{"id":"https://openalex.org/W4414231736","doi":"https://doi.org/10.1109/ialp68296.2024.11156849","title":"AAT-CGF: A Cross-Modal Deep Fusion Framework with Attention Aggregation and Cross Graph Fusion for Multimodal Emotion Recognition","display_name":"AAT-CGF: A Cross-Modal Deep Fusion Framework with Attention Aggregation and Cross Graph Fusion for Multimodal Emotion Recognition","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4414231736","doi":"https://doi.org/10.1109/ialp68296.2024.11156849"},"language":"en","primary_location":{"id":"doi:10.1109/ialp68296.2024.11156849","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp68296.2024.11156849","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Asian Language Processing (IALP)","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/A5051380319","display_name":"Zhangcheng Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhangcheng Yang","raw_affiliation_strings":["College of Information Science and Technology, Donghua University,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Donghua University,Shanghai,China","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107885495","display_name":"Xuebin Zhang","orcid":"https://orcid.org/0000-0001-5778-2152"},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuebin Zhang","raw_affiliation_strings":["College of Information Science and Technology, Donghua University,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Donghua University,Shanghai,China","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045048913","display_name":"Longting Xu","orcid":"https://orcid.org/0000-0002-2329-895X"},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longting Xu","raw_affiliation_strings":["College of Information Science and Technology, Donghua University,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Donghua University,Shanghai,China","institution_ids":["https://openalex.org/I181326427"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051380319"],"corresponding_institution_ids":["https://openalex.org/I181326427"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26814818,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"272","last_page":"277"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9902999997138977,"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":0.9902999997138977,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9223999977111816,"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/emotion-recognition","display_name":"Emotion recognition","score":0.5403000116348267},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5216000080108643},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.48159998655319214},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4546999931335449},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4422999918460846},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4106000065803528},{"id":"https://openalex.org/keywords/affective-computing","display_name":"Affective computing","score":0.37599998712539673},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.37299999594688416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7962999939918518},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5954999923706055},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5403000116348267},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5216000080108643},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.48159998655319214},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4546999931335449},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4422999918460846},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4106000065803528},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3375999927520752},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.33660000562667847},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.28610000014305115},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp68296.2024.11156849","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp68296.2024.11156849","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2087122779","https://openalex.org/W2557374949","https://openalex.org/W2584561145","https://openalex.org/W2618843390","https://openalex.org/W2740550900","https://openalex.org/W2767484504","https://openalex.org/W2778940641","https://openalex.org/W2883853499","https://openalex.org/W2904483377","https://openalex.org/W2905562398","https://openalex.org/W2953461088","https://openalex.org/W2963710346","https://openalex.org/W2964216663","https://openalex.org/W2964346351","https://openalex.org/W2981372722","https://openalex.org/W2982645239","https://openalex.org/W3037572520","https://openalex.org/W3081987387","https://openalex.org/W3093203468","https://openalex.org/W3128412859","https://openalex.org/W3158616546","https://openalex.org/W4312758889","https://openalex.org/W4322730818","https://openalex.org/W4392397487","https://openalex.org/W4392657946","https://openalex.org/W4406158083"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"emotion":[1,161],"recognition":[2],"plays":[3],"a":[4,32,40,106,113,153],"crucial":[5],"role":[6],"in":[7,13,144],"advancing":[8,159],"human-computer":[9],"interaction,":[10],"with":[11],"applications":[12],"mental":[14],"health,":[15],"education,":[16],"and":[17,25,48,62,76,79,97,109,129,155],"intelligent":[18],"systems.":[19],"However,":[20],"effectively":[21],"capturing":[22,145],"the":[23,54],"dynamic":[24,94],"complementary":[26],"interactions":[27],"among":[28],"heterogeneous":[29],"modalities":[30],"remains":[31],"significant":[33],"challenge.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38],"propose":[39],"novel":[41],"framework,":[42],"AAT-CGF,":[43],"which":[44],"integrates":[45],"Attention-based":[46],"Aggregation":[47],"Cross-modal":[49],"Graph":[50],"Fusion":[51],"to":[52],"enhance":[53],"modeling":[55],"of":[56],"fine-grained":[57,88],"emotions":[58],"across":[59,137],"audio,":[60],"visual,":[61],"textual":[63],"modalities.":[64],"The":[65,149],"framework":[66],"first":[67],"extracts":[68],"modality-specific":[69],"features":[70,89,102],"using":[71,105],"LSTM":[72],"networks":[73],"for":[74,81,158],"audio":[75],"visual":[77],"data,":[78],"BERT":[80],"text.":[82],"To":[83],"capture":[84],"subtle":[85],"emotional":[86,147],"cues,":[87],"are":[90,103],"further":[91],"refined":[92],"via":[93],"time":[95],"warping":[96],"facial":[98],"landmark":[99],"detection.":[100],"These":[101],"aggregated":[104],"self-attention":[107],"mechanism":[108],"subsequently":[110],"fused":[111],"through":[112],"graph-based":[114],"structure":[115],"that":[116,132],"dynamically":[117],"learns":[118],"cross-modal":[119],"relationships.":[120],"Extensive":[121],"experiments":[122],"on":[123],"benchmark":[124],"datasets,":[125],"including":[126],"CMU-MOSI,":[127],"IEMOCAP,":[128],"CASIA,":[130],"show":[131],"AAT-CGF":[133],"achieves":[134],"competitive":[135],"performance":[136],"various":[138],"evaluation":[139],"metrics,":[140],"demonstrating":[141],"its":[142],"effectiveness":[143],"multimodal":[146,160],"information.":[148],"proposed":[150],"approach":[151],"contributes":[152],"promising":[154],"scalable":[156],"solution":[157],"recognition.":[162]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}