{"id":"https://openalex.org/W4392908947","doi":"https://doi.org/10.1109/icassp48485.2024.10448325","title":"Sec2Sec Co-Attention Transformer for Video-Based Apparent Affective Prediction","display_name":"Sec2Sec Co-Attention Transformer for Video-Based Apparent Affective Prediction","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392908947","doi":"https://doi.org/10.1109/icassp48485.2024.10448325"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101149708","display_name":"Mingwei Sun","orcid":"https://orcid.org/0000-0002-1294-0345"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mingwei Sun","raw_affiliation_strings":["University of Maryland"],"affiliations":[{"raw_affiliation_string":"University of Maryland","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014223717","display_name":"Kunpeng Zhang","orcid":"https://orcid.org/0000-0002-1474-3169"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kunpeng Zhang","raw_affiliation_strings":["University of Maryland"],"affiliations":[{"raw_affiliation_string":"University of Maryland","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101149708"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":0.533,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.64712047,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"8255","last_page":"8259"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9557999968528748,"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":0.9557999968528748,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5994917750358582},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5457248091697693},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.10446691513061523},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08706498146057129},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0793149471282959}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5994917750358582},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5457248091697693},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.10446691513061523},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08706498146057129},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0793149471282959}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":21,"referenced_works":["https://openalex.org/W306648316","https://openalex.org/W2044807399","https://openalex.org/W2081835714","https://openalex.org/W2108525416","https://openalex.org/W2194775991","https://openalex.org/W2562607067","https://openalex.org/W2573933330","https://openalex.org/W2795078582","https://openalex.org/W2899351518","https://openalex.org/W2963155035","https://openalex.org/W2981072818","https://openalex.org/W2990408345","https://openalex.org/W3094502228","https://openalex.org/W3099638501","https://openalex.org/W3127877691","https://openalex.org/W3138516171","https://openalex.org/W4205218375","https://openalex.org/W4214612132","https://openalex.org/W4245923654","https://openalex.org/W4312560592","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Video-based":[0],"apparent":[1,72,90],"affect":[2,73,91],"detection":[3],"plays":[4],"a":[5,40,60,66],"crucial":[6],"role":[7],"in":[8,46,74,88],"video":[9,30],"understanding,":[10],"as":[11,17],"it":[12],"encompasses":[13],"various":[14],"elements":[15],"such":[16],"vision,":[18],"audio,":[19],"audio-visual":[20],"interactions,":[21],"and":[22,98],"spatiotemporal":[23],"information,":[24],"which":[25],"are":[26],"essential":[27],"for":[28,70],"accurate":[29],"predictions.":[31],"However,":[32],"existing":[33],"approaches":[34],"often":[35],"focus":[36],"on":[37,92],"extracting":[38],"only":[39],"subset":[41],"of":[42,51,112],"these":[43],"elements,":[44],"resulting":[45],"the":[47,110,117],"limited":[48],"predictive":[49],"capacity":[50],"their":[52],"models.":[53],"To":[54],"address":[55],"this":[56],"limitation,":[57],"we":[58],"propose":[59],"novel":[61],"LSTM-based":[62],"network":[63],"augmented":[64],"with":[65],"Transformer":[67,83],"co-attention":[68],"mechanism":[69],"predicting":[71,89],"videos.":[75],"We":[76],"demonstrate":[77],"that":[78],"our":[79,102],"proposed":[80],"Sec2Sec":[81],"Co-attention":[82],"surpasses":[84],"multiple":[85],"state-of-the-art":[86],"methods":[87],"two":[93],"widely":[94],"used":[95],"datasets:":[96],"LIRIS-ACCEDE":[97],"First":[99],"Impressions.":[100],"Notably,":[101],"model":[103],"offers":[104],"interpretability,":[105],"allowing":[106],"us":[107],"to":[108,116],"examine":[109],"contributions":[111],"different":[113],"time":[114],"points":[115],"overall":[118],"prediction.":[119],"The":[120],"implementation":[121],"is":[122],"available":[123],"at:":[124],"https://github.com/nestorsun/sec2sec.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}