{"id":"https://openalex.org/W4225307240","doi":"https://doi.org/10.1109/icassp43922.2022.9746418","title":"Mmlatch: Bottom-Up Top-Down Fusion For Multimodal Sentiment Analysis","display_name":"Mmlatch: Bottom-Up Top-Down Fusion For Multimodal Sentiment Analysis","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225307240","doi":"https://doi.org/10.1109/icassp43922.2022.9746418"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746418","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746418","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/A5026032406","display_name":"Georgios Paraskevopoulos","orcid":"https://orcid.org/0000-0003-4067-6294"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]},{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Georgios Paraskevopoulos","raw_affiliation_strings":["National Technical University of Athens,Athens,Greece","National Technical University of Athens, Athens, Greece","Athena Research Center, Institute for Language and Speech Processing, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Technical University of Athens,Athens,Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"National Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"Athena Research Center, Institute for Language and Speech Processing, Athens, Greece","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102773432","display_name":"Efthymios Georgiou","orcid":"https://orcid.org/0000-0002-6042-9584"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]},{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Efthymios Georgiou","raw_affiliation_strings":["National Technical University of Athens,Athens,Greece","Athena Research Center, Institute for Language and Speech Processing, Athens, Greece","National Technical University of Athens, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Technical University of Athens,Athens,Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"Athena Research Center, Institute for Language and Speech Processing, Athens, Greece","institution_ids":["https://openalex.org/I4210098364"]},{"raw_affiliation_string":"National Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022918334","display_name":"Alexandras Potamianos","orcid":null},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Alexandras Potamianos","raw_affiliation_strings":["National Technical University of Athens,Athens,Greece","Behavioral Signal Technologies, Los Angeles, CA, USA","National Technical University of Athens, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Technical University of Athens,Athens,Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"Behavioral Signal Technologies, Los Angeles, CA, USA","institution_ids":[]},{"raw_affiliation_string":"National Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5365,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.92808973,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4573","last_page":"4577"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9979000091552734,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9979000091552734,"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/T10860","display_name":"Speech and Audio Processing","score":0.9940000176429749,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9912999868392944,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.748044490814209},{"id":"https://openalex.org/keywords/sensory-system","display_name":"Sensory system","score":0.5652835369110107},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5507654547691345},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5500348210334778},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5242264866828918},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4971800148487091},{"id":"https://openalex.org/keywords/top-down-and-bottom-up-design","display_name":"Top-down and bottom-up design","score":0.479230672121048},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4537352919578552},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.44837790727615356},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4468487501144409},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38121575117111206},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.1285388171672821},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09632840752601624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.748044490814209},{"id":"https://openalex.org/C94487597","wikidata":"https://www.wikidata.org/wiki/Q11101","display_name":"Sensory system","level":2,"score":0.5652835369110107},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5507654547691345},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5500348210334778},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5242264866828918},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4971800148487091},{"id":"https://openalex.org/C135798126","wikidata":"https://www.wikidata.org/wiki/Q2167279","display_name":"Top-down and bottom-up design","level":2,"score":0.479230672121048},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4537352919578552},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.44837790727615356},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4468487501144409},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38121575117111206},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.1285388171672821},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09632840752601624},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746418","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746418","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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":51,"referenced_works":["https://openalex.org/W336490364","https://openalex.org/W1522301498","https://openalex.org/W1933349210","https://openalex.org/W1966247273","https://openalex.org/W1974684947","https://openalex.org/W2026243162","https://openalex.org/W2034214321","https://openalex.org/W2053807215","https://openalex.org/W2055332436","https://openalex.org/W2064675550","https://openalex.org/W2108554366","https://openalex.org/W2130565691","https://openalex.org/W2153720647","https://openalex.org/W2302086703","https://openalex.org/W2407555063","https://openalex.org/W2533262878","https://openalex.org/W2583643061","https://openalex.org/W2600210397","https://openalex.org/W2619383789","https://openalex.org/W2883409523","https://openalex.org/W2962931510","https://openalex.org/W2963360627","https://openalex.org/W2963703618","https://openalex.org/W2963710346","https://openalex.org/W2963811535","https://openalex.org/W2964010806","https://openalex.org/W2964051877","https://openalex.org/W2964216663","https://openalex.org/W2964266095","https://openalex.org/W2964346351","https://openalex.org/W2966715458","https://openalex.org/W2972015118","https://openalex.org/W2972493869","https://openalex.org/W2972921424","https://openalex.org/W3007282427","https://openalex.org/W3015558147","https://openalex.org/W3034266838","https://openalex.org/W3035299099","https://openalex.org/W3045969489","https://openalex.org/W3084283759","https://openalex.org/W3099414366","https://openalex.org/W3105484484","https://openalex.org/W3151576663","https://openalex.org/W3153416536","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6743446608","https://openalex.org/W6753277404","https://openalex.org/W6766904570","https://openalex.org/W6784019883","https://openalex.org/W6794047078"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W1543048115","https://openalex.org/W3081694532","https://openalex.org/W2374013449","https://openalex.org/W73545470","https://openalex.org/W1969211203","https://openalex.org/W22958017","https://openalex.org/W2364381299","https://openalex.org/W2374430585"],"abstract_inverted_index":{"Current":[0],"deep":[1,59],"learning":[2,60],"approaches":[3],"for":[4,92,117],"multimodal":[5,118],"fusion":[6,10,138],"rely":[7],"on":[8,121],"bottom-up":[9],"of":[11,28,34],"high":[12],"and":[13,95,133],"mid-level":[14],"latent":[15],"modality":[16,94],"representations":[17,39,91,98],"(late/mid":[18],"fusion)":[19],"or":[20],"low":[21],"level":[22],"sensory":[23,43,102],"inputs":[24,44],"(early":[25],"fusion).":[26],"Models":[27],"human":[29],"perception":[30],"highlight":[31],"the":[32,41,80,101,105,114,129],"importance":[33],"top-down":[35,52,72,109],"fusion,":[36],"where":[37],"high-level":[38,90],"affect":[40],"way":[42],"are":[45,54],"perceived,":[46],"i.e.":[47],"cognition":[48],"affects":[49],"perception.":[50],"These":[51],"interactions":[53],"not":[55],"captured":[56],"in":[57,79],"current":[58],"models.":[61],"In":[62],"this":[63],"work":[64],"we":[65],"propose":[66],"a":[67,76],"neural":[68],"architecture":[69],"that":[70],"captures":[71],"cross-modal":[73],"interactions,":[74],"using":[75],"feedback":[77],"mechanism":[78,88],"forward":[81],"pass":[82],"during":[83],"network":[84],"training.":[85],"The":[86],"proposed":[87,115],"extracts":[89],"each":[93],"uses":[96],"these":[97],"to":[99,107],"mask":[100],"inputs,":[103],"allowing":[104],"model":[106,116],"perform":[108],"feature":[110],"masking.":[111],"We":[112],"apply":[113],"sentiment":[119],"recognition":[120],"CMU-MOSEI.":[122],"Our":[123],"method":[124],"shows":[125],"consistent":[126],"improvements":[127],"over":[128,134],"well":[130],"established":[131],"MulT":[132],"our":[135],"strong":[136],"late":[137],"baseline,":[139],"achieving":[140],"state-of-the-art":[141],"results.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}