{"id":"https://openalex.org/W4414577190","doi":"https://doi.org/10.1109/iccv51701.2025.01335","title":"Attention to Trajectory: Trajectory-Aware Open-Vocabulary Tracking","display_name":"Attention to Trajectory: Trajectory-Aware Open-Vocabulary Tracking","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414577190","doi":"https://doi.org/10.1109/iccv51701.2025.01335"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.08145","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100778543","display_name":"Yunhao Li","orcid":"https://orcid.org/0000-0002-7337-1748"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhao Li","raw_affiliation_strings":["Institute of Software Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Software Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210128818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031056278","display_name":"Yifan Jiao","orcid":"https://orcid.org/0000-0002-8923-6997"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Jiao","raw_affiliation_strings":["Institute of Software Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Software Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210128818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101525319","display_name":"Dan Meng","orcid":"https://orcid.org/0000-0003-1980-9283"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dan Meng","raw_affiliation_strings":["OPPO Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO Research Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047220188","display_name":"Heng Fan","orcid":"https://orcid.org/0000-0002-7033-3690"},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heng Fan","raw_affiliation_strings":["University of North Texas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Texas","institution_ids":["https://openalex.org/I123534392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100337161","display_name":"Libo Zhang","orcid":"https://orcid.org/0000-0001-8450-0958"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Libo Zhang","raw_affiliation_strings":["Institute of Software Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Software Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210128818"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14390","last_page":"14398"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9807999730110168,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9807999730110168,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9642000198364258,"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/trajectory","display_name":"Trajectory","score":0.7264000177383423},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5989999771118164},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5386000275611877},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4584999978542328},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42250001430511475},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.39079999923706055},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.3896999955177307},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.3874000012874603}],"concepts":[{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7264000177383423},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7171000242233276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6392999887466431},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5989999771118164},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.574999988079071},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5386000275611877},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4584999978542328},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42250001430511475},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.39079999923706055},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3874000012874603},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C154586513","wikidata":"https://www.wikidata.org/wiki/Q4420972","display_name":"Tracking system","level":3,"score":0.3098999857902527},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2948000133037567},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28060001134872437},{"id":"https://openalex.org/C2983325608","wikidata":"https://www.wikidata.org/wiki/Q17084606","display_name":"Data association","level":3,"score":0.2605000138282776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2590000033378601}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.08145","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.08145","pdf_url":"https://arxiv.org/pdf/2503.08145","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.08145","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.08145","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.08145","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.08145","pdf_url":"https://arxiv.org/pdf/2503.08145","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Open-Vocabulary":[0],"Multi-Object":[1],"Tracking":[2],"(OV-MOT)":[3],"aims":[4],"to":[5,8,14,65,83,134],"enable":[6],"approaches":[7],"track":[9],"objects":[10],"without":[11],"being":[12],"limited":[13],"a":[15,95,117,165],"predefined":[16],"set":[17],"of":[18,57],"categories.":[19],"Current":[20],"OV-MOT":[21],"methods":[22],"typically":[23],"rely":[24],"primarily":[25],"on":[26,151],"instance-level":[27],"detection":[28],"and":[29,38,51,59,88,109,128,141],"association,":[30],"often":[31],"overlooking":[32],"trajectory":[33,45,81,119,137,162],"information":[34,46,82,138,163],"that":[35,79,101,154],"is":[36],"unique":[37],"essential":[39],"for":[40,144,168],"object":[41,86],"tracking":[42,103,159],"tasks.":[43],"Utilizing":[44],"can":[47],"enhance":[48],"association":[49,87],"stability":[50],"classification":[52,89,120,147],"accuracy,":[53],"especially":[54],"in":[55,70,90],"cases":[56],"occlusion":[58],"category":[60,110],"ambiguity,":[61],"thereby":[62],"improving":[63,106],"adaptability":[64],"novel":[66],"classes.":[67],"Thus":[68],"motivated,":[69],"this":[71],"paper":[72],"we":[73,93,114],"propose":[74],"\\textbf{TRACT},":[75],"an":[76],"open-vocabulary":[77],"tracker":[78],"leverages":[80],"improve":[84],"both":[85],"OV-MOT.":[91,169],"Specifically,":[92],"introduce":[94],"\\textit{Trajectory":[96,124,129],"Consistency":[97],"Reinforcement}":[98],"(\\textbf{TCR})":[99],"strategy,":[100],"benefits":[102],"performance":[104],"by":[105],"target":[107],"identity":[108],"consistency.":[111],"In":[112],"addition,":[113],"present":[115],"\\textbf{TraCLIP},":[116],"plug-and-play":[118],"module.":[121],"It":[122],"integrates":[123],"Feature":[125],"Aggregation}":[126],"(\\textbf{TFA})":[127],"Semantic":[130],"Enrichment}":[131],"(\\textbf{TSE})":[132],"strategies":[133],"fully":[135],"leverage":[136],"from":[139],"visual":[140],"language":[142],"perspectives":[143],"enhancing":[145],"the":[146],"results.":[148],"Extensive":[149],"experiments":[150],"OV-TAO":[152],"show":[153],"our":[155],"TRACT":[156],"significantly":[157],"improves":[158],"performance,":[160],"highlighting":[161],"as":[164],"valuable":[166],"asset":[167],"Code":[170],"will":[171],"be":[172],"released.":[173]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}