{"id":"https://openalex.org/W4372260280","doi":"https://doi.org/10.1109/icassp49357.2023.10096863","title":"Multimodal Facial Action unit Detection with Physiological Signals","display_name":"Multimodal Facial Action unit Detection with Physiological Signals","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260280","doi":"https://doi.org/10.1109/icassp49357.2023.10096863"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100319820","display_name":"Zhihua Li","orcid":"https://orcid.org/0000-0001-6564-6927"},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhihua Li","raw_affiliation_strings":["Binghamton University,Department of Computer Science,NY,USA","Department of Computer Science, Binghamton University, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Binghamton University,Department of Computer Science,NY,USA","institution_ids":["https://openalex.org/I123946342"]},{"raw_affiliation_string":"Department of Computer Science, Binghamton University, NY, USA","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104114056","display_name":"Lijun Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lijun Yin","raw_affiliation_strings":["Binghamton University,Department of Computer Science,NY,USA","Department of Computer Science, Binghamton University, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Binghamton University,Department of Computer Science,NY,USA","institution_ids":["https://openalex.org/I123946342"]},{"raw_affiliation_string":"Department of Computer Science, Binghamton University, NY, USA","institution_ids":["https://openalex.org/I123946342"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I123946342"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9993000030517578,"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":0.9993000030517578,"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/T11448","display_name":"Face recognition and analysis","score":0.9889000058174133,"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9848999977111816,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.6252428293228149},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5873693227767944},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.5200895071029663},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4874894618988037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46298256516456604},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4538714289665222},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.41948074102401733},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37270963191986084},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13913103938102722},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08279013633728027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6252428293228149},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5873693227767944},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.5200895071029663},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4874894618988037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46298256516456604},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4538714289665222},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.41948074102401733},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37270963191986084},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13913103938102722},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08279013633728027},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1595126664","https://openalex.org/W1950010372","https://openalex.org/W2051297709","https://openalex.org/W2078671978","https://openalex.org/W2152512410","https://openalex.org/W2164368909","https://openalex.org/W2169622879","https://openalex.org/W2470957930","https://openalex.org/W2741295496","https://openalex.org/W2789992948","https://openalex.org/W2808359495","https://openalex.org/W2903991757","https://openalex.org/W2963875208","https://openalex.org/W2969059826","https://openalex.org/W2995659499","https://openalex.org/W3011227460","https://openalex.org/W3016504312","https://openalex.org/W3101614002","https://openalex.org/W3115865297","https://openalex.org/W3127053097","https://openalex.org/W3157716656","https://openalex.org/W3173225380","https://openalex.org/W3176327573","https://openalex.org/W3205983874","https://openalex.org/W3211152704","https://openalex.org/W4253487878","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6752724743"],"related_works":["https://openalex.org/W611386996","https://openalex.org/W2371343292","https://openalex.org/W629290331","https://openalex.org/W617685022","https://openalex.org/W1509983653","https://openalex.org/W3215563689","https://openalex.org/W610590827","https://openalex.org/W591599671","https://openalex.org/W1556748146","https://openalex.org/W1990796017"],"abstract_inverted_index":{"Most":[0],"of":[1,30],"the":[2,27,55,86,97],"existing":[3],"facial":[4],"action":[5],"unit":[6],"detection":[7,12,42],"models":[8],"seek":[9],"to":[10,52,67,84,95],"improve":[11],"accuracy":[13],"by":[14],"utilizing":[15],"multiple":[16],"visual":[17,93],"modalities,":[18],"including":[19],"3D":[20],"geometry,":[21],"thermal,":[22],"and":[23,37,73,77,121],"depth":[24],"images.":[25],"However,":[26],"potential":[28],"usage":[29],"heterogeneous":[31],"physiological":[32,58,98,102],"modalities":[33],"(e.g.,":[34],"heart":[35],"rate":[36],"blood":[38],"pressure)":[39],"for":[40],"AU":[41],"is":[43],"not":[44],"considered":[45],"in":[46],"current":[47],"works.":[48],"Meanwhile,":[49],"it\u2019s":[50],"challenging":[51],"fully":[53],"utilize":[54,91],"hidden":[56],"emotion-correlated":[57],"signals.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63,90],"propose":[64],"deep":[65],"networks":[66],"extract":[68],"temporal":[69],"features":[70],"from":[71],"periodic":[72],"non-periodic":[74],"time-series":[75],"signals":[76],"design":[78],"an":[79],"informativeness-based":[80],"feature":[81],"fusion":[82],"module":[83],"handle":[85],"signal":[87],"noise.":[88],"Then,":[89],"spatial-temporal":[92],"representations":[94],"infer":[96],"embeddings,":[99],"allowing":[100],"absent":[101],"data":[103],"during":[104],"testing.":[105],"Experiments":[106],"show":[107],"that":[108],"our":[109],"multimodal":[110],"framework":[111],"achieves":[112],"state-of-the-art":[113],"performances":[114],"on":[115],"two":[116],"widely":[117],"used":[118],"datasets:":[119],"MMSE":[120],"BP4D.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}