{"id":"https://openalex.org/W4416251286","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227548","title":"Multi-scale Weight-residual Transformer for Uniand Multi-modal Representation Learning","display_name":"Multi-scale Weight-residual Transformer for Uniand Multi-modal Representation Learning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251286","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227548"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5111149111","display_name":"Dingxin Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105229","display_name":"City University of Hong Kong, Shenzhen Research Institute","ror":"https://ror.org/00xc0ma20","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210105229"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dingxin Cheng","raw_affiliation_strings":["Shenzhen Research Institute of Shandong University,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Shandong University,Shenzhen,China","institution_ids":["https://openalex.org/I4210105229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101908761","display_name":"Jiawei Gu","orcid":"https://orcid.org/0000-0003-2650-6870"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Gu","raw_affiliation_strings":["Shandong University,School of Mechanical, Electrical & Information Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University,School of Mechanical, Electrical & Information Engineering","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029754332","display_name":"Kang Xie","orcid":"https://orcid.org/0000-0002-8529-775X"},"institutions":[{"id":"https://openalex.org/I1302611135","display_name":"Ministry of Public Security of the People's Republic of China","ror":"https://ror.org/00bt9we26","country_code":"CN","type":"government","lineage":["https://openalex.org/I1302611135"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kang Xie","raw_affiliation_strings":["Key Lab of Information Network Security Ministry of Public Security"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Lab of Information Network Security Ministry of Public Security","institution_ids":["https://openalex.org/I1302611135"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104325435","display_name":"Mengyue Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2800372957","display_name":"China Electronics Technology Group Corporation","ror":"https://ror.org/0098hst83","country_code":"CN","type":"company","lineage":["https://openalex.org/I2800372957"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyue Zhang","raw_affiliation_strings":["The 54th Research Institute of China Electronics Technology Group Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The 54th Research Institute of China Electronics Technology Group Corporation","institution_ids":["https://openalex.org/I2800372957"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100367368","display_name":"Gang Wang","orcid":"https://orcid.org/0000-0002-3359-3565"},"institutions":[{"id":"https://openalex.org/I2800372957","display_name":"China Electronics Technology Group Corporation","ror":"https://ror.org/0098hst83","country_code":"CN","type":"company","lineage":["https://openalex.org/I2800372957"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Wang","raw_affiliation_strings":["The 54th Research Institute of China Electronics Technology Group Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The 54th Research Institute of China Electronics Technology Group Corporation","institution_ids":["https://openalex.org/I2800372957"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007360513","display_name":"Bin Jiang","orcid":"https://orcid.org/0000-0002-5840-9664"},"institutions":[{"id":"https://openalex.org/I4210105229","display_name":"City University of Hong Kong, Shenzhen Research Institute","ror":"https://ror.org/00xc0ma20","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210105229"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Jiang","raw_affiliation_strings":["Shenzhen Research Institute of Shandong University,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Shandong University,Shenzhen,China","institution_ids":["https://openalex.org/I4210105229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39461821,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2757999897003174,"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":0.2757999897003174,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.15230000019073486,"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":0.13199999928474426,"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/transformer","display_name":"Transformer","score":0.6473000049591064},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5174000263214111},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.3402000069618225},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.3353999853134155},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3160000145435333},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.31189998984336853},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2946999967098236}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6804999709129333},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6473000049591064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5392000079154968},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5174000263214111},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3450999855995178},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320329791","display_name":"Shenzhen Fundamental Research Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1849277567","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2150134853","https://openalex.org/W2183341477","https://openalex.org/W2533598788","https://openalex.org/W2952138241","https://openalex.org/W2963091558","https://openalex.org/W2963495494","https://openalex.org/W2963916161","https://openalex.org/W2964089981","https://openalex.org/W2998508940","https://openalex.org/W3034743747","https://openalex.org/W3035356601","https://openalex.org/W3043120882","https://openalex.org/W3093471110","https://openalex.org/W3104862079","https://openalex.org/W3121523901","https://openalex.org/W3130619535","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3151130473","https://openalex.org/W3155721152","https://openalex.org/W3175817778","https://openalex.org/W3176201273","https://openalex.org/W3186567887","https://openalex.org/W3190492058","https://openalex.org/W4211053420","https://openalex.org/W4214493665","https://openalex.org/W4214636423","https://openalex.org/W4214773477","https://openalex.org/W4230025115","https://openalex.org/W4253028564","https://openalex.org/W4283814553","https://openalex.org/W4289752563","https://openalex.org/W4293567872","https://openalex.org/W4304091802","https://openalex.org/W4312402470","https://openalex.org/W4312509824","https://openalex.org/W4319299894","https://openalex.org/W4375839990","https://openalex.org/W4385245566","https://openalex.org/W4385572302","https://openalex.org/W4386065705","https://openalex.org/W4386066311","https://openalex.org/W4390873017","https://openalex.org/W4400520900","https://openalex.org/W4402727186"],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"Transformer":[1,19,73],"has":[2],"demonstrated":[3],"its":[4],"comparable":[5],"performance":[6],"in":[7,18,27,154],"several":[8,189],"vision":[9],"tasks":[10],"and":[11,52,82,88,93,107,191],"multimedia":[12],"domains.":[13],"However,":[14],"the":[15,24,28,40,44,53,99,118,125,133,151,158,163,166,184],"key":[16,169],"self-attention":[17,101],"computes":[20],"global":[21,104,126],"attention":[22,38,109,127,137],"to":[23,42,117,149],"image":[25,51],"primarily":[26],"spatial":[29,37],"dimension,":[30],"which":[31,113,160],"is":[32,114],"a":[33,69,143,175],"non-local":[34],"operation.":[35],"Such":[36],"lacks":[39],"ability":[41,134],"model":[43,167],"relationship":[45],"among":[46],"local":[47,81,119,136],"regions":[48],"of":[49,128,135,157,165,186],"an":[50],"learned":[54],"representations":[55],"are":[56],"biased":[57],"with":[58],"redundant":[59],"channel":[60,147,170],"information":[61,105],"perturbation.":[62],"To":[63],"address":[64],"this":[65,97],"problem,":[66],"we":[67,79,141],"propose":[68],"new":[70],"Multi-scale":[71],"Weight-residual":[72],"(MWT)":[74],"for":[75,146,168],"uni-and":[76],"multi-modal.":[77],"Specifically,":[78],"generate":[80],"regional":[83,111],"tokens":[84],"by":[85],"different":[86],"convolutions":[87],"use":[89],"them":[90],"as":[91,138],"query":[92],"key-value,":[94],"respectively.":[95],"In":[96],"way,":[98],"computed":[100],"ensures":[102],"both":[103],"interaction":[106],"focuses":[108],"on":[110,188],"information,":[112],"more":[115,176],"relevant":[116],"information.":[120],"It":[121],"not":[122],"only":[123],"retains":[124],"transformers":[129],"but":[130],"also":[131],"obtains":[132],"CNNs.":[139],"Moreover,":[140],"introduce":[142],"weight-residual":[144],"network":[145],"dimension":[148],"alleviate":[150],"feature":[152,179],"weakening":[153],"deeper":[155],"layers":[156],"network,":[159],"can":[161,173],"improve":[162],"sensitivity":[164],"representations.":[171],"These":[172],"build":[174],"abstract":[177],"high-level":[178],"representation.":[180],"Extensive":[181],"experiments":[182],"demonstrate":[183],"effectiveness":[185],"MWT":[187],"uni-":[190],"multimodal":[192],"benchmark":[193],"tasks.":[194]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-14T00:00:00"}