{"id":"https://openalex.org/W4405167883","doi":"https://doi.org/10.1145/3700906.3700912","title":"A Novel Method on Convolutional Classification for Unifying Multimodal","display_name":"A Novel Method on Convolutional Classification for Unifying Multimodal","publication_year":2024,"publication_date":"2024-07-12","ids":{"openalex":"https://openalex.org/W4405167883","doi":"https://doi.org/10.1145/3700906.3700912"},"language":"en","primary_location":{"id":"doi:10.1145/3700906.3700912","doi":"https://doi.org/10.1145/3700906.3700912","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3700906.3700912","pdf_url":null,"source":{"id":"https://openalex.org/S7407088325","display_name":"International Conference on Image Processing, Machine Learning and Pattern Recognition (IPMLPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Proceedings of the International Conference on Image Processing, Machine Learning and Pattern Recognition","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5001728530","display_name":"Liqing Zhang","orcid":"https://orcid.org/0009-0001-3488-8795","observed_orcids":["https://orcid.org/0009-0001-3488-8795"]},"institutions":[{"id":"https://openalex.org/I146071755","display_name":"Kunming University","ror":"https://ror.org/035rhx828","country_code":"CN","type":"education","lineage":["https://openalex.org/I146071755"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqing Zhang","raw_affiliation_strings":["College of Information Engineering, Kunming University, Kunming, Yunnan, China","Key Laboratory of Data Governance and Intelligent Decision in Universities of Yunnan, Kunming, Yunnan, China"],"raw_orcid":"https://orcid.org/0009-0001-3488-8795","affiliations":[{"raw_affiliation_string":"College of Information Engineering, Kunming University, Kunming, Yunnan, China","institution_ids":["https://openalex.org/I146071755"]},{"raw_affiliation_string":"Key Laboratory of Data Governance and Intelligent Decision in Universities of Yunnan, Kunming, Yunnan, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109750934","display_name":"H.H He","orcid":"https://orcid.org/0009-0001-8327-2567","observed_orcids":["https://orcid.org/0009-0001-8327-2567","https://orcid.org/0009-0006-3393-8259"]},"institutions":[{"id":"https://openalex.org/I146071755","display_name":"Kunming University","ror":"https://ror.org/035rhx828","country_code":"CN","type":"education","lineage":["https://openalex.org/I146071755"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Houhua He","raw_affiliation_strings":["College of Information Engineering, Kunming University, Kunming, Yunnan, China","Key Laboratory of Data Governance and Intelligent Decision in Universities of Yunnan, Kunming, Yunnan, China"],"raw_orcid":"https://orcid.org/0009-0006-3393-8259","affiliations":[{"raw_affiliation_string":"College of Information Engineering, Kunming University, Kunming, Yunnan, China","institution_ids":["https://openalex.org/I146071755"]},{"raw_affiliation_string":"Key Laboratory of Data Governance and Intelligent Decision in Universities of Yunnan, Kunming, Yunnan, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093255392","display_name":"Md Golam Saklain","orcid":"https://orcid.org/0009-0003-9566-5637","observed_orcids":["https://orcid.org/0009-0003-9566-5637"]},"institutions":[{"id":"https://openalex.org/I146071755","display_name":"Kunming University","ror":"https://ror.org/035rhx828","country_code":"CN","type":"education","lineage":["https://openalex.org/I146071755"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Md Golam Saklain","raw_affiliation_strings":["College of Information Engineering, Kunming University, Kunming, Yunnan, China","Key Laboratory of Data Governance and Intelligent Decision in Universities of Yunnan, Kunming, Yunnan, China"],"raw_orcid":"https://orcid.org/0009-0003-9566-5637","affiliations":[{"raw_affiliation_string":"College of Information Engineering, Kunming University, Kunming, Yunnan, China","institution_ids":["https://openalex.org/I146071755"]},{"raw_affiliation_string":"Key Laboratory of Data Governance and Intelligent Decision in Universities of Yunnan, Kunming, Yunnan, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082081605","display_name":"Hengbin Li","orcid":"https://orcid.org/0009-0002-8648-2807","observed_orcids":["https://orcid.org/0009-0002-8648-2807"]},"institutions":[{"id":"https://openalex.org/I146071755","display_name":"Kunming University","ror":"https://ror.org/035rhx828","country_code":"CN","type":"education","lineage":["https://openalex.org/I146071755"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengbin Li","raw_affiliation_strings":["College of Information Engineering, Kunming University, Kunming, Yunnan, China","Key Laboratory of Data Governance and Intelligent Decision in Universities of Yunnan, Kunming, Yunnan, China"],"raw_orcid":"https://orcid.org/0009-0002-8648-2807","affiliations":[{"raw_affiliation_string":"College of Information Engineering, Kunming University, Kunming, Yunnan, China","institution_ids":["https://openalex.org/I146071755"]},{"raw_affiliation_string":"Key Laboratory of Data Governance and Intelligent Decision in Universities of Yunnan, Kunming, Yunnan, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079036466","display_name":"Xiaoan Liu","orcid":"https://orcid.org/0009-0008-3092-3873","observed_orcids":["https://orcid.org/0009-0008-3092-3873"]},"institutions":[{"id":"https://openalex.org/I146071755","display_name":"Kunming University","ror":"https://ror.org/035rhx828","country_code":"CN","type":"education","lineage":["https://openalex.org/I146071755"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoan Liu","raw_affiliation_strings":["College of Information Engineering, Kunming University, Kunming, Yunnan, China","Key Laboratory of Data Governance and Intelligent Decision in Universities of Yunnan, Kunming, Yunnan, China"],"raw_orcid":"https://orcid.org/0009-0008-3092-3873","affiliations":[{"raw_affiliation_string":"College of Information Engineering, Kunming University, Kunming, Yunnan, China","institution_ids":["https://openalex.org/I146071755"]},{"raw_affiliation_string":"Key Laboratory of Data Governance and Intelligent Decision in Universities of Yunnan, Kunming, Yunnan, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065493610","display_name":"Fei Deng","orcid":"https://orcid.org/0000-0002-9448-5496","observed_orcids":["https://orcid.org/0000-0002-9448-5496"]},"institutions":[{"id":"https://openalex.org/I146071755","display_name":"Kunming University","ror":"https://ror.org/035rhx828","country_code":"CN","type":"education","lineage":["https://openalex.org/I146071755"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Deng","raw_affiliation_strings":["College of Information Engineering, Kunming University, Kunming, Yunnan, China","Key Laboratory of Data Governance and Intelligent Decision in Universities of Yunnan, Kunming, Yunnan, China"],"raw_orcid":"https://orcid.org/0000-0002-9448-5496","affiliations":[{"raw_affiliation_string":"College of Information Engineering, Kunming University, Kunming, Yunnan, China","institution_ids":["https://openalex.org/I146071755"]},{"raw_affiliation_string":"Key Laboratory of Data Governance and Intelligent Decision in Universities of Yunnan, Kunming, Yunnan, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I146071755"],"apc_list":null,"apc_paid":null,"fwci":0.1401,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.36534242,"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":"35","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9556000232696533,"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":0.9556000232696533,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.03799999877810478,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0013000000035390258,"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/multimodal-classification","display_name":"multimodal classification","score":0.9829999804496765},{"id":"https://openalex.org/keywords/multiscale-attention","display_name":"multi-scale attention","score":0.7080000042915344},{"id":"https://openalex.org/keywords/sliding-window-attention","display_name":"sliding window attention","score":0.7080000042915344},{"id":"https://openalex.org/keywords/long-range-dependence","display_name":"long-range dependence","score":0.7129999995231628},{"id":"https://openalex.org/keywords/multi-scale-feature-aggregation","display_name":"multi-scale feature aggregation","score":0.47200000286102295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541954517364502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5085381269454956},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3448134958744049}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3700906.3700912","doi":"https://doi.org/10.1145/3700906.3700912","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3700906.3700912","pdf_url":null,"source":{"id":"https://openalex.org/S7407088325","display_name":"International Conference on Image Processing, Machine Learning and Pattern Recognition (IPMLPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Proceedings of the International Conference on Image Processing, Machine Learning and Pattern Recognition","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2752782242","https://openalex.org/W2896457183","https://openalex.org/W3138516171","https://openalex.org/W4312443924","https://openalex.org/W4317829628","https://openalex.org/W4319663728","https://openalex.org/W4385346076","https://openalex.org/W4386319016","https://openalex.org/W4394865305","https://openalex.org/W4396803033","https://openalex.org/W4402775306"],"related_works":["https://openalex.org/W2997395940","https://openalex.org/W4401552326","https://openalex.org/W7133331989","https://openalex.org/W7166857468","https://openalex.org/W3168896398","https://openalex.org/W2965547260","https://openalex.org/W3095907242","https://openalex.org/W4409560151","https://openalex.org/W4386598562","https://openalex.org/W3112864462"],"abstract_inverted_index":{"For":[0,57,106],"the":[1,7,13,30,34,73,78,93,111,114,143,146,153,161,164,174,182],"current":[2],"multimodal":[3],"classification,":[4],"there":[5],"is":[6,178,194],"drawback":[8],"that":[9],"can":[10,60,117,131,157,167],"not":[11],"cope":[12],"any":[14],"combination":[15],"of":[16,77,113,128,163,188],"modalities.":[17],"So,":[18],"this":[19,172],"paper":[20],"proposes":[21],"a":[22,62],"novel":[23],"unified":[24],"convolutional":[25,75,80],"classification":[26],"model":[27],"for":[28,40],"overcoming":[29],"disadvantage.":[31],"We":[32],"propose":[33],"Giant":[35],"Multi-Scale":[36],"Dilation":[37],"Block":[38,55],"(GMSDB)":[39],"enhancing":[41],"Spatial":[42],"Attention":[43,49,54,129],"Block,":[44],"including":[45],"Large":[46],"Separable":[47],"Kernel":[48],"(LSKA)":[50],"and":[51,71,86,96,124,160,181],"Multiscale":[52],"Swelling":[53],"(MSAB),":[56],"LSKA,":[58],"GMSDB":[59],"obtain":[61],"larger":[63],"sensory":[64,155],"field":[65,156],"via":[66],"an":[67,100],"ultra":[68,101],"large":[69,102],"kernel,":[70],"decompose":[72],"2D":[74],"kernel":[76],"deep":[79],"layer":[81],"into":[82,99,120],"cascaded":[83],"horizontal":[84],"1D":[85,88],"vertical":[87],"kernels,":[89],"which":[90],"effectively":[91,195],"converts":[92],"long":[94],"text":[95],"video":[97],"data":[98],"vector":[103],"matrix":[104],"representation.":[105],"MSDA,":[107],"with":[108],"multi-head":[109],"design,":[110],"channels":[112],"feature":[115],"map":[116],"be":[118,132,158,168],"divided":[119],"n":[121],"different":[122,135,139,189,192],"heads,":[123],"Sliding":[125],"Window":[126],"Expansion":[127],"(SWDA)":[130],"performed":[133],"through":[134],"dilation":[136],"rates":[137],"at":[138,149],"heads.":[140],"Based":[141],"on":[142,184],"above":[144],"model,":[145],"semantic":[147],"information":[148],"various":[150],"scales":[151,190],"within":[152],"attended":[154],"aggregated,":[159],"redundancy":[162],"self-attention":[165],"mechanism":[166],"reduced":[169],"effectively.":[170],"In":[171],"way,":[173],"long-range":[175],"dependence":[176],"problem":[177],"successfully":[179],"solved":[180],"ability":[183],"adapting":[185],"to":[186],"inputs":[187],"from":[191],"modes":[193],"improved.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2024-12-09T00:00:00"}