{"id":"https://openalex.org/W4385484602","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191461","title":"A Multimodal Hierarchical Variational Autoencoder for Saliency Detection","display_name":"A Multimodal Hierarchical Variational Autoencoder for Saliency Detection","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385484602","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191461"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","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/A5102869301","display_name":"Zhengyang Yu","orcid":"https://orcid.org/0000-0003-2335-5288"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Zhengyang Yu","raw_affiliation_strings":["College of Engineering and Computer Science, Australian National University,Canberra,Australia","College of Engineering and Computer Science, Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"College of Engineering and Computer Science, Australian National University,Canberra,Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"College of Engineering and Computer Science, Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100630815","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0002-8516-0913"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["College of Engineering and Computer Science, Australian National University,Canberra,Australia","College of Engineering and Computer Science, Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"College of Engineering and Computer Science, Australian National University,Canberra,Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"College of Engineering and Computer Science, Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072837153","display_name":"Nick Barnes","orcid":"https://orcid.org/0000-0002-9343-9535"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Nick Barnes","raw_affiliation_strings":["College of Engineering and Computer Science, Australian National University,Canberra,Australia","College of Engineering and Computer Science, Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"College of Engineering and Computer Science, Australian National University,Canberra,Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"College of Engineering and Computer Science, Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102869301"],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":0.3704,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.5934331,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":1.0,"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":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9944000244140625,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.987500011920929,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7274729609489441},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.61869877576828},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6097699403762817},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6066393256187439},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.557585597038269},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5491223931312561},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4969013035297394},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.42666590213775635},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.4256376624107361},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.4186929762363434},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3381671905517578},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.1622280478477478}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7274729609489441},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.61869877576828},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6097699403762817},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6066393256187439},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.557585597038269},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5491223931312561},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4969013035297394},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.42666590213775635},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.4256376624107361},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.4186929762363434},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3381671905517578},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.1622280478477478},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","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":119,"referenced_works":["https://openalex.org/W20683899","https://openalex.org/W241901432","https://openalex.org/W933200379","https://openalex.org/W1522301498","https://openalex.org/W1772076007","https://openalex.org/W1779483307","https://openalex.org/W1959608418","https://openalex.org/W1966025376","https://openalex.org/W1970844071","https://openalex.org/W1993713494","https://openalex.org/W2032635843","https://openalex.org/W2039154778","https://openalex.org/W2039298799","https://openalex.org/W2056108926","https://openalex.org/W2116064496","https://openalex.org/W2123046721","https://openalex.org/W2188365844","https://openalex.org/W2194775991","https://openalex.org/W2403726878","https://openalex.org/W2556013083","https://openalex.org/W2563296158","https://openalex.org/W2581387103","https://openalex.org/W2619383789","https://openalex.org/W2765838470","https://openalex.org/W2767775878","https://openalex.org/W2786541991","https://openalex.org/W2808359495","https://openalex.org/W2887486131","https://openalex.org/W2913002991","https://openalex.org/W2942049721","https://openalex.org/W2945809413","https://openalex.org/W2946520073","https://openalex.org/W2948537313","https://openalex.org/W2954204101","https://openalex.org/W2957414648","https://openalex.org/W2963948515","https://openalex.org/W2964010806","https://openalex.org/W2964092686","https://openalex.org/W2970014727","https://openalex.org/W2970972665","https://openalex.org/W2987472543","https://openalex.org/W2995936506","https://openalex.org/W3002301267","https://openalex.org/W3022015146","https://openalex.org/W3034287518","https://openalex.org/W3035357085","https://openalex.org/W3035633116","https://openalex.org/W3035688398","https://openalex.org/W3039479109","https://openalex.org/W3041956526","https://openalex.org/W3097053213","https://openalex.org/W3108318504","https://openalex.org/W3108421143","https://openalex.org/W3108608656","https://openalex.org/W3108822985","https://openalex.org/W3113067643","https://openalex.org/W3114152269","https://openalex.org/W3118710621","https://openalex.org/W3120113457","https://openalex.org/W3120243996","https://openalex.org/W3138095408","https://openalex.org/W3138516171","https://openalex.org/W3159436766","https://openalex.org/W3166092877","https://openalex.org/W3166396011","https://openalex.org/W3169978599","https://openalex.org/W3170655219","https://openalex.org/W3171638247","https://openalex.org/W3171757599","https://openalex.org/W3174906557","https://openalex.org/W3176404283","https://openalex.org/W3204197760","https://openalex.org/W3209732904","https://openalex.org/W3211771658","https://openalex.org/W3212022073","https://openalex.org/W4206873376","https://openalex.org/W4213299273","https://openalex.org/W4285058230","https://openalex.org/W4287327090","https://openalex.org/W4287757254","https://openalex.org/W4293469690","https://openalex.org/W4295177495","https://openalex.org/W4312946813","https://openalex.org/W4313164293","https://openalex.org/W4313177291","https://openalex.org/W4393881434","https://openalex.org/W6609413351","https://openalex.org/W6631190155","https://openalex.org/W6638116569","https://openalex.org/W6640963894","https://openalex.org/W6648922525","https://openalex.org/W6683200053","https://openalex.org/W6687045409","https://openalex.org/W6713578759","https://openalex.org/W6729906282","https://openalex.org/W6730357551","https://openalex.org/W6738698908","https://openalex.org/W6748455135","https://openalex.org/W6751165238","https://openalex.org/W6752724743","https://openalex.org/W6762941283","https://openalex.org/W6763249567","https://openalex.org/W6765983947","https://openalex.org/W6767287485","https://openalex.org/W6767441326","https://openalex.org/W6771643744","https://openalex.org/W6773474599","https://openalex.org/W6779473860","https://openalex.org/W6780593937","https://openalex.org/W6784364555","https://openalex.org/W6786494455","https://openalex.org/W6787133006","https://openalex.org/W6790812491","https://openalex.org/W6791353385","https://openalex.org/W6791597301","https://openalex.org/W6797613833","https://openalex.org/W6803606285","https://openalex.org/W6803674551","https://openalex.org/W6803986789"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W4386815338","https://openalex.org/W2145836866","https://openalex.org/W2803255133"],"abstract_inverted_index":{"Existing":[0],"multimodal":[1,16,25,31,40,134],"Salient":[2],"Object":[3],"Detection":[4],"(SOD)":[5],"methods":[6,38],"do":[7],"not":[8],"generalize":[9],"well":[10],"for":[11,29,117],"more":[12],"complex":[13],"and":[14,62,81],"scalable":[15,45],"learning":[17],"scenarios.":[18],"In":[19],"this":[20],"paper,":[21],"we":[22,76,99],"propose":[23,100],"a":[24,101,132],"hierarchical":[26],"variational":[27],"auto-encoder":[28],"generalized":[30],"SOD.":[32],"By":[33,70],"introducing":[34],"joint":[35],"inference":[36],"factorization":[37],"in":[39,59,89],"VAEs,":[41],"our":[42,124],"model":[43,125],"is":[44,54],"to":[46],"partially":[47],"missing":[48],"modality":[49,115],"data.":[50],"A":[51],"latent":[52,60,74],"hierarchy":[53],"proposed":[55],"which":[56],"enhances":[57],"expressiveness":[58],"space":[61],"allows":[63],"multi-level":[64],"interaction":[65],"between":[66],"features":[67],"across":[68],"modalities.":[69],"further":[71],"exploring":[72],"the":[73,84,93],"hierarchy,":[75],"provide":[77],"intuitive":[78],"uncertainty":[79,88],"visualizations":[80],"observe":[82],"that":[83,109,123,130],"main":[85],"source":[86],"of":[87],"SOD":[90,135],"derives":[91],"from":[92],"lower-level":[94],"features.":[95],"Based":[96],"on":[97],"this,":[98],"simple":[102],"yet":[103],"effective":[104],"sampling-based":[105],"confidence":[106],"estimation":[107],"method,":[108],"brings":[110],"robustness":[111],"when":[112],"encountering":[113],"untrustworthy":[114],"data":[116],"inference.":[118],"Extensive":[119],"experimental":[120],"analysis":[121],"illustrate":[122],"can":[126],"satisfy":[127],"crucial":[128],"properties":[129],"make":[131],"desirable":[133],"framework.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}