{"id":"https://openalex.org/W4406417304","doi":"https://doi.org/10.1109/tpami.2025.3529926","title":"OmniTracker: Unifying Visual Object Tracking by Tracking-With-Detection","display_name":"OmniTracker: Unifying Visual Object Tracking by Tracking-With-Detection","publication_year":2025,"publication_date":"2025-01-15","ids":{"openalex":"https://openalex.org/W4406417304","doi":"https://doi.org/10.1109/tpami.2025.3529926","pmid":"https://pubmed.ncbi.nlm.nih.gov/40030997"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3529926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3529926","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/A5101517372","display_name":"Junke Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junke Wang","raw_affiliation_strings":["Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China","School of Computer Science, Fudan University, China"],"raw_orcid":"https://orcid.org/0000-0001-8129-7333","affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026167547","display_name":"Zuxuan Wu","orcid":"https://orcid.org/0000-0002-8689-5807"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuxuan Wu","raw_affiliation_strings":["Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China","School of Computer Science, Fudan University, China"],"raw_orcid":"https://orcid.org/0000-0002-8689-5807","affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dongdong Chen","orcid":"https://orcid.org/0000-0002-4642-4373"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongdong Chen","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","Microsoft Research, Redmond, USA"],"raw_orcid":"https://orcid.org/0000-0002-4642-4373","affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100539988","display_name":"Chong Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chong Luo","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft Research, Asia, China"],"raw_orcid":"https://orcid.org/0000-0003-0939-474X","affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research, Asia, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057293861","display_name":"Xiyang Dai","orcid":"https://orcid.org/0000-0003-1761-8715"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiyang Dai","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","Microsoft Research, Redmond, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lu Yuan","orcid":"https://orcid.org/0000-0001-7879-0389"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lu Yuan","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","Microsoft Research, Redmond, USA"],"raw_orcid":"https://orcid.org/0000-0001-7879-0389","affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047962986","display_name":"Yu\u2013Gang Jiang","orcid":"https://orcid.org/0000-0002-1907-8567"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China","School of Computer Science, Fudan University, China"],"raw_orcid":"https://orcid.org/0000-0002-1907-8567","affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.4829,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.98715132,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"47","issue":"4","first_page":"3159","last_page":"3174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9984999895095825,"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":0.9984999895095825,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9865999817848206,"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9769999980926514,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.8239972591400146},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.8055610656738281},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6955220103263855},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6310402154922485},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5725668668746948},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5465070009231567},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.4672386944293976},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.42003333568573},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35880228877067566}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8239972591400146},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.8055610656738281},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6955220103263855},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6310402154922485},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5725668668746948},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5465070009231567},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.4672386944293976},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.42003333568573},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35880228877067566},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3529926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3529926","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:40030997","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40030997","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":[],"awards":[{"id":"https://openalex.org/G472569701","display_name":null,"funder_award_id":"62032006","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":144,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2055022211","https://openalex.org/W2115739848","https://openalex.org/W2126302311","https://openalex.org/W2150298366","https://openalex.org/W2171243491","https://openalex.org/W2222512263","https://openalex.org/W2225887246","https://openalex.org/W2470394683","https://openalex.org/W2565639579","https://openalex.org/W2594507094","https://openalex.org/W2794744029","https://openalex.org/W2799058067","https://openalex.org/W2799239273","https://openalex.org/W2889658408","https://openalex.org/W2891033863","https://openalex.org/W2898200825","https://openalex.org/W2920942303","https://openalex.org/W2953920664","https://openalex.org/W2955747520","https://openalex.org/W2962766617","https://openalex.org/W2962914239","https://openalex.org/W2963150697","https://openalex.org/W2963227409","https://openalex.org/W2963351448","https://openalex.org/W2963534981","https://openalex.org/W2964084369","https://openalex.org/W2964343881","https://openalex.org/W2966759264","https://openalex.org/W2967622921","https://openalex.org/W2982723417","https://openalex.org/W2983943451","https://openalex.org/W2990205821","https://openalex.org/W3001584168","https://openalex.org/W3034297219","https://openalex.org/W3034499084","https://openalex.org/W3034798428","https://openalex.org/W3035060563","https://openalex.org/W3035211844","https://openalex.org/W3035453691","https://openalex.org/W3035571898","https://openalex.org/W3035672751","https://openalex.org/W3039368862","https://openalex.org/W3084173793","https://openalex.org/W3094000868","https://openalex.org/W3094664776","https://openalex.org/W3096609285","https://openalex.org/W3106546328","https://openalex.org/W3106773277","https://openalex.org/W3108235634","https://openalex.org/W3108519869","https://openalex.org/W3109372619","https://openalex.org/W3110109236","https://openalex.org/W3119686997","https://openalex.org/W3138516171","https://openalex.org/W3139267983","https://openalex.org/W3149936330","https://openalex.org/W3156279252","https://openalex.org/W3164698655","https://openalex.org/W3167308647","https://openalex.org/W3167536469","https://openalex.org/W3167949052","https://openalex.org/W3169933013","https://openalex.org/W3170294192","https://openalex.org/W3171516518","https://openalex.org/W3176403636","https://openalex.org/W3183673520","https://openalex.org/W3199093552","https://openalex.org/W3200949949","https://openalex.org/W3202509201","https://openalex.org/W3204540098","https://openalex.org/W3204554907","https://openalex.org/W3214586131","https://openalex.org/W4206519819","https://openalex.org/W4213179364","https://openalex.org/W4214627427","https://openalex.org/W4214759957","https://openalex.org/W4226407477","https://openalex.org/W4286904999","https://openalex.org/W4310467366","https://openalex.org/W4312294051","https://openalex.org/W4312312588","https://openalex.org/W4312323989","https://openalex.org/W4312396403","https://openalex.org/W4312443924","https://openalex.org/W4312473433","https://openalex.org/W4312516520","https://openalex.org/W4312532041","https://openalex.org/W4312567319","https://openalex.org/W4312751983","https://openalex.org/W4312805142","https://openalex.org/W4313007081","https://openalex.org/W4319300181","https://openalex.org/W4319866011","https://openalex.org/W4382467859","https://openalex.org/W4386065544","https://openalex.org/W4386065815","https://openalex.org/W4386066071","https://openalex.org/W4386066081","https://openalex.org/W4386066394","https://openalex.org/W4386066459","https://openalex.org/W4386071948","https://openalex.org/W4386076040","https://openalex.org/W4386076204","https://openalex.org/W4386083103","https://openalex.org/W4386590375","https://openalex.org/W4390872626","https://openalex.org/W4390874575","https://openalex.org/W4390874670","https://openalex.org/W4393147881","https://openalex.org/W4393147957","https://openalex.org/W4393154076","https://openalex.org/W4402699341","https://openalex.org/W4402702990","https://openalex.org/W4402753923","https://openalex.org/W4402754169","https://openalex.org/W4402776403","https://openalex.org/W4402780073","https://openalex.org/W4402951596","https://openalex.org/W4405974723","https://openalex.org/W6696672603","https://openalex.org/W6757817989","https://openalex.org/W6759534164","https://openalex.org/W6784094891","https://openalex.org/W6788023325","https://openalex.org/W6793267612","https://openalex.org/W6796494355","https://openalex.org/W6796524941","https://openalex.org/W6797162190","https://openalex.org/W6798046461","https://openalex.org/W6798838024","https://openalex.org/W6805147364","https://openalex.org/W6809665764","https://openalex.org/W6811230874","https://openalex.org/W6839371072","https://openalex.org/W6839744764","https://openalex.org/W6843861238","https://openalex.org/W6851592950","https://openalex.org/W6853013044","https://openalex.org/W6856537367","https://openalex.org/W6870245713","https://openalex.org/W6870839691","https://openalex.org/W6873813557","https://openalex.org/W6874642958"],"related_works":["https://openalex.org/W4285271403","https://openalex.org/W2542007731","https://openalex.org/W4292830139","https://openalex.org/W2968379562","https://openalex.org/W4319309705","https://openalex.org/W2091015105","https://openalex.org/W4388689193","https://openalex.org/W2110899030","https://openalex.org/W29633852","https://openalex.org/W2985362983"],"abstract_inverted_index":{"Visual":[0],"Object":[1],"Tracking":[2],"(VOT)":[3],"aims":[4],"to":[5,71,139],"estimate":[6],"the":[7,29,41,45,92,95,124,142,157],"positions":[8],"of":[9,32,78,94,177],"target":[10,33],"objects":[11,34],"in":[12,40,81,99,165],"a":[13,104,129,131,146],"video":[14],"sequence,":[15],"which":[16],"is":[17,136],"an":[18],"important":[19],"vision":[20],"task":[21],"with":[22,119,127,145],"various":[23],"real-world":[24],"applications.":[25],"Depending":[26],"on":[27,172],"whether":[28],"initial":[30],"states":[31],"are":[35],"specified":[36],"by":[37],"provided":[38],"annotations":[39],"first":[42],"frame":[43],"or":[44,195],"categories,":[46],"VOT":[47],"could":[48],"be":[49],"classified":[50],"as":[51],"instance":[52],"tracking":[53,60,109,118,133,143,175,179,204],"(e.g.,":[54,61],"SOT":[55],"and":[56,58,64,85,115,153,162,187,189,202],"VOS)":[57],"category":[59],"MOT,":[62],"MOTS,":[63],"VIS)":[65],"tasks.":[66],"Different":[67],"definitions":[68],"have":[69],"led":[70],"divergent":[72],"solutions":[73],"for":[74,113,123,159],"these":[75],"two":[76],"types":[77],"tasks,":[79,180],"resulting":[80],"redundant":[82],"training":[83],"expenses":[84],"parameter":[86],"overhead.":[87],"In":[88],"this":[89],"paper,":[90],"combing":[91],"advantages":[93],"best":[96],"practices":[97],"developed":[98],"both":[100,200],"communities,":[101],"we":[102],"propose":[103],"novel":[105],"tracking-with-detection":[106],"paradigm,":[107],"where":[108],"supplements":[110],"appearance":[111],"priors":[112],"detection":[114,116],"provides":[117],"candidate":[120],"bounding":[121],"boxes":[122],"association.":[125],"Equipped":[126],"such":[128],"design,":[130],"unified":[132,203],"model,":[134],"OmniTracker,":[135],"further":[137],"presented":[138],"resolve":[140],"all":[141],"tasks":[144],"fully":[147],"shared":[148],"network":[149],"architecture,":[150],"model":[151,166],"weights,":[152],"inference":[154],"pipeline,":[155],"eliminating":[156],"need":[158],"task-specific":[160,201],"architectures":[161],"reducing":[163],"redundancy":[164],"parameters.":[167],"We":[168],"conduct":[169],"extensive":[170],"experimentation":[171],"seven":[173],"prominent":[174],"datasets":[176],"different":[178],"including":[181],"LaSOT,":[182],"TrackingNet,":[183],"DAVIS16-17,":[184],"MOT17,":[185],"MOTS20,":[186],"YTVIS19,":[188],"demonstrate":[190],"that":[191],"OmniTracker":[192],"achieves":[193],"on-par":[194],"even":[196],"better":[197],"results":[198],"than":[199],"models.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":8}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}