{"id":"https://openalex.org/W4399254592","doi":"https://doi.org/10.1145/3660395.3660454","title":"Multimodal image-text sentiment analysis based on image attention enhancement: Leveraging CBAM to enhance image features for capturing sentiment information in images for facilitating multimodal sentiment analysis","display_name":"Multimodal image-text sentiment analysis based on image attention enhancement: Leveraging CBAM to enhance image features for capturing sentiment information in images for facilitating multimodal sentiment analysis","publication_year":2023,"publication_date":"2023-09-22","ids":{"openalex":"https://openalex.org/W4399254592","doi":"https://doi.org/10.1145/3660395.3660454"},"language":"en","primary_location":{"id":"doi:10.1145/3660395.3660454","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3660395.3660454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 3rd Guangdong-Hong Kong-Macao Greater Bay Area Artificial Intelligence and Big Data Forum","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/A5079175094","display_name":"Xiangyu Kong","orcid":"https://orcid.org/0009-0007-8115-2733"},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiangyu Kong","raw_affiliation_strings":["School of Optical Information and Energy Engineering, School of Mathematics and Physics, Wuhan Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Optical Information and Energy Engineering, School of Mathematics and Physics, Wuhan Institute of Technology, China","institution_ids":["https://openalex.org/I91125648"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027075917","display_name":"Xingxing Yao","orcid":"https://orcid.org/0000-0002-2725-943X"},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingxing Yao","raw_affiliation_strings":["School of Optical Information and Energy Engineering, School of Mathematics and Physics, Wuhan Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Optical Information and Energy Engineering, School of Mathematics and Physics, Wuhan Institute of Technology, China","institution_ids":["https://openalex.org/I91125648"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013957924","display_name":"Hai Liu","orcid":"https://orcid.org/0009-0002-8135-9228"},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai Liu","raw_affiliation_strings":["School of Optical Information and Energy Engineering, School of Mathematics and Physics, Wuhan Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Optical Information and Energy Engineering, School of Mathematics and Physics, Wuhan Institute of Technology, China","institution_ids":["https://openalex.org/I91125648"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079175094"],"corresponding_institution_ids":["https://openalex.org/I91125648"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22515036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"346","last_page":"351"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9871000051498413,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9829999804496765,"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":0.8154904842376709},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.7059918642044067},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6531020402908325},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5515581369400024},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5422483682632446},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5224819779396057},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5218426585197449},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5079506039619446},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5069037079811096},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4435790181159973},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4363604784011841},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4179408550262451},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3350728750228882},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2758157253265381}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8154904842376709},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.7059918642044067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6531020402908325},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5515581369400024},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5422483682632446},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5224819779396057},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5218426585197449},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5079506039619446},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5069037079811096},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4435790181159973},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4363604784011841},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4179408550262451},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3350728750228882},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2758157253265381},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3660395.3660454","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3660395.3660454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 3rd Guangdong-Hong Kong-Macao Greater Bay Area Artificial Intelligence and Big Data Forum","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":11,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2265228180","https://openalex.org/W2552066052","https://openalex.org/W2562781711","https://openalex.org/W2744979708","https://openalex.org/W2798802604","https://openalex.org/W2884585870","https://openalex.org/W2911840101","https://openalex.org/W2964167669","https://openalex.org/W2964185501","https://openalex.org/W3214945732"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Traditional":[0],"sentiment":[1,59,147,163],"analysis":[2,60],"methods":[3],"are":[4,140],"often":[5],"confined":[6],"to":[7,11,36,46,125],"single":[8,34],"modality,":[9],"failing":[10],"fully":[12],"exploit":[13],"the":[14,21,41,96,102,123,134,150,159,174,179],"information":[15,26],"in":[16,158],"multimodal":[17,57,162],"data.":[18],"They":[19],"overlook":[20],"interaction":[22],"and":[23,118,131,145,169],"richness":[24],"of":[25,99,161],"among":[27],"different":[28],"modalities,":[29],"relying":[30],"solely":[31],"on":[32,63,149,178],"a":[33,56],"modality":[35],"extract":[37],"emotional":[38],"features":[39,114,132,139],"from":[40,74],"data":[42],"can":[43],"easily":[44],"lead":[45],"ambiguous":[47],"results.":[48],"To":[49,94],"address":[50],"this":[51,53],"issue,":[52],"paper":[54],"proposes":[55],"image-text":[58,152],"model":[61,69,77,89,124],"based":[62],"image":[64,91,100,113,138],"attention":[65,117],"enhancement,":[66],"MITSIAE.":[67],"The":[68,136,154],"employs":[70],"Bidirectional":[71],"Encoder":[72],"Representations":[73],"Transformers":[75],"(BERT)":[76],"for":[78,90],"text":[79,143,168],"feature":[80,92],"extraction,":[81],"followed":[82],"by":[83,173],"Visual":[84],"Geometry":[85],"Group":[86],"19":[87],"(VGG19)":[88],"extraction.":[93],"enhance":[95],"representational":[97],"capacity":[98],"features,":[101,144],"Convolutional":[103],"Block":[104],"Attention":[105],"Module":[106],"(CBAM)":[107],"was":[108],"employed,":[109],"which":[110,165],"attentively":[111],"weights":[112],"with":[115,142],"channel":[116],"spatial":[119],"attention.":[120],"This":[121],"enables":[122],"more":[126],"effectively":[127],"capture":[128],"key":[129],"regions":[130],"within":[133],"images.":[135],"enhanced":[137],"fused":[141,151],"conduct":[146],"classification":[148],"features.":[153],"proposed":[155],"approach's":[156],"effectiveness":[157],"task":[160],"analysis,":[164],"involves":[166],"both":[167],"images,":[170],"is":[171],"demonstrated":[172],"experimental":[175],"results":[176],"obtained":[177],"MVSA":[180],"dataset.":[181]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}