{"id":"https://openalex.org/W6922180481","doi":"https://doi.org/10.1109/tcsvt.2025.3587703","title":"BR-MoE: Blind Multi-Modal Tracking With Route-Dynamic Mixture of Experts","display_name":"BR-MoE: Blind Multi-Modal Tracking With Route-Dynamic Mixture of Experts","publication_year":2025,"publication_date":"2025-07-10","ids":{"openalex":"https://openalex.org/W6922180481","doi":"https://doi.org/10.1109/tcsvt.2025.3587703"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3587703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3587703","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":null,"display_name":"Qingguo Meng","orcid":"https://orcid.org/0009-0007-0906-1976"},"institutions":[{"id":"https://openalex.org/I197869895","display_name":"Anhui Medical University","ror":"https://ror.org/03xb04968","country_code":"CN","type":"education","lineage":["https://openalex.org/I197869895"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qingguo Meng","raw_affiliation_strings":["Anhui Provincial International Joint Research Center for Advanced Technology in Medical Imaging, Anhui Provincial Key Laboratory of Secure Artificial Intelligence, School of Artificial Intelligence, Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial International Joint Research Center for Advanced Technology in Medical Imaging, Anhui Provincial Key Laboratory of Secure Artificial Intelligence, School of Artificial Intelligence, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I197869895"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Andong Lu","orcid":"https://orcid.org/0000-0002-0902-2260"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Andong Lu","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zhe Jin","orcid":"https://orcid.org/0000-0003-4501-7992"},"institutions":[{"id":"https://openalex.org/I197869895","display_name":"Anhui Medical University","ror":"https://ror.org/03xb04968","country_code":"CN","type":"education","lineage":["https://openalex.org/I197869895"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Jin","raw_affiliation_strings":["Anhui Provincial International Joint Research Center for Advanced Technology in Medical Imaging, Anhui Provincial Key Laboratory of Secure Artificial Intelligence, School of Artificial Intelligence, Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial International Joint Research Center for Advanced Technology in Medical Imaging, Anhui Provincial Key Laboratory of Secure Artificial Intelligence, School of Artificial Intelligence, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I197869895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197869895"],"apc_list":null,"apc_paid":null,"fwci":3.6185,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93988411,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"35","issue":"12","first_page":"11908","last_page":"11921"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9039000272750854,"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":0.9039000272750854,"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":0.02250000089406967,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.005100000184029341,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6105999946594238},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5971999764442444},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5641999840736389},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5235000252723694},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5180000066757202},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.49970000982284546},{"id":"https://openalex.org/keywords/active-appearance-model","display_name":"Active appearance model","score":0.4514999985694885},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.426800012588501},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.39309999346733093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7915999889373779},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6747999787330627},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6105999946594238},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5971999764442444},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5641999840736389},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5235000252723694},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5180000066757202},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.49970000982284546},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4823000133037567},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.4514999985694885},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.39309999346733093},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3928999900817871},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.37139999866485596},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3515999913215637},{"id":"https://openalex.org/C154586513","wikidata":"https://www.wikidata.org/wiki/Q4420972","display_name":"Tracking system","level":3,"score":0.34779998660087585},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.29899999499320984},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C32283439","wikidata":"https://www.wikidata.org/wiki/Q1407014","display_name":"Radar tracker","level":3,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3587703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3587703","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":[{"score":0.725721001625061,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2818677759","display_name":null,"funder_award_id":"2308085MF200","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"},{"id":"https://openalex.org/G5331336184","display_name":null,"funder_award_id":"62376003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8360374351","display_name":null,"funder_award_id":"62406002","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"},{"id":"https://openalex.org/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W1964846093","https://openalex.org/W2016802777","https://openalex.org/W2098711149","https://openalex.org/W2109553284","https://openalex.org/W2130026429","https://openalex.org/W2295160276","https://openalex.org/W2470394683","https://openalex.org/W2512653618","https://openalex.org/W2917353338","https://openalex.org/W2962766617","https://openalex.org/W2963351448","https://openalex.org/W2963905288","https://openalex.org/W2966759264","https://openalex.org/W2991778094","https://openalex.org/W2996575194","https://openalex.org/W3001584168","https://openalex.org/W3014764396","https://openalex.org/W3035453691","https://openalex.org/W3035511673","https://openalex.org/W3035571898","https://openalex.org/W3035672751","https://openalex.org/W3035725297","https://openalex.org/W3099671582","https://openalex.org/W3101990647","https://openalex.org/W3110562975","https://openalex.org/W3127756064","https://openalex.org/W3132864630","https://openalex.org/W3153607844","https://openalex.org/W3158472981","https://openalex.org/W3163168119","https://openalex.org/W3181069167","https://openalex.org/W3183904268","https://openalex.org/W3187284461","https://openalex.org/W3198377975","https://openalex.org/W3202534481","https://openalex.org/W3209993199","https://openalex.org/W3214586131","https://openalex.org/W4214737929","https://openalex.org/W4214759957","https://openalex.org/W4283808043","https://openalex.org/W4293523180","https://openalex.org/W4304098539","https://openalex.org/W4312310776","https://openalex.org/W4312532041","https://openalex.org/W4312751983","https://openalex.org/W4312805142","https://openalex.org/W4320036905","https://openalex.org/W4321195219","https://openalex.org/W4362657847","https://openalex.org/W4366824006","https://openalex.org/W4380520387","https://openalex.org/W4381894703","https://openalex.org/W4382240192","https://openalex.org/W4385757397","https://openalex.org/W4386075603","https://openalex.org/W4386075647","https://openalex.org/W4386075741","https://openalex.org/W4386083135","https://openalex.org/W4387587572","https://openalex.org/W4390738630","https://openalex.org/W4390874575","https://openalex.org/W4392449443","https://openalex.org/W4400447303","https://openalex.org/W4401109531","https://openalex.org/W4401210525","https://openalex.org/W4401328869","https://openalex.org/W4402727444","https://openalex.org/W4402753948","https://openalex.org/W4402754150","https://openalex.org/W4403182256","https://openalex.org/W4403842231","https://openalex.org/W4404179499","https://openalex.org/W4404641681","https://openalex.org/W4405488178","https://openalex.org/W4409346692","https://openalex.org/W4416016665"],"related_works":[],"abstract_inverted_index":{"Multi-modal":[0],"object":[1],"tracking":[2,11,44,226],"combines":[3,166],"visible":[4],"light":[5],"with":[6,87],"auxiliary":[7],"modalities":[8],"for":[9,36,219],"better":[10],"accuracy,":[12],"including":[13],"sub-tasks":[14],"like":[15],"RGB-T":[16],"(RGB":[17,21,26],"and":[18,22,24,27,34,69,100,110,165,195,215,236,239,244],"Thermal),":[19],"RGB-D":[20],"Depth),":[23],"RGB-E":[25],"Event)":[28],"tracking.":[29],"However,":[30],"existing":[31],"algorithms,":[32],"designed":[33],"trained":[35,180],"specific":[37,144],"tasks,":[38],"impose":[39],"high":[40],"costs":[41],"on":[42,49,162,212,223,233,242],"universal":[43,57],"systems":[45],"as":[46],"they":[47],"rely":[48],"multiple":[50],"independent":[51],"trackers.":[52],"Despite":[53],"efforts":[54],"to":[55,64,128,142,157,169,192],"develop":[56],"multi-modal":[58,225],"trackers,":[59],"these":[60],"methods":[61],"often":[62],"fail":[63],"effectively":[65],"integrate":[66],"both":[67,98],"modality-agnostic":[68,99,130],"modality-specific":[70,101,136,159],"information":[71],"across":[72],"various":[73],"modalities,":[74],"constraining":[75],"their":[76,167],"performance.":[77],"In":[78,121,184,200],"this":[79],"paper,":[80],"we":[81,187,203],"propose":[82],"the":[83,118,158,163,171,185,197,201,217],"Blind":[84],"Multi-Modal":[85],"Tracking":[86],"Route-Dynamic":[88],"Mixture":[89],"of":[90,103,117,208],"Experts":[91],"(BR-MoE).":[92],"This":[93],"approach":[94],"can":[95],"simultaneously":[96],"model":[97,111,218],"features":[102,210],"each":[104,139],"modality":[105,119,190],"within":[106],"a":[107,149,205],"unified":[108],"structure":[109],"parameters,":[112],"all":[113],"without":[114],"prior":[115],"knowledge":[116],"types.":[120],"particular,":[122],"BR-MoE":[123,147,178,229],"employs":[124],"Vision":[125],"Transformer":[126],"(ViT)":[127],"extract":[129],"features,":[131],"while":[132],"embedding":[133],"four":[134],"parallel":[135],"experts":[137,160],"in":[138,181],"ViT":[140],"block":[141],"capture":[143],"features.":[145],"Additionally,":[146],"incorporates":[148],"Modality-Aware":[150],"Module":[151],"(MAM)":[152],"that":[153],"adaptively":[154],"assigns":[155],"weights":[156],"based":[161,211],"input":[164],"outputs":[168],"generate":[170],"final":[172],"feature":[173,220],"representation.":[174],"To":[175],"achieve":[176],"this,":[177],"is":[179],"two":[182],"phases.":[183],"first,":[186],"manually":[188],"provide":[189],"types":[191],"supervise":[193],"MAM":[194],"select":[196],"right":[198],"expert.":[199],"second,":[202],"do":[204],"weighted":[206],"aggregation":[207],"experts\u2019":[209],"MAM\u2019s":[213],"decision":[214],"fine-tune":[216],"changes.":[221],"Experiments":[222],"five":[224],"datasets":[227],"show":[228],"gets":[230],"state-of-the-art":[231],"performance":[232,241],"RGBT234,":[234],"DepthTrack":[235],"VisEvent":[237],"datasets,":[238],"comparable":[240],"LasHeR":[243],"VOT-RGBD22":[245],"datasets.":[246]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-04-12T07:58:50.170612","created_date":"2025-10-10T00:00:00"}