{"id":"https://openalex.org/W7125831836","doi":"https://doi.org/10.1109/tcsvt.2026.3657773","title":"ProMoT: Progressive Prompting of Modality and Temporal Dynamics for RGB-T Tracking","display_name":"ProMoT: Progressive Prompting of Modality and Temporal Dynamics for RGB-T Tracking","publication_year":2026,"publication_date":"2026-01-27","ids":{"openalex":"https://openalex.org/W7125831836","doi":"https://doi.org/10.1109/tcsvt.2026.3657773"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3657773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3657773","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Circuits and Systems for Video Technology","raw_type":"journal-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/A5124024053","display_name":"Jia Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Chen","raw_affiliation_strings":["Fujian Key Laboratory of Pattern Recognition and Image Understanding, School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0006-1719-507X","affiliations":[{"raw_affiliation_string":"Fujian Key Laboratory of Pattern Recognition and Image Understanding, School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124031300","display_name":"Rui Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Xu","raw_affiliation_strings":["Fujian Key Laboratory of Network Computing and Intelligent Information Processing, College of Computer and Data Science, Fuzhou University, Fuzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3767-6816","affiliations":[{"raw_affiliation_string":"Fujian Key Laboratory of Network Computing and Intelligent Information Processing, College of Computer and Data Science, Fuzhou University, Fuzhou, China","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123922917","display_name":"Si Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si Chen","raw_affiliation_strings":["Fujian Key Laboratory of Pattern Recognition and Image Understanding, School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-5631-7942","affiliations":[{"raw_affiliation_string":"Fujian Key Laboratory of Pattern Recognition and Image Understanding, School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123978987","display_name":"Yuzhen Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuzhen Niu","raw_affiliation_strings":["Fujian Key Laboratory of Network Computing and Intelligent Information Processing, College of Computer and Data Science, Fuzhou University, Fuzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9874-9719","affiliations":[{"raw_affiliation_string":"Fujian Key Laboratory of Network Computing and Intelligent Information Processing, College of Computer and Data Science, Fuzhou University, Fuzhou, China","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123907789","display_name":"Yan Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Yan","raw_affiliation_strings":["School of Informatics, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-3674-7160","affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124050676","display_name":"Da-Han Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Da-Han Wang","raw_affiliation_strings":["Fujian Key Laboratory of Pattern Recognition and Image Understanding, School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-5901-0778","affiliations":[{"raw_affiliation_string":"Fujian Key Laboratory of Pattern Recognition and Image Understanding, School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09138073,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"6","first_page":"8092","last_page":"8107"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9469000101089478,"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":0.9469000101089478,"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":0.012199999764561653,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.004900000058114529,"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/discriminative-model","display_name":"Discriminative model","score":0.836899995803833},{"id":"https://openalex.org/keywords/bittorrent-tracker","display_name":"BitTorrent tracker","score":0.6510000228881836},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.64410001039505},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5831000208854675},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5688999891281128},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5098999738693237},{"id":"https://openalex.org/keywords/active-appearance-model","display_name":"Active appearance model","score":0.3889999985694885},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3889000117778778}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.836899995803833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7865999937057495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7044000029563904},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.6510000228881836},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.64410001039505},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5831000208854675},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5688999891281128},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5375999808311462},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5098999738693237},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.3889999985694885},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3889000117778778},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.3693000078201294},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.361299991607666},{"id":"https://openalex.org/C2779726219","wikidata":"https://www.wikidata.org/wiki/Q7685884","display_name":"Target acquisition","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.26440000534057617},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3657773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3657773","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7593285441398621}],"awards":[{"id":"https://openalex.org/G2532709054","display_name":null,"funder_award_id":"62576301","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3956371495","display_name":null,"funder_award_id":"3502Z202573073","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4782616423","display_name":null,"funder_award_id":"62372388","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6920052985","display_name":null,"funder_award_id":"62571466","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"RGB-T":[0,190],"tracking":[1,60,191],"benefits":[2],"from":[3,95,134],"the":[4,100,108,142,152],"complementary":[5],"nature":[6],"of":[7,77,110],"RGB":[8,173],"and":[9,32,38,66,136,144,174,187],"TIR":[10,175],"modalities,":[11],"yet":[12],"their":[13],"relative":[14],"reliability":[15],"for":[16,172],"target":[17,43,85,119,159],"localization":[18,160],"often":[19],"shifts":[20],"over":[21],"time.":[22],"Most":[23],"existing":[24],"trackers":[25],"fail":[26],"to":[27,29,148],"adapt":[28],"such":[30],"modality":[31,189],"temporal":[33,67],"dynamics":[34],"in":[35,42,161],"a":[36,58,70,123,169],"unified":[37],"effective":[39],"manner,":[40],"resulting":[41],"representations":[44,98,133],"that":[45,62,194],"are":[46,166],"neither":[47],"discriminative":[48,145],"nor":[49],"temporally":[50,117],"consistent.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55,81,121],"propose":[56],"ProMoT,":[57],"novel":[59],"framework":[61],"jointly":[63],"integrates":[64],"cross-modal":[65,132],"cues":[68,94],"into":[69],"progressive":[71],"prompting":[72],"process,":[73],"enabling":[74,107],"continuous":[75],"retrieval":[76],"target-aware":[78,111],"representations.":[79],"Specifically,":[80],"design":[82],"an":[83],"adaptive":[84],"query":[86],"generator":[87],"(QueryGen),":[88],"which":[89,129],"selectively":[90],"aggregates":[91],"informative":[92],"spatio-temporal":[93],"diverse":[96],"ghost":[97,103],"through":[99],"dynamic":[101],"sparse":[102],"fusion":[104],"mechanism,":[105],"thereby":[106],"generation":[109],"queries.":[112],"To":[113],"further":[114],"preserve":[115],"fine-grained,":[116],"consistent":[118],"cues,":[120],"introduce":[122],"high-order":[124,131],"contextual":[125],"prompt":[126],"updater":[127],"(PromptUpdater),":[128],"encodes":[130],"current":[135,153],"previous":[137],"frames.":[138,163],"These":[139],"prompts":[140],"establish":[141],"compact":[143],"inter-frame":[146],"context":[147],"not":[149],"only":[150],"refine":[151],"frame\u2019s":[154],"features":[155],"but":[156],"also":[157],"guide":[158],"future":[162],"All":[164],"components":[165],"built":[167],"upon":[168],"parameter-shared":[170],"backbone":[171],"inputs,":[176],"forming":[177],"our":[178],"complete":[179,186],"ProMoT":[180,195],"framework.":[181],"Extensive":[182],"experiments":[183],"on":[184],"both":[185],"missing":[188],"benchmarks":[192],"show":[193],"consistently":[196],"achieves":[197],"state-of-the-art":[198],"performance":[199],"while":[200],"balancing":[201],"efficiency.":[202]},"counts_by_year":[],"updated_date":"2026-06-06T06:22:57.294733","created_date":"2026-01-28T00:00:00"}