","display_name":"Dantong Niu","orcid":"https://orcid.org/0009-0006-7421-5858"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dantong Niu","raw_affiliation_strings":["Berkeley AI Research, University of California, Berkeley, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0009-0006-7421-5858","affiliations":[{"raw_affiliation_string":"Berkeley AI Research, University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046273191","display_name":"Liao Qu","orcid":"https://orcid.org/0000-0001-5228-0348"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liao Qu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5228-0348","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054577986","display_name":"Yanyu Qi","orcid":"https://orcid.org/0009-0008-9931-7855"},"institutions":[{"id":"https://openalex.org/I52158045","display_name":"China Agricultural University","ror":"https://ror.org/04v3ywz14","country_code":"CN","type":"education","lineage":["https://openalex.org/I52158045"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyu Qi","raw_affiliation_strings":["College of Information and Electrical Engineering, China Agricultural University, Beijing, USA"],"raw_orcid":"https://orcid.org/0009-0008-9931-7855","affiliations":[{"raw_affiliation_string":"College of Information and Electrical Engineering, China Agricultural University, Beijing, USA","institution_ids":["https://openalex.org/I52158045"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113749469","display_name":"Shi Jun Ji","orcid":"https://orcid.org/0009-0009-4584-4569"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji Shi","raw_affiliation_strings":["National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-4584-4569","affiliations":[{"raw_affiliation_string":"National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033503889","display_name":"Wenzhen Yue","orcid":"https://orcid.org/0000-0002-5165-0869"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhen Yue","raw_affiliation_strings":["National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5165-0869","affiliations":[{"raw_affiliation_string":"National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028438544","display_name":"Bowei Xing","orcid":"https://orcid.org/0009-0001-3254-3902"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowei Xing","raw_affiliation_strings":["National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-3254-3902","affiliations":[{"raw_affiliation_string":"National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103205579","display_name":"Taiyan Chen","orcid":"https://orcid.org/0000-0001-9957-9144"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Taiyan Chen","raw_affiliation_strings":["National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9957-9144","affiliations":[{"raw_affiliation_string":"National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015981200","display_name":"Xianghua Ying","orcid":"https://orcid.org/0000-0002-9785-0727"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianghua Ying","raw_affiliation_strings":["National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9785-0727","affiliations":[{"raw_affiliation_string":"National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5088611866"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22611503,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9426","last_page":"9434"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12032","display_name":"Multisensory perception and integration","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T12032","display_name":"Multisensory perception and integration","score":0.9987000226974487,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9969000220298767,"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/T12496","display_name":"Color perception and design","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7541326284408569},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7485944628715515},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5207205414772034},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49303480982780457},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.44685959815979004},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44648364186286926},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2113085687160492}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541326284408569},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7485944628715515},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5207205414772034},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49303480982780457},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.44685959815979004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44648364186286926},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2113085687160492}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681070","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2056135328","https://openalex.org/W2076756823","https://openalex.org/W2113708607","https://openalex.org/W2162681317","https://openalex.org/W2165371202","https://openalex.org/W2194775991","https://openalex.org/W2559655401","https://openalex.org/W2596164567","https://openalex.org/W2605929543","https://openalex.org/W2894404285","https://openalex.org/W2895250390","https://openalex.org/W2895340898","https://openalex.org/W2955084925","https://openalex.org/W2963112696","https://openalex.org/W2987701848","https://openalex.org/W2997217064","https://openalex.org/W2997487053","https://openalex.org/W2998449272","https://openalex.org/W3034185160","https://openalex.org/W3034287518","https://openalex.org/W3034728336","https://openalex.org/W3034965397","https://openalex.org/W3035422681","https://openalex.org/W3048939150","https://openalex.org/W3090469840","https://openalex.org/W3099638501","https://openalex.org/W3107944836","https://openalex.org/W3109623941","https://openalex.org/W3170511209","https://openalex.org/W3171516518","https://openalex.org/W4214542306","https://openalex.org/W4221142197","https://openalex.org/W4298140583","https://openalex.org/W4301409532","https://openalex.org/W4313123347","https://openalex.org/W4385823188","https://openalex.org/W4387969495","https://openalex.org/W4387969528","https://openalex.org/W4392152057","https://openalex.org/W6948380196"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Panoramic":[0],"audio-visual":[1,87,92],"saliency":[2,46,106,120,143],"detection":[3,144],"is":[4,132,150],"to":[5,34,62,81,90,99,110],"segment":[6],"the":[7,20,53,111,118,123,139],"most":[8],"attention-attractive":[9],"regions":[10,23],"in":[11,70],"360\u00b0":[12],"panoramic":[13,71,83],"videos":[14],"with":[15],"sound.":[16],"To":[17],"meticulously":[18],"delineate":[19],"detected":[21],"salient":[22,40,68],"and":[24,43,64,94,103,145],"effectively":[25],"model":[26,131],"human":[27],"attention":[28],"shift,":[29],"we":[30,51,116],"extend":[31],"this":[32,49],"task":[33],"more":[35],"fine-grained":[36],"instance":[37],"scenarios:":[38],"identifying":[39],"object":[41,97],"instances":[42,102],"inferring":[44],"their":[45,105],"ranks.":[47],"In":[48],"paper,":[50],"propose":[52],"first":[54],"instance-level":[55],"framework":[56],"that":[57,129],"can":[58],"simultaneously":[59],"be":[60],"applied":[61],"segmentation":[63],"ranking":[65,146],"of":[66,76,113,134],"multiple":[67],"objects":[69],"videos.":[72],"Specifically,":[73],"it":[74],"consists":[75],"a":[77,85,95],"distortion-aware":[78],"pixel":[79],"decoder":[80,98],"overcome":[82],"distortions,":[84],"sequential":[86],"fusion":[88],"module":[89],"integrate":[91],"information,":[93],"spatio-temporal":[96],"separate":[100],"individual":[101],"predict":[104],"scores.":[107],"Moreover,":[108],"owing":[109],"absence":[112],"such":[114],"annotations,":[115],"create":[117],"ground-truth":[119],"ranks":[121],"for":[122,141],"PAVS10K":[124,140],"benchmark.":[125],"Extensive":[126],"experiments":[127],"demonstrate":[128],"our":[130],"capable":[133],"achieving":[135],"state-of-the-art":[136],"performance":[137],"on":[138],"both":[142],"tasks.":[147],"The":[148],"code":[149],"available":[151],"at":[152],"https://github.com/ruohaoguo/pavsodr.":[153]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}