{"id":"https://openalex.org/W7105644389","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227612","title":"ECViT: Efficient Convolutional Vision Transformer with Local-Attention and Multi-scale Stages","display_name":"ECViT: Efficient Convolutional Vision Transformer with Local-Attention and Multi-scale Stages","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W7105644389","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227612"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227612","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":"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":null,"display_name":"Zhoujie Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhoujie Qian","raw_affiliation_strings":["Shanghai University,School of Computer Engineering and Science,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai University,School of Computer Engineering and Science,Shanghai,China","institution_ids":["https://openalex.org/I141962983"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I141962983"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57520595,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.8878999948501587,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.8878999948501587,"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":0.013399999588727951,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.00800000037997961,"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/transformer","display_name":"Transformer","score":0.6685000061988831},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.586899995803833},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5523999929428101},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4860000014305115},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.41830000281333923},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40059998631477356},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.35370001196861267},{"id":"https://openalex.org/keywords/convolutional-code","display_name":"Convolutional code","score":0.3481999933719635}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.745199978351593},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6685000061988831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6136999726295471},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.586899995803833},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5523999929428101},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4860000014305115},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.41830000281333923},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40059998631477356},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3555000126361847},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.3481999933719635},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.3458000123500824},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29420000314712524},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C2779757391","wikidata":"https://www.wikidata.org/wiki/Q6002292","display_name":"Image translation","level":3,"score":0.2662000060081482},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227612","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2147800946","https://openalex.org/W2194775991","https://openalex.org/W2549139847","https://openalex.org/W2601564443","https://openalex.org/W2618530766","https://openalex.org/W2963446712","https://openalex.org/W2963616706","https://openalex.org/W3096609285","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3170841864","https://openalex.org/W3211490618","https://openalex.org/W4214493665","https://openalex.org/W4214614183","https://openalex.org/W4214634256","https://openalex.org/W4246193833","https://openalex.org/W4385245566","https://openalex.org/W4402703046"],"related_works":[],"abstract_inverted_index":{"Vision":[0,49],"Transformers":[1],"(ViTs)":[2],"have":[3],"revolutionized":[4],"computer":[5],"vision":[6],"by":[7,84],"leveraging":[8],"self-attention":[9,29],"to":[10,24,75,105],"model":[11],"long-range":[12],"dependencies.":[13],"However,":[14],"ViTs":[15],"face":[16],"challenges":[17],"such":[18,68],"as":[19,69],"high":[20,150],"computational":[21,137],"costs":[22],"due":[23],"the":[25,31,46,58,81,92],"quadratic":[26],"scaling":[27],"of":[28,33,37,60],"and":[30,62,71,90,101,111,124,138],"requirement":[32],"a":[34,52,102],"large":[35],"amount":[36],"training":[38],"data.":[39],"To":[40],"address":[41],"these":[42],"limitations,":[43],"we":[44],"propose":[45],"Efficient":[47],"Convolutional":[48,76],"Transformer":[50,82],"(ECViT),":[51],"hybrid":[53],"architecture":[54],"that":[55,116,148],"effectively":[56],"combines":[57],"strengths":[59],"CNNs":[61],"Transformers.":[63],"ECViT":[64,117,141],"introduces":[65],"inductive":[66],"biases":[67],"locality":[70],"translation":[72],"invariance,":[73],"inherent":[74],"Neural":[77],"Networks":[78],"(CNNs)":[79],"into":[80],"framework":[83],"extracting":[85],"patches":[86],"from":[87],"low-level":[88],"features":[89],"enhancing":[91],"encoder":[93],"with":[94],"convolutional":[95],"operations.":[96],"Additionally,":[97],"it":[98],"incorporates":[99],"local-attention":[100],"pyramid":[103],"structure":[104],"enable":[106],"efficient":[107],"multi-scale":[108],"feature":[109],"extraction":[110],"representation.":[112],"Experimental":[113],"results":[114],"demonstrate":[115],"achieves":[118],"an":[119,143],"optimal":[120],"balance":[121],"between":[122],"performance":[123],"efficiency,":[125],"outperforming":[126],"state-of-the-art":[127],"models":[128],"on":[129],"various":[130],"image":[131],"classification":[132],"tasks":[133],"while":[134],"maintaining":[135],"low":[136],"storage":[139],"requirements.":[140],"offers":[142],"ideal":[144],"solution":[145],"for":[146],"applications":[147],"prioritize":[149],"efficiency":[151],"without":[152],"compromising":[153],"performance.":[154]},"counts_by_year":[],"updated_date":"2025-11-15T23:13:30.683059","created_date":"2025-11-14T00:00:00"}