{"id":"https://openalex.org/W3033504107","doi":"https://doi.org/10.1145/3379156.3391337","title":"Deep Audio-Visual Saliency: Baseline Model and Data","display_name":"Deep Audio-Visual Saliency: Baseline Model and Data","publication_year":2020,"publication_date":"2020-06-02","ids":{"openalex":"https://openalex.org/W3033504107","doi":"https://doi.org/10.1145/3379156.3391337","mag":"3033504107"},"language":"en","primary_location":{"id":"doi:10.1145/3379156.3391337","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3379156.3391337","pdf_url":null,"source":{"id":"https://openalex.org/S4306500162","display_name":"ACM Symposium on Eye Tracking Research and Applications","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Symposium on Eye Tracking Research and Applications","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/A5002546998","display_name":"Hamed R. Tavakoli","orcid":"https://orcid.org/0000-0002-9466-9148"},"institutions":[{"id":"https://openalex.org/I2738502077","display_name":"Nokia (Finland)","ror":"https://ror.org/04pkc8m17","country_code":"FI","type":"company","lineage":["https://openalex.org/I2738502077"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Hamed Rezazadegan Tavakoli","raw_affiliation_strings":["Nokia Technologies, Finland"],"affiliations":[{"raw_affiliation_string":"Nokia Technologies, Finland","institution_ids":["https://openalex.org/I2738502077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068743986","display_name":"Ali Borji","orcid":"https://orcid.org/0000-0001-8198-0335"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ali Borji","raw_affiliation_strings":["Individual Researcher"],"affiliations":[{"raw_affiliation_string":"Individual Researcher","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057931031","display_name":"Juho Kannala","orcid":"https://orcid.org/0000-0001-5088-4041"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Juho Kannala","raw_affiliation_strings":["Aalto University"],"affiliations":[{"raw_affiliation_string":"Aalto University","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088180438","display_name":"Esa Rahtu","orcid":"https://orcid.org/0000-0001-8767-0864"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Esa Rahtu","raw_affiliation_strings":["Tampere University"],"affiliations":[{"raw_affiliation_string":"Tampere University","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5002546998"],"corresponding_institution_ids":["https://openalex.org/I2738502077"],"apc_list":null,"apc_paid":null,"fwci":0.8793,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.75880554,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"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":0.9997000098228455,"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":0.9997000098228455,"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":0.998199999332428,"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/T10971","display_name":"Olfactory and Sensory Function Studies","score":0.9973999857902527,"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":0.8365112543106079},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6431408524513245},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.636817991733551},{"id":"https://openalex.org/keywords/sensory-cue","display_name":"Sensory cue","score":0.5484921336174011},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5322912335395813},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5210568308830261},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4973914921283722},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.49612554907798767},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.4530966579914093},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4486277401447296},{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.4469260573387146},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4277419447898865},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3387349843978882},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.08411416411399841}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8365112543106079},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6431408524513245},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.636817991733551},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.5484921336174011},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5322912335395813},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5210568308830261},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4973914921283722},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49612554907798767},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.4530966579914093},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4486277401447296},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.4469260573387146},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4277419447898865},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3387349843978882},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.08411416411399841},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3379156.3391337","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3379156.3391337","pdf_url":null,"source":{"id":"https://openalex.org/S4306500162","display_name":"ACM Symposium on Eye Tracking Research and Applications","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Symposium on Eye Tracking Research and Applications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W119228284","https://openalex.org/W1978479866","https://openalex.org/W1979753320","https://openalex.org/W1981697898","https://openalex.org/W1986001465","https://openalex.org/W1988712925","https://openalex.org/W1991139021","https://openalex.org/W2034436892","https://openalex.org/W2042665538","https://openalex.org/W2054802006","https://openalex.org/W2082183045","https://openalex.org/W2119577735","https://openalex.org/W2128779052","https://openalex.org/W2133589685","https://openalex.org/W2149095485","https://openalex.org/W2151900481","https://openalex.org/W2155479901","https://openalex.org/W2177528296","https://openalex.org/W2212216676","https://openalex.org/W2213100575","https://openalex.org/W2241136623","https://openalex.org/W2378845821","https://openalex.org/W2498738402","https://openalex.org/W2558906385","https://openalex.org/W2711275409","https://openalex.org/W2895640967","https://openalex.org/W2896657282","https://openalex.org/W2962934715","https://openalex.org/W2962965915","https://openalex.org/W2963828885","https://openalex.org/W3101840568","https://openalex.org/W3147008444","https://openalex.org/W4255411781","https://openalex.org/W4388624454"],"related_works":["https://openalex.org/W2183271128","https://openalex.org/W1589443630","https://openalex.org/W1561602432","https://openalex.org/W2385108104","https://openalex.org/W1999328396","https://openalex.org/W2769824675","https://openalex.org/W2113986142","https://openalex.org/W2148584227","https://openalex.org/W2127677160","https://openalex.org/W2168991662"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,32,66,108],"conceptually":[4],"simple":[5],"and":[6,37,52,124,130],"effective":[7],"Deep":[8],"Audio-Visual":[9,25],"Embedding":[10],"for":[11,40,72],"dynamic":[12,61],"saliency":[13,46,70,74,115,120],"prediction":[14,75],"dubbed":[15],"\u201cDAVE\u201d":[16],"in":[17,60,76],"conjunction":[18],"with":[19],"our":[20],"efforts":[21],"towards":[22],"building":[23],"an":[24],"Eye-tracking":[26],"corpus":[27],"named":[28],"\u201cAVE\u201d.":[29],"Despite":[30],"existing":[31],"strong":[33],"relation":[34],"between":[35],"auditory":[36,55],"visual":[38,50],"cues":[39,51],"guiding":[41],"gaze":[42],"during":[43],"perception,":[44],"video":[45,90,119],"models":[47,106],"only":[48],"consider":[49],"neglect":[53],"the":[54,77,80,97,104,118],"information":[56],"that":[57,113],"is":[58,83,93],"ubiquitous":[59],"scenes.":[62],"Here,":[63],"we":[64],"propose":[65],"baseline":[67,91],"deep":[68],"audio-visual":[69,105,114],"model":[71,82,92,116],"multi-modal":[73],"wild.":[78],"Thus":[79],"proposed":[81],"intentionally":[84],"designed":[85],"to":[86,100],"be":[87],"simple.":[88],"A":[89],"also":[94],"developed":[95],"on":[96,107],"same":[98],"architecture":[99],"assess":[101],"effectiveness":[102],"of":[103],"fair":[109],"basis.":[110],"We":[111],"demonstrate":[112],"outperforms":[117],"models.":[121],"The":[122],"data":[123],"code":[125],"are":[126],"available":[127],"at":[128],"https://hrtavakoli.github.io/AVE/":[129],"https://github.com/hrtavakoli/DAVE":[131]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
