{"id":"https://openalex.org/W4409128969","doi":"https://doi.org/10.1109/tcsvt.2025.3557570","title":"Mamba Adapter: Efficient Multi-Modal Fusion for Vision-Language Tracking","display_name":"Mamba Adapter: Efficient Multi-Modal Fusion for Vision-Language Tracking","publication_year":2025,"publication_date":"2025-04-03","ids":{"openalex":"https://openalex.org/W4409128969","doi":"https://doi.org/10.1109/tcsvt.2025.3557570"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3557570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3557570","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/A5046443025","display_name":"Liangtao Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liangtao Shi","raw_affiliation_strings":["Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China"],"raw_orcid":"https://orcid.org/0009-0003-5934-8837","affiliations":[{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]},{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058101262","display_name":"Bineng Zhong","orcid":"https://orcid.org/0000-0003-3423-1539"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bineng Zhong","raw_affiliation_strings":["Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China"],"raw_orcid":"https://orcid.org/0000-0003-3423-1539","affiliations":[{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]},{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049287545","display_name":"Qihua Liang","orcid":"https://orcid.org/0000-0003-2353-5246"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qihua Liang","raw_affiliation_strings":["Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China"],"raw_orcid":"https://orcid.org/0000-0003-2353-5246","affiliations":[{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]},{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102797916","display_name":"Xiantao Hu","orcid":"https://orcid.org/0009-0007-1541-1717"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiantao Hu","raw_affiliation_strings":["Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China"],"raw_orcid":"https://orcid.org/0009-0007-1541-1717","affiliations":[{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]},{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019827327","display_name":"Zhiyi Mo","orcid":"https://orcid.org/0009-0008-6123-363X"},"institutions":[{"id":"https://openalex.org/I4210107865","display_name":"Wuzhou University","ror":"https://ror.org/01vv37n49","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210107865"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyi Mo","raw_affiliation_strings":["School of Data Science and Software Engineering, Wuzhou University, Wuzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-6123-363X","affiliations":[{"raw_affiliation_string":"School of Data Science and Software Engineering, Wuzhou University, Wuzhou, China","institution_ids":["https://openalex.org/I4210107865"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025660318","display_name":"Shuxiang Song","orcid":"https://orcid.org/0000-0003-0280-2640"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuxiang Song","raw_affiliation_strings":["Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China"],"raw_orcid":"https://orcid.org/0000-0003-0280-2640","affiliations":[{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]},{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5046443025"],"corresponding_institution_ids":["https://openalex.org/I29739308"],"apc_list":null,"apc_paid":null,"fwci":9.066,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.97872061,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"35","issue":"9","first_page":"9300","last_page":"9311"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9771000146865845,"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":0.9771000146865845,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9703999757766724,"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9678999781608582,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.6614448428153992},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6442534923553467},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5984874963760376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.552990734577179},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4898640811443329},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4739382565021515},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4529227316379547},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.4313086271286011},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.1110585629940033},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09144535660743713},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07293891906738281}],"concepts":[{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.6614448428153992},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6442534923553467},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5984874963760376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.552990734577179},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4898640811443329},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4739382565021515},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4529227316379547},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.4313086271286011},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.1110585629940033},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09144535660743713},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07293891906738281},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3557570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3557570","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":[],"awards":[{"id":"https://openalex.org/G1337806133","display_name":null,"funder_award_id":"62472109","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2223467375","display_name":null,"funder_award_id":"62466051","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G363226264","display_name":null,"funder_award_id":"U23A20383","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5457884491","display_name":null,"funder_award_id":"2025GXNSFAA069676","funder_id":"https://openalex.org/F4320330374","funder_display_name":"Foundation for Science and Technology"},{"id":"https://openalex.org/G5910227603","display_name":null,"funder_award_id":"2025GXNSFAA069417","funder_id":"https://openalex.org/F4320330374","funder_display_name":"Foundation for Science and Technology"},{"id":"https://openalex.org/G8509855231","display_name":null,"funder_award_id":"2024GXNSFGA010001","funder_id":"https://openalex.org/F4320330374","funder_display_name":"Foundation for Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320330374","display_name":"Foundation for Science and Technology","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1964846093","https://openalex.org/W2154889144","https://openalex.org/W2214352687","https://openalex.org/W2470394683","https://openalex.org/W2473930607","https://openalex.org/W2518013266","https://openalex.org/W2557641257","https://openalex.org/W2560647685","https://openalex.org/W2747053578","https://openalex.org/W2799058067","https://openalex.org/W2891033863","https://openalex.org/W2896457183","https://openalex.org/W2960512482","https://openalex.org/W2962766617","https://openalex.org/W2963109634","https://openalex.org/W2963351448","https://openalex.org/W2963534981","https://openalex.org/W3010072143","https://openalex.org/W3090155371","https://openalex.org/W3106542916","https://openalex.org/W3168243772","https://openalex.org/W3173871266","https://openalex.org/W3181069167","https://openalex.org/W3205239873","https://openalex.org/W3214586131","https://openalex.org/W4214759957","https://openalex.org/W4304098539","https://openalex.org/W4312323989","https://openalex.org/W4312651322","https://openalex.org/W4312751983","https://openalex.org/W4312805142","https://openalex.org/W4313307856","https://openalex.org/W4380520387","https://openalex.org/W4381735302","https://openalex.org/W4382119472","https://openalex.org/W4385245566","https://openalex.org/W4385569741","https://openalex.org/W4386066081","https://openalex.org/W4386066459","https://openalex.org/W4386075643","https://openalex.org/W4386075647","https://openalex.org/W4387969322","https://openalex.org/W4390871886","https://openalex.org/W4393147957","https://openalex.org/W4393148494","https://openalex.org/W4393154934","https://openalex.org/W4393159185","https://openalex.org/W4393159404","https://openalex.org/W4396598146","https://openalex.org/W4396982312","https://openalex.org/W4402704627","https://openalex.org/W4402753915","https://openalex.org/W4402754169","https://openalex.org/W4403758852","https://openalex.org/W4404783315","https://openalex.org/W4409257348","https://openalex.org/W4409367158","https://openalex.org/W4409368360"],"related_works":["https://openalex.org/W2132659060","https://openalex.org/W2031992971","https://openalex.org/W2788731446","https://openalex.org/W2204403038","https://openalex.org/W3214791684","https://openalex.org/W3152170969","https://openalex.org/W2379054866","https://openalex.org/W2370195708","https://openalex.org/W1490651872","https://openalex.org/W2139242969"],"abstract_inverted_index":{"Utilizing":[0],"the":[1,10,45,61,81,89,98,104,118,124,135,178,181,185,192,199],"high-level":[2],"semantic":[3],"information":[4,14,165],"of":[5,12,48,83,103,161,180,198],"language":[6,129,143,164],"to":[7,36,42,87],"compensate":[8],"for":[9,126],"limitations":[11],"vision":[13,127,145],"is":[15,108,147],"a":[16,66,132],"highly":[17],"regarded":[18],"approach":[19,96],"in":[20,55,150],"single-object":[21],"tracking.":[22],"However,":[23],"most":[24],"existing":[25],"vision-language":[26,92,174],"(VL)":[27],"trackers":[28],"employ":[29],"full-parameter":[30],"fine-tuning,":[31],"which":[32,79],"can":[33],"easily":[34],"lead":[35],"catastrophic":[37],"forgetting.":[38],"Therefore,":[39],"they":[40],"fail":[41],"fully":[43],"exploit":[44],"prior":[46],"knowledge":[47,102],"pre-trained":[49,106],"models":[50,205],"from":[51],"upstream":[52,105],"tasks,":[53],"resulting":[54],"unsatisfactory":[56],"tracking":[57,120,175],"performance.":[58],"To":[59],"alleviate":[60],"above":[62],"problem,":[63],"we":[64],"propose":[65],"simple":[67],"yet":[68],"effective":[69],"Vision-Language":[70],"Tracking":[71],"pipeline":[72],"based":[73],"on":[74,134,171,191],"Mamba":[75],"Adapter,":[76],"named":[77],"MAVLT,":[78],"adopts":[80],"idea":[82],"parameter-efficient":[84],"fine-tuning":[85],"(PEFT)":[86],"realize":[88],"interaction":[90,141,160],"between":[91,137,142],"modalities.":[93,138],"This":[94,115],"novel":[95],"offers":[97],"following":[99],"advantages:":[100],"(1)The":[101],"model":[107],"efficiently":[109],"inherited":[110],"by":[111],"freezing":[112],"its":[113],"parameters.":[114],"ensures":[116],"that":[117],"VL":[119],"framework":[121],"only":[122,196],"learns":[123],"modules":[125],"and":[128,144,163,204],"interaction,":[130],"with":[131,195],"focus":[133],"fusion":[136],"(2)The":[139],"modal":[140],"encoders":[146],"flexibly":[148],"bridged":[149],"each":[151],"encoder":[152],"layer":[153],"via":[154],"proposed":[155,182],"mamba":[156],"adapter,":[157],"enabling":[158],"efficient":[159],"visual":[162],"at":[166,208],"multiple":[167],"levels.":[168],"Extensive":[169],"experiments":[170],"five":[172],"popular":[173],"benchmarks":[176,194],"validate":[177],"effectiveness":[179],"MAVLT.":[183],"Particularly,":[184],"MAVLT":[186],"achieves":[187],"73.4%":[188],"AUC":[189],"score":[190],"LaSOT":[193],"0.18%(0.32M)":[197],"total":[200],"parameters":[201],"updates.":[202],"Code":[203],"are":[206],"available":[207],"https://github.com/GXNU-ZhongLab/MAVLT.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}