{"id":"https://openalex.org/W7131104387","doi":"https://doi.org/10.1109/tip.2026.3661393","title":"SMTrack: State-Aware Mamba for Efficient Temporal Modeling in Visual Tracking","display_name":"SMTrack: State-Aware Mamba for Efficient Temporal Modeling in Visual Tracking","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7131104387","doi":"https://doi.org/10.1109/tip.2026.3661393","pmid":"https://pubmed.ncbi.nlm.nih.gov/41729667"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3661393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3661393","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5060224928","display_name":"Yinchao Ma","orcid":"https://orcid.org/0009-0003-0506-5217"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinchao Ma","raw_affiliation_strings":["School of Information Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0003-0506-5217","affiliations":[{"raw_affiliation_string":"School of Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101450608","display_name":"Dewei Yang","orcid":"https://orcid.org/0000-0002-3914-4445"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dengqing Yang","raw_affiliation_strings":["School of Information Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006578719","display_name":"Zhangyu He","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhangyu He","raw_affiliation_strings":["School of Information Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0002-0524-3952","affiliations":[{"raw_affiliation_string":"School of Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054606798","display_name":"Wenfei Yang","orcid":"https://orcid.org/0000-0003-3599-7659"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenfei Yang","raw_affiliation_strings":["School of Information Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-3599-7659","affiliations":[{"raw_affiliation_string":"School of Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":null,"display_name":"Tianzhu Zhang","orcid":"https://orcid.org/0000-0003-1856-9564"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianzhu Zhang","raw_affiliation_strings":["School of Information Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1856-9564","affiliations":[{"raw_affiliation_string":"School of Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17372136,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"2249","last_page":"2261"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9394999742507935,"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":0.9394999742507935,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.009700000286102295,"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":0.005799999926239252,"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/computational-complexity-theory","display_name":"Computational complexity theory","score":0.5267000198364258},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.47609999775886536},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.44920000433921814},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4302000105381012},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.427700012922287},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4196000099182129},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.41190001368522644},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4083999991416931},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.37940001487731934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7986999750137329},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6514000296592712},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5737000107765198},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.5267000198364258},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.47609999775886536},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.44920000433921814},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4302000105381012},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.427700012922287},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4196000099182129},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4083999991416931},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.37940001487731934},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3285999894142151},{"id":"https://openalex.org/C119666444","wikidata":"https://www.wikidata.org/wiki/Q5977280","display_name":"Temporal resolution","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2863999903202057},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.27459999918937683},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3661393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3661393","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:41729667","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41729667","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.45308756828308105}],"awards":[{"id":"https://openalex.org/G6447223638","display_name":null,"funder_award_id":"U25A20536","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6545572955","display_name":null,"funder_award_id":"12150007","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Visual":[0],"tracking":[1,34,98],"aims":[2],"to":[3,28,32,63,107,128,154],"automatically":[4],"estimate":[5],"the":[6,69,72],"state":[7,73,162],"of":[8,71,170],"a":[9,13,78,92,119],"target":[10],"object":[11],"in":[12,20,45,50],"video":[14],"sequence,":[15],"which":[16,166],"is":[17],"challenging":[18],"especially":[19],"dynamic":[21],"scenarios.":[22],"Thus,":[23],"numerous":[24],"methods":[25],"are":[26],"proposed":[27],"introduce":[29],"temporal":[30,48,65,80,110,132,141,172],"cues":[31,133,173],"enhance":[33],"robustness.":[35],"However,":[36],"conventional":[37],"CNN":[38],"and":[39,97,164],"Transformer":[40],"architectures":[41],"exhibit":[42],"inherent":[43],"limitations":[44],"modeling":[46,81],"long-range":[47,109,140],"dependencies":[49],"visual":[51,84],"tracking,":[52,85],"often":[53],"necessitating":[54],"either":[55],"complex":[56],"customized":[57,101],"modules":[58,102],"or":[59,103],"substantial":[60,104],"computational":[61,105,145,168,187],"costs":[62,106,169],"integrate":[64],"cues.":[66],"Inspired":[67],"by":[68],"success":[70],"space":[74,123],"model,":[75],"we":[76,117],"propose":[77,118],"novel":[79,120],"paradigm":[82],"for":[83,95,134],"termed":[86],"State-aware":[87],"Mamba":[88],"Tracker":[89],"(SMTrack),":[90],"providing":[91],"neat":[93],"pipeline":[94],"training":[96],"without":[99],"needing":[100],"build":[108],"dependencies.":[111],"It":[112],"enjoys":[113],"several":[114],"merits.":[115],"First,":[116],"selective":[121],"state-aware":[122],"model":[124],"with":[125,143,156,185],"state-wise":[126],"parameters":[127],"capture":[129],"more":[130],"diverse":[131],"robust":[135],"tracking.":[136,175],"Second,":[137],"SMTrack":[138,150,181],"facilitates":[139],"interactions":[142],"linear":[144],"complexity":[146],"during":[147,174],"training.":[148],"Third,":[149],"enables":[151],"each":[152],"frame":[153],"interact":[155],"previously":[157],"tracked":[158],"frames":[159],"via":[160],"hidden":[161],"propagation":[163],"updating,":[165],"releases":[167],"handling":[171],"Extensive":[176],"experimental":[177],"results":[178],"demonstrate":[179],"that":[180],"achieves":[182],"promising":[183],"performance":[184],"low":[186],"costs.":[188]},"counts_by_year":[],"updated_date":"2026-02-28T06:14:18.631764","created_date":"2026-02-06T00:00:00"}