{"id":"https://openalex.org/W4390577959","doi":"https://doi.org/10.1109/tpami.2024.3349519","title":"MixFormer: End-to-End Tracking With Iterative Mixed Attention","display_name":"MixFormer: End-to-End Tracking With Iterative Mixed Attention","publication_year":2024,"publication_date":"2024-01-04","ids":{"openalex":"https://openalex.org/W4390577959","doi":"https://doi.org/10.1109/tpami.2024.3349519","pmid":"https://pubmed.ncbi.nlm.nih.gov/38713562"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3349519","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3349519","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5003850662","display_name":"Yutao Cui","orcid":"https://orcid.org/0000-0003-4788-9751"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutao Cui","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4788-9751","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104636421","display_name":"Cheng Jiang","orcid":"https://orcid.org/0009-0003-2170-2538"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Jiang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0003-2170-2538","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101546753","display_name":"Gangshan Wu","orcid":"https://orcid.org/0000-0003-1391-1762"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gangshan Wu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-1391-1762","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100436505","display_name":"Limin Wang","orcid":"https://orcid.org/0000-0002-3674-7718"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Limin Wang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-3674-7718","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":26.9915,"has_fulltext":false,"cited_by_count":72,"citation_normalized_percentile":{"value":0.99820335,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"46","issue":"6","first_page":"4129","last_page":"4146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.4700999855995178,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.4700999855995178,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.4474000036716461,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.43630000948905945,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.919194757938385},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6215052008628845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5373344421386719},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.47308284044265747},{"id":"https://openalex.org/keywords/dead-end","display_name":"Dead end","score":0.4639456272125244},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.45930230617523193},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.4290223717689514},{"id":"https://openalex.org/keywords/radar-tracker","display_name":"Radar tracker","score":0.4134692847728729},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3214084208011627},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18811798095703125},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.16613513231277466},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.08414795994758606}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.919194757938385},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6215052008628845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5373344421386719},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47308284044265747},{"id":"https://openalex.org/C2986709869","wikidata":"https://www.wikidata.org/wiki/Q398589","display_name":"Dead end","level":3,"score":0.4639456272125244},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.45930230617523193},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.4290223717689514},{"id":"https://openalex.org/C32283439","wikidata":"https://www.wikidata.org/wiki/Q1407014","display_name":"Radar tracker","level":3,"score":0.4134692847728729},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3214084208011627},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18811798095703125},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.16613513231277466},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.08414795994758606},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3349519","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3349519","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:38713562","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38713562","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6100000143051147}],"awards":[{"id":"https://openalex.org/G4152983559","display_name":null,"funder_award_id":"2022ZD0160900","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G528746023","display_name":null,"funder_award_id":"61921006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6791897338","display_name":null,"funder_award_id":"62076119","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"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":91,"referenced_works":["https://openalex.org/W161114242","https://openalex.org/W1857884451","https://openalex.org/W1861492603","https://openalex.org/W1964846093","https://openalex.org/W2034803354","https://openalex.org/W2044986361","https://openalex.org/W2108598243","https://openalex.org/W2154889144","https://openalex.org/W2158592639","https://openalex.org/W2470394683","https://openalex.org/W2507009361","https://openalex.org/W2518876086","https://openalex.org/W2557641257","https://openalex.org/W2558899534","https://openalex.org/W2599547527","https://openalex.org/W2794744029","https://openalex.org/W2799058067","https://openalex.org/W2886910176","https://openalex.org/W2898200825","https://openalex.org/W2955747520","https://openalex.org/W2962766617","https://openalex.org/W2962824803","https://openalex.org/W2963074722","https://openalex.org/W2963227409","https://openalex.org/W2963534981","https://openalex.org/W2964069521","https://openalex.org/W2964111344","https://openalex.org/W2964242925","https://openalex.org/W2966759264","https://openalex.org/W2990763144","https://openalex.org/W2998434318","https://openalex.org/W3001584168","https://openalex.org/W3016979720","https://openalex.org/W3034297219","https://openalex.org/W3034617042","https://openalex.org/W3035211844","https://openalex.org/W3035453691","https://openalex.org/W3035460038","https://openalex.org/W3035511673","https://openalex.org/W3035524453","https://openalex.org/W3035571898","https://openalex.org/W3035672751","https://openalex.org/W3047017093","https://openalex.org/W3096609285","https://openalex.org/W3104158266","https://openalex.org/W3108235634","https://openalex.org/W3108519869","https://openalex.org/W3121523901","https://openalex.org/W3127178541","https://openalex.org/W3127756064","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3151599417","https://openalex.org/W3167536469","https://openalex.org/W3167762749","https://openalex.org/W3168663926","https://openalex.org/W3174225630","https://openalex.org/W3176187859","https://openalex.org/W3203857058","https://openalex.org/W3204540098","https://openalex.org/W3204554907","https://openalex.org/W3208338480","https://openalex.org/W3209993199","https://openalex.org/W3214586131","https://openalex.org/W4214493665","https://openalex.org/W4214506192","https://openalex.org/W4214703333","https://openalex.org/W4214759957","https://openalex.org/W4312255167","https://openalex.org/W4312323989","https://openalex.org/W4312446817","https://openalex.org/W4312453657","https://openalex.org/W4312472480","https://openalex.org/W4312516520","https://openalex.org/W4312532041","https://openalex.org/W4312651496","https://openalex.org/W4312751983","https://openalex.org/W4312804044","https://openalex.org/W4312805142","https://openalex.org/W4313156423","https://openalex.org/W4389666313","https://openalex.org/W6630840828","https://openalex.org/W6631190155","https://openalex.org/W6739901393","https://openalex.org/W6784333009","https://openalex.org/W6793935331","https://openalex.org/W6796761347","https://openalex.org/W6805147364","https://openalex.org/W6810265253","https://openalex.org/W6849641342","https://openalex.org/W6852835101"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W3016188207","https://openalex.org/W4293268064","https://openalex.org/W2593532750","https://openalex.org/W3207232378","https://openalex.org/W2218833963","https://openalex.org/W2642467014","https://openalex.org/W2964709658","https://openalex.org/W4240479622","https://openalex.org/W4246369259"],"abstract_inverted_index":{"Visual":[0],"object":[1],"tracking":[2,40,220],"often":[3],"employs":[4],"a":[5,38,62,110,123,128,139,214],"multi-stage":[6],"pipeline":[7,21],"of":[8,26,56,120,141,239],"feature":[9,27,69],"extraction,":[10],"target":[11,30,72,91,182],"information":[12,31,73],"integration,":[13,32],"and":[14,22,29,59,71,86,92,108,127,144,152,170,199,230,246],"bounding":[15],"box":[16],"estimation.":[17],"To":[18],"simplify":[19],"this":[20,34],"unify":[23],"the":[24,54,146,162,172],"process":[25],"extraction":[28,70],"in":[33,155,193],"paper,":[35],"we":[36,60,98,116,137,187],"present":[37],"compact":[39],"framework,":[41],"termed":[42],"as":[43],"MixFormer,":[44],"built":[45],"upon":[46],"transformers.":[47],"Our":[48,210],"core":[49],"design":[50,171],"is":[51],"to":[52,81,166,179,195,206],"utilize":[53],"flexibility":[55],"attention":[57,191],"operations,":[58],"propose":[61,200],"Mixed":[63],"Attention":[64],"Module":[65],"(MAM)":[66],"for":[67],"simultaneous":[68],"integration.":[74],"This":[75],"synchronous":[76],"modeling":[77],"scheme":[78,192],"allows":[79],"us":[80],"extract":[82],"target-specific":[83],"discriminative":[84],"features":[85],"perform":[87],"extensive":[88],"communication":[89],"between":[90,149],"search":[93],"area.":[94],"Based":[95],"on":[96,113,218,241,244,248],"MAM,":[97],"build":[99],"our":[100,156,167,234],"MixFormer":[101,121,157,168,211],"trackers":[102,169,212],"simply":[103],"by":[104],"stacking":[105],"multiple":[106,181],"MAMs":[107],"placing":[109],"localization":[111],"head":[112],"top.":[114],"Specifically,":[115],"instantiate":[117],"two":[118,135],"types":[119],"trackers,":[122,136],"hierarchical":[124],"tracker":[125,131],"MixCvT,":[126],"non-hierarchical":[129],"simple":[130],"MixViT.":[132],"For":[133],"these":[134],"investigate":[138],"series":[140],"pre-training":[142,151,154,165,176],"methods":[143],"uncover":[145],"different":[147],"behaviors":[148],"supervised":[150],"self-supervised":[153],"trackers.":[158],"We":[159],"also":[160],"extend":[161],"masked":[163],"autoencoder":[164],"new":[173,215],"competitive":[174],"TrackMAE":[175],"technique.":[177],"Finally,":[178],"handle":[180],"templates":[183],"during":[184],"online":[185],"tracking,":[186],"devise":[188],"an":[189,201],"asymmetric":[190],"MAM":[194],"reduce":[196],"computational":[197],"cost,":[198],"effective":[202],"score":[203],"prediction":[204],"module":[205],"select":[207],"high-quality":[208],"templates.":[209],"set":[213],"state-of-the-art":[216],"performance":[217],"seven":[219],"benchmarks,":[221],"including":[222],"LaSOT,":[223,242],"TrackingNet,":[224],"VOT2020,":[225],"GOT-10":[226],"k,":[227],"OTB100,":[228],"TOTB":[229],"UAV123.":[231],"In":[232],"particular,":[233],"MixViT-L":[235],"achieves":[236],"AUC":[237],"scores":[238],"73.3%":[240],"86.1%":[243],"TrackingNet":[245],"82.8%":[247],"TOTB.":[249]},"counts_by_year":[{"year":2026,"cited_by_count":17},{"year":2025,"cited_by_count":33},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T08:27:34.040176","created_date":"2025-10-10T00:00:00"}