{"id":"https://openalex.org/W2082828292","doi":"https://doi.org/10.1145/2502081.2502215","title":"Learning representations for affective video understanding","display_name":"Learning representations for affective video understanding","publication_year":2013,"publication_date":"2013-10-21","ids":{"openalex":"https://openalex.org/W2082828292","doi":"https://doi.org/10.1145/2502081.2502215","mag":"2082828292"},"language":"en","primary_location":{"id":"doi:10.1145/2502081.2502215","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2502081.2502215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5043131371","display_name":"Esra Acar","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Esra Acar","raw_affiliation_strings":["DAI Laboratory, Technische Universitat Berlin, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DAI Laboratory, Technische Universitat Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5043131371"],"corresponding_institution_ids":["https://openalex.org/I4577782"],"apc_list":null,"apc_paid":null,"fwci":0.8315,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.76091486,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1055","last_page":"1058"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9991999864578247,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9991999864578247,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9977999925613403,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9926000237464905,"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":0.6721457242965698},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4386889338493347},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4016112685203552}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6721457242965698},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4386889338493347},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4016112685203552}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2502081.2502215","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2502081.2502215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W953419521","https://openalex.org/W1869734671","https://openalex.org/W1973810917","https://openalex.org/W1983364832","https://openalex.org/W2002055708","https://openalex.org/W2006407148","https://openalex.org/W2011664673","https://openalex.org/W2032455730","https://openalex.org/W2075942472","https://openalex.org/W2091084672","https://openalex.org/W2098935012","https://openalex.org/W2104453314","https://openalex.org/W2113076747","https://openalex.org/W2114920167","https://openalex.org/W2116001771","https://openalex.org/W2121407761","https://openalex.org/W2146104196","https://openalex.org/W2340134902","https://openalex.org/W2800106282"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"Among":[0],"the":[1,12,25,96,100,120,124,151],"ever":[2],"growing":[3],"available":[4],"multimedia":[5,8],"data,":[6],"finding":[7],"content":[9,38,52,176,216],"which":[10],"matches":[11],"current":[13,101],"mood":[14],"of":[15,27,127,150,168],"users":[16],"is":[17,30,159],"a":[18,31,148,156],"challenging":[19],"problem.":[20],"Choosing":[21],"discriminative":[22],"features":[23,59,109,171],"for":[24,123,138,173,213],"representation":[26,45],"video":[28,36,129,140,174,214],"segments":[29],"key":[32],"issue":[33],"in":[34,76,82,99,110],"designing":[35],"affective":[37,51,125,143,175,215],"analysis":[39,53],"algorithms,":[40],"where":[41],"no":[42],"dominant":[43],"feature":[44],"has":[46],"emerged":[47],"yet.":[48],"Most":[49],"existing":[50],"methods":[54],"either":[55],"use":[56,72,119],"low-level":[57,170],"audio-visual":[58],"or":[60],"generate":[61,193],"hand-crafted":[62],"higher":[63,114,164],"level":[64,115,165],"representations.":[65,117],"In":[66],"this":[67,183],"work,":[68],"we":[69,162],"propose":[70],"to":[71,84,112,180],"deep":[73],"learning":[74],"methods,":[75],"particular,":[77],"convolutional":[78],"neural":[79],"networks":[80],"(CNNs),":[81],"order":[83,111],"learn":[85,163],"mid-level":[86,194,205],"representations":[87,122,166,196,203,207],"from":[88],"automatically":[89],"extracted":[90],"raw":[91],"features.":[92],"We":[93,118,131,178,191],"exploit":[94],"only":[95],"audio":[97,116,206],"modality":[98,188],"framework":[102],"and":[103,185,199,211],"employ":[104],"Mel-Frequency":[105],"Cepstral":[106],"Coefficients":[107],"(MFCC)":[108],"build":[113],"learned":[121],"classification":[126],"music":[128],"clips.":[130],"choose":[132],"multi-class":[133],"support":[134],"vector":[135],"machines":[136],"(SVMs)":[137],"classifying":[139],"clips":[141],"into":[142],"categories.":[144],"Preliminary":[145],"results":[146],"on":[147],"subset":[149],"DEAP":[152],"dataset":[153],"show":[154],"that":[155],"significant":[157],"improvement":[158],"obtained":[160],"when":[161],"instead":[167],"using":[169,197],"directly":[172],"analysis.":[177,217],"plan":[179],"further":[181],"extend":[182],"work":[184],"include":[186],"visual":[187,195,202],"as":[189],"well.":[190],"will":[192],"CNNs":[198],"fuse":[200],"these":[201],"with":[204],"both":[208],"at":[209],"feature-":[210],"decision-level":[212]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}