{"id":"https://openalex.org/W4362654293","doi":"https://doi.org/10.1109/tmm.2023.3264851","title":"CMAT: Integrating Convolution Mixer and Self-Attention for Visual Tracking","display_name":"CMAT: Integrating Convolution Mixer and Self-Attention for Visual Tracking","publication_year":2023,"publication_date":"2023-04-05","ids":{"openalex":"https://openalex.org/W4362654293","doi":"https://doi.org/10.1109/tmm.2023.3264851"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3264851","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3264851","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5100384783","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0002-6750-5105"},"institutions":[{"id":"https://openalex.org/I141103825","display_name":"Nanchang Institute of Technology","ror":"https://ror.org/00avfj807","country_code":"CN","type":"education","lineage":["https://openalex.org/I141103825"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jun Wang","raw_affiliation_strings":["School of Information Engineering, Nanchang Institute of Technology, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Nanchang Institute of Technology, Nanchang, China","institution_ids":["https://openalex.org/I141103825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057351252","display_name":"Peng Yin","orcid":"https://orcid.org/0000-0003-4968-1436"},"institutions":[{"id":"https://openalex.org/I141103825","display_name":"Nanchang Institute of Technology","ror":"https://ror.org/00avfj807","country_code":"CN","type":"education","lineage":["https://openalex.org/I141103825"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Yin","raw_affiliation_strings":["School of Information Engineering, Nanchang Institute of Technology, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Nanchang Institute of Technology, Nanchang, China","institution_ids":["https://openalex.org/I141103825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089028066","display_name":"Yuanyun Wang","orcid":"https://orcid.org/0000-0002-6446-5873"},"institutions":[{"id":"https://openalex.org/I141103825","display_name":"Nanchang Institute of Technology","ror":"https://ror.org/00avfj807","country_code":"CN","type":"education","lineage":["https://openalex.org/I141103825"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyun Wang","raw_affiliation_strings":["School of Information Engineering, Nanchang Institute of Technology, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Nanchang Institute of Technology, Nanchang, China","institution_ids":["https://openalex.org/I141103825"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053387996","display_name":"Wenhui Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I141103825","display_name":"Nanchang Institute of Technology","ror":"https://ror.org/00avfj807","country_code":"CN","type":"education","lineage":["https://openalex.org/I141103825"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhui Yang","raw_affiliation_strings":["School of Information Engineering, Nanchang Institute of Technology, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Nanchang Institute of Technology, Nanchang, China","institution_ids":["https://openalex.org/I141103825"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100384783"],"corresponding_institution_ids":["https://openalex.org/I141103825"],"apc_list":null,"apc_paid":null,"fwci":3.6297,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.94535255,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"26","issue":null,"first_page":"326","last_page":"338"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9995999932289124,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9995999932289124,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9805999994277954,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T11019","display_name":"Image Enhancement Techniques","score":0.965499997138977,"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/computer-science","display_name":"Computer science","score":0.8251136541366577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6096335649490356},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5891680121421814},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5097634196281433},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4956742525100708},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.47322264313697815},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4712788462638855},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.4454454481601715},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33026885986328125},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2845008671283722}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8251136541366577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6096335649490356},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5891680121421814},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5097634196281433},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4956742525100708},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.47322264313697815},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4712788462638855},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.4454454481601715},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33026885986328125},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2845008671283722},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3264851","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3264851","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[{"id":"https://openalex.org/G4117401117","display_name":null,"funder_award_id":"61861032","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1915785815","https://openalex.org/W2089961441","https://openalex.org/W2194775991","https://openalex.org/W2470394683","https://openalex.org/W2518876086","https://openalex.org/W2557641257","https://openalex.org/W2604701225","https://openalex.org/W2605173812","https://openalex.org/W2794744029","https://openalex.org/W2797812763","https://openalex.org/W2799058067","https://openalex.org/W2884585870","https://openalex.org/W2886910176","https://openalex.org/W2891033863","https://openalex.org/W2898200825","https://openalex.org/W2963534981","https://openalex.org/W2966759264","https://openalex.org/W2983446232","https://openalex.org/W2997896013","https://openalex.org/W2998434318","https://openalex.org/W3001584168","https://openalex.org/W3009294634","https://openalex.org/W3034297219","https://openalex.org/W3034617042","https://openalex.org/W3035211844","https://openalex.org/W3035511673","https://openalex.org/W3035571898","https://openalex.org/W3035672751","https://openalex.org/W3102817716","https://openalex.org/W3108235634","https://openalex.org/W3108519869","https://openalex.org/W3159231306","https://openalex.org/W3160694286","https://openalex.org/W3162457465","https://openalex.org/W3167536469","https://openalex.org/W3168663926","https://openalex.org/W3172509117","https://openalex.org/W3174225630","https://openalex.org/W3203510176","https://openalex.org/W3204540098","https://openalex.org/W3208338480","https://openalex.org/W3214586131","https://openalex.org/W4214493665","https://openalex.org/W4214710672","https://openalex.org/W4214759957","https://openalex.org/W4221166201","https://openalex.org/W4226224676","https://openalex.org/W4285603016","https://openalex.org/W4285661751","https://openalex.org/W4312255167","https://openalex.org/W4312516520","https://openalex.org/W4312519354","https://openalex.org/W4312651496","https://openalex.org/W4312735552","https://openalex.org/W4313134759","https://openalex.org/W4319300771","https://openalex.org/W4320717620","https://openalex.org/W6739901393","https://openalex.org/W6759215614","https://openalex.org/W6784333009","https://openalex.org/W6795704626","https://openalex.org/W6805147364","https://openalex.org/W6809923571","https://openalex.org/W6811014117"],"related_works":["https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W2922073769","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W4378510483","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W2964954556","https://openalex.org/W3019910406"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNNs)":[3],"and":[4,97,122,146,170,215,239],"Transformer":[5,39],"are":[6,173,209],"two":[7],"powerful":[8],"representation":[9],"learning":[10],"techniques":[11],"for":[12,77,89,211],"visual":[13,78],"tracking.":[14],"Although":[15],"CNNs":[16],"can":[17,47,59],"effectively":[18,48,106],"reduce":[19],"local":[20],"redundancy":[21,119],"via":[22],"small-neighborhood":[23],"convolution":[24],"operations,":[25],"their":[26],"limited":[27],"receptive":[28,127],"fields":[29],"make":[30],"it":[31],"difficult":[32],"to":[33,61,100,130,176,197],"capture":[34,49],"global":[35,133],"dependency.":[36,51],"Self-attention":[37],"in":[38,120,160],"uses":[40],"patches":[41,58],"as":[42],"the":[43,72,132,157,161,165,168,178,181,192,195,199,203],"input":[44],"representation,":[45],"which":[46,105],"long-range":[50],"However,":[52],"blind":[53],"similarity":[54],"comparisons":[55],"between":[56],"all":[57],"lead":[60],"high":[62],"redundancy.":[63],"Is":[64],"there":[65],"then":[66],"a":[67,85,102,140,186,234,240],"technique":[68],"that":[69],"combines":[70],"well":[71],"advantages":[73],"of":[74,113,136,156,180,194,202],"both":[75],"paradigms":[76],"tracking?":[79],"In":[80,164,230],"this":[81],"work,":[82],"we":[83,93,138],"design":[84],"novel":[86],"backbone":[87,182],"network":[88,183,204],"feature":[90,213],"extraction.":[91],"First,":[92],"choose":[94],"Depthwise":[95],"Convolution":[96,99,103,116,144],"Pointwise":[98],"build":[101],"Mixer,":[104],"separates":[107],"spatial":[108,121],"mixing":[109,112],"from":[110],"channel-wise":[111],"information.":[114],"The":[115,148,217],"Mixer":[117,145],"reduces":[118],"channel":[123,158],"features":[124,208],"while":[125,245],"increasing":[126],"field.":[128],"Then,":[129],"exploit":[131],"modeling":[134],"ability":[135,201],"self-attention,":[137],"construct":[139],"module":[141,149,196],"by":[142],"aggregating":[143],"self-attention.":[147],"shares":[150],"dominant":[151],"computational":[152],"complexity":[153],"(the":[154],"square":[155],"size)":[159],"first":[162],"stage.":[163],"second":[166],"stage,":[167],"shift":[169],"summation":[171],"operations":[172],"lightweight.":[174],"Finally,":[175],"alleviate":[177],"overfitting":[179],"during":[184],"training,":[185],"dropout":[187],"layer":[188],"is":[189],"added":[190],"at":[191,247],"end":[193],"improve":[198],"generalization":[200],"model.":[205],"Stronger":[206],"image":[207],"provided":[210],"subsequent":[212],"fusion":[214],"prediction.":[216],"proposed":[218],"tracker":[219],"(named":[220],"CMAT)":[221],"achieves":[222,233],"satisfying":[223],"tracking":[224],"performance":[225],"on":[226,237,243],"ten":[227],"challenging":[228],"datasets.":[229],"particular,":[231],"CMAT":[232],"64.1%":[235],"AUC":[236,242],"LaSOT":[238],"68.9%":[241],"UAV123":[244],"running":[246],"23":[248],"FPS.":[249]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}