{"id":"https://openalex.org/W4304091755","doi":"https://doi.org/10.1145/3503161.3548018","title":"Representation Learning through Multimodal Attention and Time-Sync Comments for Affective Video Content Analysis","display_name":"Representation Learning through Multimodal Attention and Time-Sync Comments for Affective Video Content Analysis","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304091755","doi":"https://doi.org/10.1145/3503161.3548018"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548018","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548018","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th 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/A5081132731","display_name":"Jicai Pan","orcid":"https://orcid.org/0000-0002-7935-3452"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jicai Pan","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077046519","display_name":"Shangfei Wang","orcid":"https://orcid.org/0000-0003-1164-9895"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangfei Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059244709","display_name":"Lin Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Fang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":4.9192,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.96149358,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"42","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.996999979019165,"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":0.8078335523605347},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6146856546401978},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5556859970092773},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5232621431350708},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4864308834075928},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48113954067230225},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.45513617992401123},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4266315996646881},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38274192810058594},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37305575609207153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8078335523605347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6146856546401978},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5556859970092773},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5232621431350708},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4864308834075928},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48113954067230225},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.45513617992401123},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4266315996646881},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38274192810058594},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37305575609207153},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548018","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548018","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8472469554","display_name":null,"funder_award_id":"92048203","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W306648316","https://openalex.org/W2044807399","https://openalex.org/W2060505035","https://openalex.org/W2173163709","https://openalex.org/W2177696193","https://openalex.org/W2188687388","https://openalex.org/W2524923107","https://openalex.org/W2562476021","https://openalex.org/W2605324664","https://openalex.org/W2613995098","https://openalex.org/W2740409734","https://openalex.org/W2777446440","https://openalex.org/W2790495655","https://openalex.org/W2794257965","https://openalex.org/W2943770669","https://openalex.org/W2962934715","https://openalex.org/W2966094747","https://openalex.org/W2967510410","https://openalex.org/W2979368787","https://openalex.org/W2984369117","https://openalex.org/W2990604978","https://openalex.org/W2996799978","https://openalex.org/W3099153556","https://openalex.org/W3102047656","https://openalex.org/W3125250951","https://openalex.org/W3125615400","https://openalex.org/W3135367836","https://openalex.org/W3182328899","https://openalex.org/W3199741300","https://openalex.org/W3205519684","https://openalex.org/W3207343197","https://openalex.org/W3207833857"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2185469136","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W2086519370","https://openalex.org/W2028665553","https://openalex.org/W2087343574","https://openalex.org/W2535915176","https://openalex.org/W2105860728"],"abstract_inverted_index":{"Although":[0],"temporal":[1,38,67,86,199],"patterns":[2,236],"inherent":[3],"in":[4,123,139,217],"visual":[5],"and":[6,56,104,129,133,151,237],"audio":[7],"signals":[8],"are":[9,101,113,157],"crucial":[10],"for":[11,79],"affective":[12,200,218,235],"video":[13,58,127,149,219],"content":[14,220],"analysis,":[15],"they":[16],"have":[17],"not":[18],"been":[19],"thoroughly":[20],"explored":[21],"yet.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26,41],"propose":[27],"a":[28,43,61,73,124,167],"novel":[29],"Temporal-Aware":[30],"Multimodal":[31],"(TAM)":[32],"method":[33],"to":[34,52,118,159,188],"fully":[35,64],"capture":[36],"the":[37,66,115,120,134,137,141,146,161,175,185,210,229],"information.":[39],"Specifically,":[40],"design":[42],"cross-temporal":[44,162],"multimodal":[45,163],"fusion":[46,51,164,186,212,230],"module":[47,165,187,213,231],"that":[48,209,225],"applies":[49],"attention-based":[50],"different":[53,70],"modalities":[54],"within":[55],"across":[57],"segments.":[59],"As":[60],"result,":[62],"it":[63],"captures":[65],"relations":[68],"between":[69,148],"modalities.":[71],"Furthermore,":[72],"single":[74],"emotion":[75],"label":[76],"lacks":[77],"supervision":[78],"learning":[80,191],"representation":[81,128,150,190],"of":[82],"each":[83],"segment,":[84],"making":[85],"pattern":[87],"mining":[88],"difficult.":[89],"We":[90],"leverage":[91],"time-synchronized":[92],"comments":[93,100],"(TSCs)":[94],"as":[95],"auxiliary":[96],"supervision,":[97],"since":[98],"these":[99],"easily":[102],"accessible":[103],"contain":[105],"rich":[106],"emotional":[107,121],"cues.":[108],"Two":[109],"TSC-based":[110,227],"self-supervised":[111,155,181],"tasks":[112,156,183],"designed:":[114],"first":[116],"aims":[117],"predict":[119],"words":[122],"TSC":[125,130,142,152],"from":[126,174],"contextual":[131],"semantics,":[132],"second":[135],"predicts":[136],"segment":[138],"which":[140,171],"appears":[143],"by":[144],"calculating":[145],"correlation":[147],"embedding.":[153],"These":[154,180],"used":[158],"pre-train":[160],"on":[166,192,204],"large-scale":[168],"video-TSC":[169],"dataset,":[170],"is":[172],"crawled":[173],"web":[176],"without":[177],"labeling":[178],"costs.":[179],"pre-training":[182],"prompt":[184],"perform":[189],"segments":[193],"including":[194],"TSC,":[195],"thus":[196],"capturing":[197],"more":[198,233],"patterns.":[201],"Experimental":[202],"results":[203,216],"three":[205],"benchmark":[206],"datasets":[207],"show":[208],"proposed":[211],"achieves":[214,238],"state-of-the-art":[215],"analysis.":[221],"Ablation":[222],"studies":[223],"verify":[224],"after":[226],"pre-training,":[228],"learns":[232],"segments'":[234],"better":[239],"performance.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}