{"id":"https://openalex.org/W3158522902","doi":"https://doi.org/10.1155/2021/6610997","title":"Deep Multimodal Fusion Autoencoder for Saliency Prediction of RGB\u2010D Images","display_name":"Deep Multimodal Fusion Autoencoder for Saliency Prediction of RGB\u2010D Images","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3158522902","doi":"https://doi.org/10.1155/2021/6610997","mag":"3158522902","pmid":"https://pubmed.ncbi.nlm.nih.gov/34035801"},"language":"en","primary_location":{"id":"doi:10.1155/2021/6610997","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/6610997","pdf_url":"https://downloads.hindawi.com/journals/cin/2021/6610997.pdf","source":{"id":"https://openalex.org/S72372694","display_name":"Computational Intelligence and Neuroscience","issn_l":"1687-5265","issn":["1687-5265","1687-5273"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Intelligence and Neuroscience","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://downloads.hindawi.com/journals/cin/2021/6610997.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024672335","display_name":"Kengda Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kengda Huang","raw_affiliation_strings":["School of Information and Electronic Engineering, Zhejiang University of Science & Technology, Hangzhou 310023, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Electronic Engineering, Zhejiang University of Science & Technology, Hangzhou 310023, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076872319","display_name":"Wujie Zhou","orcid":"https://orcid.org/0000-0002-3055-2493"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wujie Zhou","raw_affiliation_strings":["Institute of Information and Communication Engineering, Zhejiang University, Hangzhou 310027, China","School of Information and Electronic Engineering, Zhejiang University of Science & Technology, Hangzhou 310023, China"],"raw_orcid":"https://orcid.org/0000-0002-3055-2493","affiliations":[{"raw_affiliation_string":"Institute of Information and Communication Engineering, Zhejiang University, Hangzhou 310027, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"School of Information and Electronic Engineering, Zhejiang University of Science & Technology, Hangzhou 310023, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073112133","display_name":"Meixin Fang","orcid":"https://orcid.org/0009-0006-1327-4416"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meixin Fang","raw_affiliation_strings":["Institute of Information and Communication Engineering, Zhejiang University, Hangzhou 310027, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information and Communication Engineering, Zhejiang University, Hangzhou 310027, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076872319"],"corresponding_institution_ids":["https://openalex.org/I168879160","https://openalex.org/I76130692"],"apc_list":{"value":2100,"currency":"USD","value_usd":2100},"apc_paid":{"value":2100,"currency":"USD","value_usd":2100},"fwci":0.3879,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.59620723,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"2021","issue":"1","first_page":"6610997","last_page":"6610997"},"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":0.9939000010490417,"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":0.9815999865531921,"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/autoencoder","display_name":"Autoencoder","score":0.9099273681640625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.8541690111160278},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.7842632532119751},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7299292087554932},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6770435571670532},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6673139333724976},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6150914430618286},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6047094464302063},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5116689205169678},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5060247778892517},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4967723488807678},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41250404715538025},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33336228132247925},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23312905430793762}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.9099273681640625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8541690111160278},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.7842632532119751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7299292087554932},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6770435571670532},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6673139333724976},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6150914430618286},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6047094464302063},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5116689205169678},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5060247778892517},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4967723488807678},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41250404715538025},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33336228132247925},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23312905430793762},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D005403","descriptor_name":"Fixation, Ocular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005403","descriptor_name":"Fixation, Ocular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005403","descriptor_name":"Fixation, Ocular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1155/2021/6610997","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/6610997","pdf_url":"https://downloads.hindawi.com/journals/cin/2021/6610997.pdf","source":{"id":"https://openalex.org/S72372694","display_name":"Computational Intelligence and Neuroscience","issn_l":"1687-5265","issn":["1687-5265","1687-5273"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Intelligence and Neuroscience","raw_type":"journal-article"},{"id":"pmid:34035801","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34035801","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational intelligence and neuroscience","raw_type":null},{"id":"pmh:oai:doaj.org/article:02991630e6c8476a8247c7befcb79de0","is_oa":true,"landing_page_url":"https://doaj.org/article/02991630e6c8476a8247c7befcb79de0","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Intelligence and Neuroscience, Vol 2021 (2021)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8116150","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8116150","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Comput Intell Neurosci","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1155/2021/6610997","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/6610997","pdf_url":"https://downloads.hindawi.com/journals/cin/2021/6610997.pdf","source":{"id":"https://openalex.org/S72372694","display_name":"Computational Intelligence and Neuroscience","issn_l":"1687-5265","issn":["1687-5265","1687-5273"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Intelligence and Neuroscience","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G191214056","display_name":null,"funder_award_id":"LY18F020012","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G3094706128","display_name":null,"funder_award_id":"LY18F020012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4233520035","display_name":null,"funder_award_id":"61502429","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G6189259675","display_name":null,"funder_award_id":"61502429","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/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3158522902.pdf","grobid_xml":"https://content.openalex.org/works/W3158522902.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W865056197","https://openalex.org/W1497443722","https://openalex.org/W1566291481","https://openalex.org/W1606286388","https://openalex.org/W1942214758","https://openalex.org/W1948843088","https://openalex.org/W1968613884","https://openalex.org/W1978741881","https://openalex.org/W1986951513","https://openalex.org/W1993084194","https://openalex.org/W1997137149","https://openalex.org/W2004362043","https://openalex.org/W2039920533","https://openalex.org/W2041719651","https://openalex.org/W2078903912","https://openalex.org/W2090116516","https://openalex.org/W2097117768","https://openalex.org/W2128272608","https://openalex.org/W2135957164","https://openalex.org/W2146103513","https://openalex.org/W2148383759","https://openalex.org/W2206823058","https://openalex.org/W2212216676","https://openalex.org/W2288514685","https://openalex.org/W2311587418","https://openalex.org/W2314032274","https://openalex.org/W2320663691","https://openalex.org/W2341145739","https://openalex.org/W2437041077","https://openalex.org/W2442293398","https://openalex.org/W2497806559","https://openalex.org/W2528092473","https://openalex.org/W2533058588","https://openalex.org/W2553917458","https://openalex.org/W2556549638","https://openalex.org/W2568628164","https://openalex.org/W2581756885","https://openalex.org/W2586820357","https://openalex.org/W2592997798","https://openalex.org/W2603340075","https://openalex.org/W2612135493","https://openalex.org/W2618530766","https://openalex.org/W2619578085","https://openalex.org/W2624257031","https://openalex.org/W2725229849","https://openalex.org/W2762270259","https://openalex.org/W2765161239","https://openalex.org/W2771328814","https://openalex.org/W2800632947","https://openalex.org/W2890897637","https://openalex.org/W2963828885","https://openalex.org/W2964114039","https://openalex.org/W2997355859","https://openalex.org/W3024706580","https://openalex.org/W3035499612","https://openalex.org/W3080081801","https://openalex.org/W3088365851","https://openalex.org/W3098145348","https://openalex.org/W3102465101","https://openalex.org/W3120889480","https://openalex.org/W3122238731","https://openalex.org/W3159018159","https://openalex.org/W3163132162"],"related_works":["https://openalex.org/W2983142544","https://openalex.org/W2891059443","https://openalex.org/W4281663961","https://openalex.org/W3208888551","https://openalex.org/W4313561566","https://openalex.org/W3208386644","https://openalex.org/W4220682630","https://openalex.org/W3181622257","https://openalex.org/W4389832810","https://openalex.org/W3133533225"],"abstract_inverted_index":{"In":[0,31],"recent":[1],"years,":[2],"the":[3,22,43,54,99,104,107,117,129,144,162],"prediction":[4,24,45,57,150],"of":[5,15,25,46,53,106],"salient":[6],"regions":[7],"in":[8],"RGB-D":[9,26,47,55],"images":[10,27],"has":[11],"become":[12],"a":[13,36,123,134,169],"focus":[14],"research.":[16],"Compared":[17],"to":[18],"its":[19],"RGB":[20],"counterpart,":[21],"saliency":[23,44,56,118,149],"is":[28,120],"more":[29],"challenging.":[30],"this":[32],"study,":[33],"we":[34],"propose":[35],"novel":[37],"deep":[38,130],"multimodal":[39],"fusion":[40],"autoencoder":[41,52,77,96,146,164],"for":[42],"images.":[48],"The":[49,76,95,158],"core":[50],"trainable":[51],"model":[58],"employs":[59],"two":[60,153],"raw":[61],"modalities":[62],"(RGB":[63],"and":[64,69,91,102,113,137],"depth/disparity":[65],"information)":[66],"as":[67,74],"inputs":[68],"their":[70],"corresponding":[71],"eye-fixation":[72],"attributes":[73],"labels.":[75],"comprises":[78],"four":[79],"main":[80],"networks:":[81],"color":[82,112],"channel":[83,86],"network,":[84,87,90],"disparity":[85,114],"feature":[88,92,124,139],"concatenated":[89],"learning":[93,136,140],"network.":[94],"can":[97],"mine":[98],"complex":[100],"relationship":[101],"make":[103],"utmost":[105],"complementary":[108],"characteristics":[109],"between":[110],"both":[111],"cues.":[115],"Finally,":[116],"map":[119],"predicted":[121],"via":[122],"combination":[125],"subnetwork,":[126],"which":[127],"combines":[128],"features":[131],"extracted":[132],"from":[133],"prior":[135],"convolutional":[138],"subnetworks.":[141],"We":[142],"compare":[143],"proposed":[145,163],"with":[147],"other":[148],"models":[151,167],"on":[152],"publicly":[154],"available":[155],"benchmark":[156],"datasets.":[157],"results":[159],"demonstrate":[160],"that":[161],"outperforms":[165],"these":[166],"by":[168],"significant":[170],"margin.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}