{"id":"https://openalex.org/W4410242491","doi":"https://doi.org/10.1007/s11263-025-02439-x","title":"Autoregressive Temporal Modeling for Advanced Tracking-by-Diffusion","display_name":"Autoregressive Temporal Modeling for Advanced Tracking-by-Diffusion","publication_year":2025,"publication_date":"2025-05-09","ids":{"openalex":"https://openalex.org/W4410242491","doi":"https://doi.org/10.1007/s11263-025-02439-x"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-025-02439-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02439-x","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/s11263-025-02439-x","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002689322","display_name":"Pha Nguyen","orcid":"https://orcid.org/0000-0003-1517-1382"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pha Nguyen","raw_affiliation_strings":["Department of EECS, University of Arkansas, Fayetteville, AR, USA"],"raw_orcid":"https://orcid.org/0000-0003-1517-1382","affiliations":[{"raw_affiliation_string":"Department of EECS, University of Arkansas, Fayetteville, AR, USA","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075264465","display_name":"Rishi Madhok","orcid":null},"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":"Rishi Madhok","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023298542","display_name":"Bhiksha Raj","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhiksha Raj","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056226189","display_name":"Khoa Luu","orcid":"https://orcid.org/0000-0003-2104-0901"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Khoa Luu","raw_affiliation_strings":["Department of EECS, University of Arkansas, Fayetteville, AR, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of EECS, University of Arkansas, Fayetteville, AR, USA","institution_ids":["https://openalex.org/I78715868"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5002689322","https://openalex.org/A5056226189"],"corresponding_institution_ids":["https://openalex.org/I78715868"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":{"value":2890,"currency":"EUR","value_usd":3690},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07330102,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"133","issue":"8","first_page":"5505","last_page":"5526"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9993000030517578,"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":0.9993000030517578,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9944999814033508,"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/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.9944000244140625,"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/autoregressive-model","display_name":"Autoregressive model","score":0.7676832675933838},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5909332036972046},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5389874577522278},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5144729614257812},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.491792231798172},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.47018516063690186},{"id":"https://openalex.org/keywords/star-model","display_name":"STAR model","score":0.4102151095867157},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.3159031271934509},{"id":"https://openalex.org/keywords/autoregressive-integrated-moving-average","display_name":"Autoregressive integrated moving average","score":0.2533301115036011},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24096572399139404},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.2329196035861969},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22299280762672424}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7676832675933838},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5909332036972046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5389874577522278},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5144729614257812},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.491792231798172},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.47018516063690186},{"id":"https://openalex.org/C194657046","wikidata":"https://www.wikidata.org/wiki/Q7394685","display_name":"STAR model","level":4,"score":0.4102151095867157},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.3159031271934509},{"id":"https://openalex.org/C24338571","wikidata":"https://www.wikidata.org/wiki/Q2566298","display_name":"Autoregressive integrated moving average","level":3,"score":0.2533301115036011},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24096572399139404},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2329196035861969},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22299280762672424},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11263-025-02439-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02439-x","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11263-025-02439-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02439-x","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":137,"referenced_works":["https://openalex.org/W146900863","https://openalex.org/W1901129140","https://openalex.org/W1991111872","https://openalex.org/W2016135469","https://openalex.org/W2020209171","https://openalex.org/W2047286693","https://openalex.org/W2098669323","https://openalex.org/W2111644456","https://openalex.org/W2124541566","https://openalex.org/W2124781496","https://openalex.org/W2129069237","https://openalex.org/W2134529534","https://openalex.org/W2146183743","https://openalex.org/W2150066425","https://openalex.org/W2170316986","https://openalex.org/W2171243491","https://openalex.org/W2237765446","https://openalex.org/W2252355370","https://openalex.org/W2424778531","https://openalex.org/W2470139095","https://openalex.org/W2511791013","https://openalex.org/W2519586580","https://openalex.org/W2532516272","https://openalex.org/W2534527426","https://openalex.org/W2603203130","https://openalex.org/W2739491435","https://openalex.org/W2799058067","https://openalex.org/W2889935068","https://openalex.org/W2897582990","https://openalex.org/W2900871370","https://openalex.org/W2920942303","https://openalex.org/W2950703532","https://openalex.org/W2953920664","https://openalex.org/W2962855257","https://openalex.org/W2962923976","https://openalex.org/W2963001155","https://openalex.org/W2963227409","https://openalex.org/W2963524571","https://openalex.org/W2964015640","https://openalex.org/W2964084369","https://openalex.org/W2964347345","https://openalex.org/W2981393651","https://openalex.org/W2982723417","https://openalex.org/W2986732333","https://openalex.org/W2990138404","https://openalex.org/W2997896013","https://openalex.org/W3020589396","https://openalex.org/W3034240185","https://openalex.org/W3035060563","https://openalex.org/W3035308063","https://openalex.org/W3035442500","https://openalex.org/W3035672751","https://openalex.org/W3084173793","https://openalex.org/W3086436251","https://openalex.org/W3090155371","https://openalex.org/W3095753995","https://openalex.org/W3098744844","https://openalex.org/W3099887740","https://openalex.org/W3104218139","https://openalex.org/W3104778224","https://openalex.org/W3106542916","https://openalex.org/W3106763294","https://openalex.org/W3106920598","https://openalex.org/W3108418701","https://openalex.org/W3108519869","https://openalex.org/W3109908659","https://openalex.org/W3110159886","https://openalex.org/W3110257065","https://openalex.org/W3119686997","https://openalex.org/W3131332223","https://openalex.org/W3159619744","https://openalex.org/W3165926952","https://openalex.org/W3167949052","https://openalex.org/W3170294192","https://openalex.org/W3173664046","https://openalex.org/W3175782503","https://openalex.org/W3181069167","https://openalex.org/W3200878848","https://openalex.org/W3201555865","https://openalex.org/W3203518786","https://openalex.org/W3207452968","https://openalex.org/W3211099767","https://openalex.org/W3217030260","https://openalex.org/W3217365746","https://openalex.org/W4211192810","https://openalex.org/W4214516362","https://openalex.org/W4226088892","https://openalex.org/W4281661987","https://openalex.org/W4283457321","https://openalex.org/W4286904999","https://openalex.org/W4288054401","https://openalex.org/W4292787292","https://openalex.org/W4298185919","https://openalex.org/W4307076412","https://openalex.org/W4312326540","https://openalex.org/W4312339971","https://openalex.org/W4312473433","https://openalex.org/W4312562660","https://openalex.org/W4312567319","https://openalex.org/W4312762601","https://openalex.org/W4312933868","https://openalex.org/W4313117614","https://openalex.org/W4321766229","https://openalex.org/W4378170107","https://openalex.org/W4378474398","https://openalex.org/W4378498790","https://openalex.org/W4378509482","https://openalex.org/W4385575022","https://openalex.org/W4386076180","https://openalex.org/W4386076204","https://openalex.org/W4386076331","https://openalex.org/W4386083103","https://openalex.org/W4390871749","https://openalex.org/W4390871782","https://openalex.org/W4390872615","https://openalex.org/W4390873135","https://openalex.org/W4390873752","https://openalex.org/W4390874241","https://openalex.org/W4390963175","https://openalex.org/W4393147944","https://openalex.org/W4393149283","https://openalex.org/W4393346468","https://openalex.org/W4402753781","https://openalex.org/W4403575764","https://openalex.org/W4403906568","https://openalex.org/W6608497737","https://openalex.org/W6640963894","https://openalex.org/W6714644935","https://openalex.org/W6739901393","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6795288823","https://openalex.org/W6796042156","https://openalex.org/W6810793953","https://openalex.org/W6846523392","https://openalex.org/W6852835101","https://openalex.org/W6853660567"],"related_works":["https://openalex.org/W2439807930","https://openalex.org/W2009692134","https://openalex.org/W1972271943","https://openalex.org/W2019155478","https://openalex.org/W2024529895","https://openalex.org/W2168175994","https://openalex.org/W1902630399","https://openalex.org/W2120434453","https://openalex.org/W3120578569","https://openalex.org/W2349019353"],"abstract_inverted_index":{"Object":[0],"tracking":[1,69,112,136,208],"is":[2],"a":[3,64,101,114,130,139,182],"widely":[4],"studied":[5],"computer":[6,210],"vision":[7],"task":[8],"with":[9],"video":[10,127,151,161],"and":[11,90,123,146,167,202,209],"instance":[12],"analysis":[13],"applications.":[14],"While":[15],"paradigms":[16,137],"such":[17],"as":[18,113],"tracking-by-regression":[19],",":[20,22,63],"-detection":[21],"-attention":[23],"have":[24],"advanced":[25],"the":[26,37,50,55,77],"field,":[27],"generative":[28,38,74],"modeling":[29,188],"offers":[30],"new":[31,183],"potential.":[32],"Although":[33],"some":[34],"studies":[35],"explore":[36],"process":[39],"in":[40,49,70,126,159,189,206],"instance-based":[41,150],"understanding":[42,162,190],"tasks,":[43],"they":[44],"rely":[45],"on":[46,171,185],"prediction":[47],"refinement":[48],"coordinate":[51],"space":[52],"rather":[53],"than":[54],"visual":[56,73,186,192,207],"domain.":[57],"Instead,":[58],"this":[59],"paper":[60,178],"presents":[61],"Tracking-by-Diffusion":[62],"novel":[65],"paradigm":[66,83],"for":[67],"object":[68],"video,":[71],"leveraging":[72],"models":[75,109,166],"via":[76],"perspective":[78,184],"of":[79],"autoregressive":[80,187],"models.":[81],"This":[82,177],"demonstrates":[84,203],"broad":[85],"applicability":[86],"across":[87,174],"point,":[88],"box,":[89],"mask":[91],"modalities":[92],"while":[93],"uniquely":[94,120],"enabling":[95,148],"textual":[96],"guidance.":[97],"We":[98],"present":[99],"DIFTracker,":[100],"framework":[102],"that":[103,133],"utilizes":[104],"iterative":[105],"latent":[106],"variable":[107],"diffusion":[108],"to":[110,156],"redefine":[111],"next-frame":[115],"reconstruction":[116],"task.":[117],"Our":[118],"approach":[119],"combines":[121],"spatial":[122],"temporal":[124],"dependencies":[125],"data,":[128,193],"offering":[129],"unified":[131],"solution":[132],"encompasses":[134],"existing":[135],"within":[138],"single":[140],"Inversion-Reconstruction":[141],"process.":[142],"DIFTracker":[143],"operates":[144],"online":[145],"auto-regressively,":[147],"flexible":[149],"understanding.":[152],"It":[153],"allows":[154],"us":[155],"overcome":[157],"difficulties":[158],"variable-length":[160],"encountered":[163],"by":[164],"video-inflated":[165],"perform":[168],"superior":[169],"performance":[170],"seven":[172],"benchmarks":[173],"five":[175],"modalities.":[176],"not":[179],"only":[180],"introduces":[181],"sequential":[191],"specifically":[194],"videos,":[195],"but":[196],"also":[197],"provides":[198],"robust":[199],"theoretical":[200],"validations":[201],"broader":[204],"applications":[205],"vision.":[211]},"counts_by_year":[],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}