{"id":"https://openalex.org/W4413144526","doi":"https://doi.org/10.1109/cvpr52734.2025.00680","title":"Autoregressive Sequential Pretraining for Visual Tracking","display_name":"Autoregressive Sequential Pretraining for Visual Tracking","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413144526","doi":"https://doi.org/10.1109/cvpr52734.2025.00680"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00680","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5107950644","display_name":"Shiyi Liang","orcid":"https://orcid.org/0009-0006-1840-2106"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyi Liang","raw_affiliation_strings":["Xi’an Jiaotong University,School of Software Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Software Engineering","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101233277","display_name":"Yifan Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Bai","raw_affiliation_strings":["Xi’an Jiaotong University,School of Software Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Software Engineering","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100687952","display_name":"Yihong Gong","orcid":"https://orcid.org/0000-0002-1793-5836"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihong Gong","raw_affiliation_strings":["Xi’an Jiaotong University,School of Software Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Software Engineering","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107955483","display_name":"Xing Wei","orcid":"https://orcid.org/0000-0003-0998-4862"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Wei","raw_affiliation_strings":["Xi’an Jiaotong University,School of Software Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Software Engineering","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":3.5291,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.93290946,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7254","last_page":"7264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9936000108718872,"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":0.9936000108718872,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9785000085830688,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9599999785423279,"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":0.703493595123291},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.6478358507156372},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5552560091018677},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.4980659484863281},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4655849039554596},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.13050144910812378},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11408087611198425}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.703493595123291},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6478358507156372},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5552560091018677},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.4980659484863281},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4655849039554596},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.13050144910812378},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11408087611198425}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00680","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4300000071525574}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,37,67,110,166],"visual":[3],"object":[4,14,63],"tracking":[5,135],"have":[6],"shifted":[7],"towards":[8],"a":[9,73,89,111,115],"sequential":[10],"generation":[11],"paradigm,":[12],"where":[13],"deformation":[15],"and":[16,65],"motion":[17,66],"exhibit":[18],"strong":[19],"temporal":[20,168],"dependencies.":[21],"Despite":[22],"the":[23,35,38,43,60,79,97,123,145,161],"importance":[24],"of":[25,45,62,163],"these":[26],"dependencies,":[27],"widely":[28],"adopted":[29],"image-level":[30],"pretrained":[31,124],"backbones":[32],"barely":[33],"capture":[34],"dynamics":[36],"consecutive":[39],"video,":[40],"which":[41,130],"is":[42,100,131],"essence":[44],"tracking.":[46,173],"Thus,":[47],"we":[48,117,121],"propose":[49],"AutoRegressive":[50],"Sequential":[51],"Pretraining":[52],"(ARP),":[53],"an":[54],"unsupervised":[55],"spatio-temporal":[56],"learner,":[57],"via":[58],"generating":[59,107],"evolution":[61],"appearance":[64],"video":[68,172],"sequences.":[69],"Our":[70],"method":[71],"leverages":[72],"diffusion":[74],"model":[75],"to":[76,93,102,148],"autoregressively":[77],"generate":[78],"future":[80],"frame":[81],"appearance,":[82],"conditioned":[83],"on":[84,152],"historical":[85],"embeddings":[86],"extracted":[87],"by":[88,106],"general":[90],"encoder.":[91],"Furthermore,":[92],"ensure":[94],"trajectory":[95,104],"coherence,":[96],"same":[98],"encoder":[99],"employed":[101],"learn":[103],"consistency":[105],"coordinate":[108],"sequences":[109],"reverse":[112],"autoregressive":[113],"fashion,":[114],"process":[116],"term":[118],"backtracking.":[119],"Further,":[120],"integrate":[122],"ARP":[125],"into":[126],"AR-TrackV2,":[127],"creating":[128],"ARPTrack,":[129],"further":[132],"fine-tuned":[133],"for":[134,170],"tasks.":[136],"ARPTrack":[137],"achieves":[138],"state-of-the-art":[139],"performance":[140],"across":[141],"multiple":[142],"benchmarks,":[143],"becoming":[144],"first":[146],"tracker":[147],"surpass":[149],"80%":[150],"AO":[151],"GOT-10k,":[153],"while":[154],"maintaining":[155],"high":[156],"efficiency.":[157],"These":[158],"results":[159],"demonstrate":[160],"effectiveness":[162],"our":[164],"approach":[165],"capturing":[167],"dependencies":[169],"continuous":[171],"The":[174],"code":[175],"will":[176],"be":[177],"released":[178],"soon.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}