{"id":"https://openalex.org/W4403319665","doi":"https://doi.org/10.1145/3698881","title":"Audio-Visual Saliency Prediction Model with Implicit Neural Representation","display_name":"Audio-Visual Saliency Prediction Model with Implicit Neural Representation","publication_year":2024,"publication_date":"2024-10-11","ids":{"openalex":"https://openalex.org/W4403319665","doi":"https://doi.org/10.1145/3698881"},"language":"en","primary_location":{"id":"doi:10.1145/3698881","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3698881","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3698881","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":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3698881","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101917050","display_name":"Nana Zhang","orcid":"https://orcid.org/0000-0002-9843-5269"},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nana Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Donghua University, Shanghai, China","School of Computer Science and Technology, Donghua University, China"],"raw_orcid":"https://orcid.org/0000-0002-9843-5269","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Donghua University, Shanghai, China","institution_ids":["https://openalex.org/I181326427"]},{"raw_affiliation_string":"School of Computer Science and Technology, Donghua University, China","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101096690","display_name":"Min Xiong","orcid":"https://orcid.org/0009-0001-9393-8975"},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Xiong","raw_affiliation_strings":["School of Computer Science and Technology, Donghua University, Shanghai, China","School of Computer Science and Technology, Donghua University, China"],"raw_orcid":"https://orcid.org/0009-0001-9393-8975","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Donghua University, Shanghai, China","institution_ids":["https://openalex.org/I181326427"]},{"raw_affiliation_string":"School of Computer Science and Technology, Donghua University, China","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"middle","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"]},{"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":"Dandan Zhu","raw_affiliation_strings":["Institute of AI Education, East China Normal University, Shanghai, China and Key Laboratory of Artificial Intelligence, Ministry of Education, Shanghai Jiao Tong University, Shanghai, China","Institute of AI Education, Shanghai, East China Normal University, China and Key Laboratory of Artificial Intelligence, Ministry of Education, Shanghai Jiao Tong University, China"],"raw_orcid":"https://orcid.org/0000-0003-0329-6321","affiliations":[{"raw_affiliation_string":"Institute of AI Education, East China Normal University, Shanghai, China and Key Laboratory of Artificial Intelligence, Ministry of Education, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"Institute of AI Education, Shanghai, East China Normal University, China and Key Laboratory of Artificial Intelligence, Ministry of Education, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930","https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101790399","display_name":"Kun Zhu","orcid":"https://orcid.org/0000-0002-5773-5089"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Kun Zhu","raw_affiliation_strings":["Key Laboratory of Embedded System and Service Computing, Ministry of Education, Tongji University, Shanghai, China","Key Laboratory of Embedded System and Service Computing, Ministry of Education, Tongji University, China"],"raw_orcid":"https://orcid.org/0000-0002-5773-5089","affiliations":[{"raw_affiliation_string":"Key Laboratory of Embedded System and Service Computing, Ministry of Education, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Key Laboratory of Embedded System and Service Computing, Ministry of Education, Tongji University, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109998714","display_name":"Guangtao Zhai","orcid":null},"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":["Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China","Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, China"],"raw_orcid":"https://orcid.org/0000-0001-8165-9322","affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113429102","display_name":"Xiaokang Yang","orcid":null},"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":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China"],"raw_orcid":"https://orcid.org/0000-0003-4029-3322","affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12730764,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":"4","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9966999888420105,"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":0.9966999888420105,"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":0.9930999875068665,"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"}},{"id":"https://openalex.org/T12032","display_name":"Multisensory perception and integration","score":0.9901000261306763,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9062220454216003},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5918699502944946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4719119369983673},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.44928669929504395},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38307973742485046},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34348171949386597},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1560213565826416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9062220454216003},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5918699502944946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4719119369983673},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.44928669929504395},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38307973742485046},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34348171949386597},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1560213565826416},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3698881","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3698881","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3698881","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"}],"best_oa_location":{"id":"doi:10.1145/3698881","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3698881","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3698881","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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1118802410","display_name":null,"funder_award_id":"2232024D-25","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2685695899","display_name":null,"funder_award_id":"62377011, 62302337, 62402098","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4403319665.pdf"},"referenced_works_count":70,"referenced_works":["https://openalex.org/W1152443276","https://openalex.org/W1497599070","https://openalex.org/W1510835000","https://openalex.org/W1988712925","https://openalex.org/W1996721809","https://openalex.org/W2026393195","https://openalex.org/W2078903912","https://openalex.org/W2106752067","https://openalex.org/W2111990464","https://openalex.org/W2119577735","https://openalex.org/W2128272608","https://openalex.org/W2130184867","https://openalex.org/W2146103513","https://openalex.org/W2149095485","https://openalex.org/W2155479901","https://openalex.org/W2186222003","https://openalex.org/W2212216676","https://openalex.org/W2288514685","https://openalex.org/W2403373496","https://openalex.org/W2442293398","https://openalex.org/W2498738402","https://openalex.org/W2528092473","https://openalex.org/W2529272619","https://openalex.org/W2533370895","https://openalex.org/W2561270043","https://openalex.org/W2583180462","https://openalex.org/W2612135493","https://openalex.org/W2731833015","https://openalex.org/W2748092049","https://openalex.org/W2904232353","https://openalex.org/W2912083425","https://openalex.org/W2927638312","https://openalex.org/W2930163499","https://openalex.org/W2946520073","https://openalex.org/W2955060956","https://openalex.org/W2962965915","https://openalex.org/W2963339238","https://openalex.org/W2963503775","https://openalex.org/W2964109005","https://openalex.org/W2969741484","https://openalex.org/W2971688562","https://openalex.org/W2980565715","https://openalex.org/W2986131415","https://openalex.org/W3000351820","https://openalex.org/W3005401190","https://openalex.org/W3034287518","https://openalex.org/W3034873438","https://openalex.org/W3036843665","https://openalex.org/W3085887408","https://openalex.org/W3092948912","https://openalex.org/W3099561715","https://openalex.org/W3138095408","https://openalex.org/W3151956566","https://openalex.org/W3171371659","https://openalex.org/W3173531806","https://openalex.org/W3180059462","https://openalex.org/W3195161059","https://openalex.org/W3202477427","https://openalex.org/W3205725084","https://openalex.org/W4200150166","https://openalex.org/W4224281996","https://openalex.org/W4229917313","https://openalex.org/W4240153047","https://openalex.org/W4283712710","https://openalex.org/W4288242633","https://openalex.org/W4293405121","https://openalex.org/W4313165271","https://openalex.org/W4313476633","https://openalex.org/W4380202601","https://openalex.org/W4386076558"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"With":[0],"the":[1,9,15,38,79,100,106,115,129,174],"remarkable":[2],"advancement":[3],"of":[4,12,17,45,63,118],"deep":[5],"learning":[6],"techniques":[7],"and":[8,42,77,148,157],"wide":[10],"availability":[11],"large-scale":[13],"datasets,":[14],"performance":[16],"audio-visual":[18,26,53,89,170],"saliency":[19,27,54,90,123,181],"prediction":[20,28,55],"has":[21],"been":[22],"drastically":[23],"improved.":[24],"Actually,":[25],"is":[29,140],"still":[30],"at":[31],"an":[32],"early":[33],"exploration":[34],"stage":[35],"due":[36],"to":[37,98,142,160,167],"spatial-temporal":[39],"signal":[40],"complexity":[41],"dynamic":[43,80],"continuity":[44,81],"video":[46,75,119],"content.":[47],"To":[48],"our":[49],"knowledge,":[50],"most":[51],"existing":[52],"approaches":[56],"usually":[57],"represent":[58],"videos":[59],"as":[60],"3D":[61],"grid":[62],"RGB":[64],"values":[65],"using":[66,105],"discrete":[67],"convolutional":[68],"neural":[69,95,109],"networks":[70],"(CNNs),":[71],"which":[72,125,152],"inevitably":[73],"incurs":[74],"content-agnostic":[76],"ignores":[78],"issues.":[82],"This":[83],"article":[84],"proposes":[85],"a":[86,135,184],"novel":[87],"parametric":[88,108,136],"(PAVS)":[91],"model":[92,177],"with":[93],"implicit":[94],"representation":[96,132],"(INR)":[97],"address":[99],"aforementioned":[101],"problems.":[102],"Specifically,":[103],"by":[104,183],"proposed":[107,175],"network,":[110],"we":[111],"can":[112,126,153],"effectively":[113],"encode":[114],"space-time":[116],"coordinates":[117],"frames":[120],"into":[121],"corresponding":[122],"values,":[124],"significantly":[127],"enhance":[128],"compact":[130],"feature":[131,137,171],"ability.":[133],"Meanwhile,":[134],"fusion":[138,172],"method":[139],"developed":[141],"achieve":[143],"intrinsic":[144],"interactions":[145],"between":[146],"audio":[147,156],"visual":[149,158],"information":[150],"streams,":[151],"adaptively":[154],"fuse":[155],"features":[159],"obtain":[161],"competitive":[162],"performance.":[163],"Notably,":[164],"without":[165],"resorting":[166],"any":[168],"specific":[169],"strategy,":[173],"PAVS":[176],"outperforms":[178],"other":[179],"state-of-the-art":[180],"methods":[182],"large":[185],"margin.":[186]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}