{"id":"https://openalex.org/W3194334462","doi":"https://doi.org/10.23919/mva51890.2021.9511406","title":"Leveraging Frequency Based Salient Spatial Sound Localization to Improve 360\u00b0 Video Saliency Prediction","display_name":"Leveraging Frequency Based Salient Spatial Sound Localization to Improve 360\u00b0 Video Saliency Prediction","publication_year":2021,"publication_date":"2021-07-25","ids":{"openalex":"https://openalex.org/W3194334462","doi":"https://doi.org/10.23919/mva51890.2021.9511406","mag":"3194334462"},"language":"en","primary_location":{"id":"doi:10.23919/mva51890.2021.9511406","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mva51890.2021.9511406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 17th International Conference on Machine Vision and Applications (MVA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5019736541","display_name":"Mert Cokelek","orcid":null},"institutions":[{"id":"https://openalex.org/I66514158","display_name":"Hacettepe University","ror":"https://ror.org/04kwvgz42","country_code":"TR","type":"education","lineage":["https://openalex.org/I66514158"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Mert Cokelek","raw_affiliation_strings":["Hacettepe University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hacettepe University","institution_ids":["https://openalex.org/I66514158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074611723","display_name":"Nevrez \u0130mamo\u011flu","orcid":"https://orcid.org/0000-0002-2661-599X"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nevrez Imamoglu","raw_affiliation_strings":["AIST, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIST, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003249945","display_name":"Cagri Ozcinar","orcid":"https://orcid.org/0000-0003-4915-2251"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cagri Ozcinar","raw_affiliation_strings":["Samsung Research, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research, UK","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074809120","display_name":"Erkut Erdem","orcid":"https://orcid.org/0000-0002-6744-8614"},"institutions":[{"id":"https://openalex.org/I66514158","display_name":"Hacettepe University","ror":"https://ror.org/04kwvgz42","country_code":"TR","type":"education","lineage":["https://openalex.org/I66514158"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Erkut Erdem","raw_affiliation_strings":["Hacettepe University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hacettepe University","institution_ids":["https://openalex.org/I66514158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000080119","display_name":"Aykut Erdem","orcid":"https://orcid.org/0000-0002-6280-8422"},"institutions":[{"id":"https://openalex.org/I1351752","display_name":"Ko\u00e7 University","ror":"https://ror.org/00jzwgz36","country_code":"TR","type":"education","lineage":["https://openalex.org/I1351752"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Aykut Erdem","raw_affiliation_strings":["Ko\u00e7 University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ko\u00e7 University","institution_ids":["https://openalex.org/I1351752"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9945999979972839,"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":0.9926000237464905,"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":0.8419269323348999},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.7478258609771729},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5432227253913879},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5213521718978882},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.5083009600639343},{"id":"https://openalex.org/keywords/virtual-reality","display_name":"Virtual reality","score":0.46525153517723083},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.45272329449653625},{"id":"https://openalex.org/keywords/augmented-reality","display_name":"Augmented reality","score":0.44220033288002014},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.43660610914230347},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3948037326335907},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3785504102706909},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3590410351753235},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.33086949586868286}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8419269323348999},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.7478258609771729},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5432227253913879},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5213521718978882},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.5083009600639343},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.46525153517723083},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.45272329449653625},{"id":"https://openalex.org/C153715457","wikidata":"https://www.wikidata.org/wiki/Q254183","display_name":"Augmented reality","level":2,"score":0.44220033288002014},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.43660610914230347},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3948037326335907},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3785504102706909},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3590410351753235},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.33086949586868286},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/mva51890.2021.9511406","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mva51890.2021.9511406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 17th International Conference on Machine Vision and Applications (MVA)","raw_type":"proceedings-article"},{"id":"pmh:oai:cdm21054.contentdm.oclc.org:IR/9980","is_oa":false,"landing_page_url":"https://doi.org/10.23919/MVA51890.2021.9511406 ","pdf_url":null,"source":{"id":"https://openalex.org/S4306401341","display_name":"Digital Collections portal (Ko\u00e7 University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1351752","host_organization_name":"Ko\u00e7 University","host_organization_lineage":["https://openalex.org/I1351752"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of MVA 2021 - 17th International Conference on Machine Vision Applications","raw_type":"Conference proceeding"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1975141679","https://openalex.org/W2004294009","https://openalex.org/W2054802006","https://openalex.org/W2067373059","https://openalex.org/W2079317768","https://openalex.org/W2798665861","https://openalex.org/W2946520073","https://openalex.org/W2963503775","https://openalex.org/W3000351820","https://openalex.org/W3011978462","https://openalex.org/W3034287518","https://openalex.org/W3034304805","https://openalex.org/W3097337310","https://openalex.org/W3111243176","https://openalex.org/W3117908628","https://openalex.org/W4247442285","https://openalex.org/W6667646228","https://openalex.org/W6763249567","https://openalex.org/W6771902541","https://openalex.org/W6787656261","https://openalex.org/W6949518029"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W2494533082","https://openalex.org/W4214771044","https://openalex.org/W4382560817","https://openalex.org/W4387698063","https://openalex.org/W1975359510","https://openalex.org/W3004352674","https://openalex.org/W1611900921","https://openalex.org/W3110605476","https://openalex.org/W1803351015"],"abstract_inverted_index":{"Virtual":[0],"and":[1,19,56,76,132,164],"augmented":[2],"reality":[3],"(VR/AR)":[4],"systems":[5],"dramatically":[6],"gained":[7],"in":[8,108,136],"popularity":[9],"with":[10],"various":[11],"application":[12],"areas":[13],"such":[14],"as":[15,148],"gaming,":[16],"social":[17],"media,":[18],"communication.":[20],"It":[21],"is":[22,69,126,145],"therefore":[23],"a":[24,93],"crucial":[25],"task":[26],"to":[27,31,70,84],"have":[28,45],"the":[29,78,130,152,168,174],"knowhow":[30],"efficiently":[32],"utilize,":[33],"store":[34],"or":[35],"deliver":[36],"360\u00b0":[37,53,82],"videos":[38,83],"for":[39,52,98,128],"end-users.":[40],"Towards":[41],"this":[42,61,99,119],"aim,":[43],"researchers":[44],"been":[46],"developing":[47],"deep":[48],"neural":[49],"network":[50],"models":[51,72,96,102,178],"multimedia":[54],"processing":[55],"computer":[57],"vision":[58],"fields.":[59],"In":[60,118],"line":[62],"of":[63,134,141,156],"work,":[64],"an":[65,121],"important":[66],"research":[67],"direction":[68],"build":[71],"that":[73,166],"can":[74],"learn":[75],"predict":[77],"observers'":[79],"attention":[80],"on":[81,151],"obtain":[85],"so-called":[86],"saliency":[87,95,124,135,154,177],"maps":[88],"computationally.":[89],"Although":[90],"there":[91],"are":[92],"few":[94],"proposed":[97,169],"purpose,":[100],"these":[101],"generally":[103],"consider":[104],"only":[105],"visual":[106],"cues":[107,114,144],"video":[109,153,176],"frames":[110],"by":[111],"neglecting":[112],"audio":[113,143,149,171],"from":[115],"sound":[116],"sources.":[117],"study,":[120],"unsupervised":[122],"frequency-based":[123],"model":[125],"presented":[127],"predicting":[129],"strength":[131],"location":[133],"spatial":[137,170],"audio.":[138],"The":[139],"prediction":[140],"salient":[142],"then":[146],"used":[147],"bias":[150,172],"predictions":[155],"state-of-the-art":[157],"models.":[158],"Our":[159],"experiments":[160],"yield":[161],"promising":[162],"results":[163],"show":[165],"integrating":[167],"into":[173],"existing":[175],"consistently":[179],"improves":[180],"their":[181],"performance.":[182]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2021-08-30T00:00:00"}