{"id":"https://openalex.org/W2056907797","doi":"https://doi.org/10.1145/2671188.2749400","title":"Mutlimodal Learning with Deep Boltzmann Machine for Emotion Prediction in User Generated Videos","display_name":"Mutlimodal Learning with Deep Boltzmann Machine for Emotion Prediction in User Generated Videos","publication_year":2015,"publication_date":"2015-06-22","ids":{"openalex":"https://openalex.org/W2056907797","doi":"https://doi.org/10.1145/2671188.2749400","mag":"2056907797"},"language":"en","primary_location":{"id":"doi:10.1145/2671188.2749400","doi":"https://doi.org/10.1145/2671188.2749400","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2671188.2749400","pdf_url":null,"source":{"id":"https://openalex.org/S4306419706","display_name":"International Conference on Multimedia Retrieval","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ink.library.smu.edu.sg/sis_research/6502","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101503112","display_name":"Lei Pang","orcid":"https://orcid.org/0000-0003-1738-3143","observed_orcids":["https://orcid.org/0000-0003-1738-3143"]},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lei Pang","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010722442","display_name":"Chong\u2010Wah Ngo","orcid":"https://orcid.org/0000-0003-4182-8261","observed_orcids":["https://orcid.org/0000-0003-4182-8261"]},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chong-Wah Ngo","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I168719708"],"apc_list":null,"apc_paid":null,"fwci":2.5062,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.91869952,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"619","last_page":"622"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9916999936103821,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9916999936103821,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.0035000001080334187,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0010000000474974513,"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/emotion-prediction","display_name":"emotion prediction","score":0.7910000085830688},{"id":"https://openalex.org/keywords/user-generated-video","display_name":"user-generated video","score":0.8840000033378601},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"multimodal learning","score":0.8429999947547913},{"id":"https://openalex.org/keywords/deep-boltzmann-machine","display_name":"deep Boltzmann machine","score":0.9819999933242798},{"id":"https://openalex.org/keywords/audio-visual-text-fusion","display_name":"audio-visual-text fusion","score":0.6779999732971191},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"unsupervised learning","score":0.7039999961853027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8069202899932861},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6425292491912842},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5881814956665039},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.5521138310432434},{"id":"https://openalex.org/C2779812673","wikidata":"https://www.wikidata.org/wiki/Q169251","display_name":"Sadness","level":3,"score":0.5458366274833679},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5194455981254578},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5131338238716125},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4705653190612793},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4511021673679352},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4503284692764282},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3963380753993988},{"id":"https://openalex.org/C2779302386","wikidata":"https://www.wikidata.org/wiki/Q79871","display_name":"Anger","level":2,"score":0.30390429496765137},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2671188.2749400","doi":"https://doi.org/10.1145/2671188.2749400","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2671188.2749400","pdf_url":null,"source":{"id":"https://openalex.org/S4306419706","display_name":"International Conference on Multimedia Retrieval","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-7505","doi":null,"is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/6502","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1145/2671188.2749400","raw_type":"Conference Proceeding Article"}],"best_oa_location":{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-7505","doi":null,"is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/6502","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1145/2671188.2749400","raw_type":"Conference Proceeding Article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G8270975370","display_name":null,"funder_award_id":"CityU 11210514","funder_id":"https://openalex.org/F4320309893","funder_display_name":"City University of Hong Kong"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320309893","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W146470039","https://openalex.org/W154472438","https://openalex.org/W189596042","https://openalex.org/W1974894717","https://openalex.org/W2017411072","https://openalex.org/W2017814585","https://openalex.org/W2075456404","https://openalex.org/W2100002341","https://openalex.org/W2100495367","https://openalex.org/W2113317774","https://openalex.org/W2156709807","https://openalex.org/W2188687388","https://openalex.org/W2295300449","https://openalex.org/W2963992782"],"related_works":["https://openalex.org/W1930223417","https://openalex.org/W1480583224","https://openalex.org/W2752062163","https://openalex.org/W4307818284","https://openalex.org/W2967510410","https://openalex.org/W7198483564","https://openalex.org/W7096684434","https://openalex.org/W2998641113","https://openalex.org/W2477529024","https://openalex.org/W2924126491"],"abstract_inverted_index":{"Detecting":[0],"emotions":[1],"from":[2,44],"user-generated":[3,87],"videos,":[4],"such":[5],"as":[6,19],"\"anger\"":[7],"and":[8,72,132],"\"sadness\",":[9],"has":[10],"attracted":[11],"widespread":[12],"interest":[13],"recently.":[14],"The":[15,80,116],"problem":[16],"is":[17,32,82],"challenging":[18],"effectively":[20],"representing":[21],"video":[22,29],"data":[23],"with":[24,75],"multi-view":[25],"information":[26],"(e.g.,":[27],"audio,":[28],"or":[30,52],"text)":[31],"not":[33],"trivial.":[34],"In":[35],"contrast":[36],"to":[37,57,128,136],"the":[38,64,86,96,100,104,121,129,144],"existing":[39],"works":[40],"that":[41,108,120],"extract":[42],"features":[43,112],"each":[45],"modality":[46],"(view)":[47],"separately":[48],"followed":[49],"by":[50],"early":[51],"late":[53],"fusion,":[54],"we":[55],"propose":[56],"learn":[58],"a":[59],"joint":[60,125],"density":[61],"model":[62,81,123],"over":[63],"space":[65],"of":[66,102],"multi-modal":[67],"inputs":[68],"(including":[69],"visual,":[70],"auditory":[71,133],"textual":[73],"modalities)":[74],"Deep":[76],"Boltzmann":[77],"Machine":[78],"(DBM).":[79],"trained":[83],"directly":[84],"on":[85,143],"Web":[88],"videos":[89],"without":[90],"any":[91],"labeling":[92],"effort.":[93],"More":[94],"importantly,":[95],"deep":[97],"architecture":[98],"enlightens":[99],"possibility":[101],"discovering":[103],"highly":[105],"non-linear":[106],"relationships":[107],"exist":[109],"between":[110],"low-level":[111],"across":[113],"different":[114],"modalities.":[115],"experiment":[117],"results":[118],"show":[119],"DBM":[122],"learns":[124],"representation":[126],"complementary":[127],"hand-crafted":[130],"visual":[131],"features,":[134],"leading":[135],"7.7%":[137],"performance":[138],"improvement":[139],"in":[140],"classification":[141],"accuracy":[142],"recently":[145],"released":[146],"VideoEmotion":[147],"dataset.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}