{"id":"https://openalex.org/W4402403041","doi":"https://doi.org/10.1109/mapr63514.2024.10660940","title":"ICViT: Integrated Framework for Complexity Reduction in Vision Transformer","display_name":"ICViT: Integrated Framework for Complexity Reduction in Vision Transformer","publication_year":2024,"publication_date":"2024-08-15","ids":{"openalex":"https://openalex.org/W4402403041","doi":"https://doi.org/10.1109/mapr63514.2024.10660940"},"language":"en","primary_location":{"id":"doi:10.1109/mapr63514.2024.10660940","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mapr63514.2024.10660940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Multimedia Analysis and Pattern Recognition (MAPR)","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/A5048526869","display_name":"Tien Dang","orcid":"https://orcid.org/0000-0001-6894-2852"},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Tien Dang","raw_affiliation_strings":["University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I23582244"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065249287","display_name":"Khanh-Duy Nguyen","orcid":"https://orcid.org/0000-0003-4237-2737"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khanh-Duy Nguyen","raw_affiliation_strings":["University of Information Technology,Ho Chi Minh City,Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089393633","display_name":"Khang Nguyen","orcid":"https://orcid.org/0000-0001-5058-6597"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khang Nguyen","raw_affiliation_strings":["University of Information Technology,Ho Chi Minh City,Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048526869"],"corresponding_institution_ids":["https://openalex.org/I23582244"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1279341,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9858999848365784,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9821000099182129,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5712133646011353},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5547164082527161},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4163525700569153},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.16390913724899292},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14420023560523987},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11915645003318787},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.11272010207176208}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5712133646011353},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5547164082527161},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4163525700569153},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.16390913724899292},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14420023560523987},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11915645003318787},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.11272010207176208},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mapr63514.2024.10660940","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mapr63514.2024.10660940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Multimedia Analysis and Pattern Recognition (MAPR)","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":31,"referenced_works":["https://openalex.org/W2990138404","https://openalex.org/W3033529678","https://openalex.org/W3131500599","https://openalex.org/W3133696297","https://openalex.org/W3138516171","https://openalex.org/W3151130473","https://openalex.org/W3171206729","https://openalex.org/W3175515048","https://openalex.org/W4214634256","https://openalex.org/W4292779060","https://openalex.org/W4296565034","https://openalex.org/W4297775537","https://openalex.org/W4312671791","https://openalex.org/W4320036893","https://openalex.org/W4385245566","https://openalex.org/W4389666313","https://openalex.org/W4390874124","https://openalex.org/W4394625669","https://openalex.org/W6737664043","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6778883912","https://openalex.org/W6779163297","https://openalex.org/W6779709467","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6790690058","https://openalex.org/W6792695861","https://openalex.org/W6794345597","https://openalex.org/W6803916128","https://openalex.org/W6842658462"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"Vision":[3],"Transformer":[4],"has":[5],"emerged":[6],"as":[7,109],"a":[8,80,159],"new":[9],"trend":[10],"in":[11,144,192],"the":[12,21,37,60,68,100,131,140,169,180],"field":[13],"of":[14,62,65,90,103,182],"computer":[15],"vision,":[16],"attracting":[17],"considerable":[18],"attention":[19,38],"from":[20],"research":[22],"community.":[23],"However,":[24],"their":[25],"impressive":[26],"performance":[27,97],"went":[28],"along":[29],"with":[30],"high":[31],"computation":[32],"complexity,":[33],"attributed":[34],"to":[35,45,58,71,94,126,162,165],"both":[36],"mechanism":[39,70],"and":[40,48,98,117,130],"multi-layer":[41],"perceptrons":[42],"(MLPs),":[43],"leading":[44],"resource-intensive":[46],"training":[47],"inference":[49],"processes.":[50],"Numerous":[51],"prior":[52,128],"works":[53],"have":[54],"proposed":[55],"various":[56],"strategies":[57,93],"alleviate":[59],"complexity":[61,102],"ViT,":[63],"many":[64],"which":[66],"decomposing":[67],"self-attention":[69],"enhance":[72],"performance.":[73],"Building":[74],"upon":[75],"this":[76,183],"foundation,":[77],"we":[78],"propose":[79],"novel":[81],"architectural":[82],"framework":[83],"called":[84,172],"ICViT.":[85],"This":[86],"architecture":[87],"integrates":[88],"several":[89],"these":[91],"decomposition":[92],"simultaneously":[95],"improve":[96],"reduce":[99],"computational":[101],"ViT.":[104],"By":[105],"leveraging":[106],"techniques":[107],"such":[108],"Hydra":[110],"Attention,":[111,114,116,119],"Linear":[112],"Angular":[113],"SimA":[115],"Class":[118],"our":[120,137,163],"approach":[121],"demonstrates":[122],"notable":[123],"advancements":[124,191],"compared":[125],"previous":[127],"methodologies":[129],"foundational":[132],"ViT":[133,142],"framework.":[134],"For":[135],"instance,":[136],"ICViT":[138,164],"surpasses":[139],"original":[141],"9.7%":[143],"accuracy":[145],"on":[146,149],"Cifar-10,":[147],"8.57%":[148],"Cifar-100,":[150],"while":[151],"utilizes":[152],"24.4%":[153],"fewer":[154],"parameters.":[155],"We":[156],"also":[157],"integrate":[158],"special":[160],"technique":[161],"help":[166],"it":[167],"learn":[168],"local":[170],"communication":[171],"Local":[173],"Patch":[174],"Interation":[175],"(LPI).":[176],"Our":[177],"findings":[178],"underscore":[179],"efficacy":[181],"multifaceted":[184],"integration,":[185],"offering":[186],"promising":[187],"avenues":[188],"for":[189],"future":[190],"transformer-based":[193],"architecture.":[194]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
