{"id":"https://openalex.org/W2768534944","doi":"https://doi.org/10.1109/icci-cc.2017.8109785","title":"Towards multimodal saliency detection: An enhancement of audio-visual correlation estimation","display_name":"Towards multimodal saliency detection: An enhancement of audio-visual correlation estimation","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2768534944","doi":"https://doi.org/10.1109/icci-cc.2017.8109785","mag":"2768534944"},"language":"en","primary_location":{"id":"doi:10.1109/icci-cc.2017.8109785","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icci-cc.2017.8109785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 16th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","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/A5003679632","display_name":"Antonio Rodr\u00edguez-Hidalgo","orcid":"https://orcid.org/0000-0003-3809-7920"},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Antonio Rodriguez-Hidalgo","raw_affiliation_strings":["Department of Signal Theory and Communications, Universidad Carlos III de Madrid, Avda. de la Universidad, 30, Leganés, Madrid, 28911, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Signal Theory and Communications, Universidad Carlos III de Madrid, Avda. de la Universidad, 30, Leganés, Madrid, 28911, Spain","institution_ids":["https://openalex.org/I50357001"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090068120","display_name":"Carmen Pel\u00e1ez-Moreno","orcid":"https://orcid.org/0000-0003-1425-6763"},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Carmen Pelaez-Moreno","raw_affiliation_strings":["Department of Signal Theory and Communications, Universidad Carlos III de Madrid, Avda. de la Universidad, 30, Leganés, Madrid, 28911, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Signal Theory and Communications, Universidad Carlos III de Madrid, Avda. de la Universidad, 30, Leganés, Madrid, 28911, Spain","institution_ids":["https://openalex.org/I50357001"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065719579","display_name":"Ascensi\u00f3n Gallardo-Antol\u00edn","orcid":"https://orcid.org/0000-0002-9322-3128"},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ascension Gallardo-Antolin","raw_affiliation_strings":["Department of Signal Theory and Communications, Universidad Carlos III de Madrid, Avda. de la Universidad, 30, Leganés, Madrid, 28911, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Signal Theory and Communications, Universidad Carlos III de Madrid, Avda. de la Universidad, 30, Leganés, Madrid, 28911, Spain","institution_ids":["https://openalex.org/I50357001"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5003679632"],"corresponding_institution_ids":["https://openalex.org/I50357001"],"apc_list":null,"apc_paid":null,"fwci":0.091,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.48298082,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"438","last_page":"443"},"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/T10971","display_name":"Olfactory and Sensory Function Studies","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T12032","display_name":"Multisensory perception and integration","score":0.9976000189781189,"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":0.8249920010566711},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6786512136459351},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.6297045350074768},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5839836597442627},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5605080127716064},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.49411991238594055},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.4684935510158539},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4402984082698822},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43806904554367065},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40525221824645996},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3744356632232666},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1463983654975891},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09615638852119446}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8249920010566711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6786512136459351},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.6297045350074768},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5839836597442627},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5605080127716064},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.49411991238594055},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.4684935510158539},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4402984082698822},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43806904554367065},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40525221824645996},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3744356632232666},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1463983654975891},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09615638852119446},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icci-cc.2017.8109785","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icci-cc.2017.8109785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 16th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","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":15,"referenced_works":["https://openalex.org/W65124300","https://openalex.org/W1472787671","https://openalex.org/W2046487233","https://openalex.org/W2046893754","https://openalex.org/W2055111849","https://openalex.org/W2093111229","https://openalex.org/W2128272608","https://openalex.org/W2135046866","https://openalex.org/W2135835174","https://openalex.org/W2135957164","https://openalex.org/W2143688352","https://openalex.org/W2154504070","https://openalex.org/W2156232986","https://openalex.org/W2213100575","https://openalex.org/W2400119699"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W4286646204","https://openalex.org/W2564375980","https://openalex.org/W2030154815","https://openalex.org/W2051121715","https://openalex.org/W3092720353"],"abstract_inverted_index":{"This":[0],"work":[1],"is":[2],"focused":[3],"on":[4,63],"the":[5,18,33,52,58,64,67,83,91,96,99,109,138,141,160,173,185,188,192],"task":[6],"of":[7,35,54,66,69,85,98,111,121,128,140,187,191],"multimodal":[8],"saliency":[9,37,87,136,148],"detection.":[10,38],"Very":[11],"few":[12],"works":[13],"have":[14,115],"been":[15],"developed":[16,116],"in":[17,32],"field,":[19],"and":[20,94,107,154],"there":[21],"are":[22],"no":[23],"well-established":[24],"baselines":[25],"or":[26],"benchmarks":[27],"comparable":[28],"to":[29,45,89],"those":[30],"existing":[31,48],"field":[34],"visual":[36,74,147],"In":[39],"this":[40],"paper,":[41],"we":[42,114],"set":[43],"out":[44],"improve":[46],"an":[47,169],"model":[49,149],"by":[50],"enhancing":[51],"performance":[53,110,139,186],"its":[55,70],"key":[56],"module:":[57],"audio-visual":[59,162],"correlation":[60,68],"estimation":[61,101,181],"based":[62],"computation":[65],"acoustic":[71,92,135,166,194],"inconsistency":[72,93,167],"with":[73,144,150],"motion":[75,100,155,180],"estimation.":[76,156],"We":[77],"propose":[78],"two":[79],"main":[80],"modifications:":[81],"first,":[82],"introduction":[84],"auditory":[86,170],"algorithms":[88],"compute":[90],"second,":[95],"improvement":[97],"procedure.":[102],"To":[103],"verify":[104],"our":[105,112],"hyphothesis":[106],"analyze":[108],"contribution,":[113],"experiments":[117],"considering":[118],"a":[119,145],"database":[120],"30":[122],"videos,":[123],"that":[124,133,164],"includes":[125],"eye-tracker":[126],"fixations":[127],"several":[129],"subjects.":[130],"Results":[131],"show":[132],"using":[134,176],"improves":[137],"system":[142],"compared":[143],"conventional":[146],"color,":[151],"orientation,":[152],"intensity":[153],"It":[157],"also":[158,182],"outperforms":[159],"baseline":[161],"system,":[163,189],"uses":[165],"as":[168],"cue.":[171],"On":[172],"other":[174],"hand,":[175],"optical":[177],"flow":[178],"for":[179],"increases":[183],"significantly":[184],"regardless":[190],"tested":[193],"feature.":[195]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}