{"id":"https://openalex.org/W7128430808","doi":"https://doi.org/10.1109/tcsvt.2026.3662479","title":"WmLSTM: A Plug-and-Play Window-Level mLSTM-Based Temporal Encoder for Robust Visual Tracking","display_name":"WmLSTM: A Plug-and-Play Window-Level mLSTM-Based Temporal Encoder for Robust Visual Tracking","publication_year":2026,"publication_date":"2026-02-09","ids":{"openalex":"https://openalex.org/W7128430808","doi":"https://doi.org/10.1109/tcsvt.2026.3662479"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3662479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3662479","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/A5101808186","display_name":"Yao Chen","orcid":"https://orcid.org/0000-0003-2324-2013"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Chen","raw_affiliation_strings":["National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology (ASGO) and the School of Computer Science, Northwestern Polytechnical University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0003-2324-2013","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology (ASGO) and the School of Computer Science, Northwestern Polytechnical University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124718151","display_name":"Guancheng Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guancheng Jia","raw_affiliation_strings":["National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology (ASGO) and the School of Computer Science, Northwestern Polytechnical University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0009-0008-7540-0902","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology (ASGO) and the School of Computer Science, Northwestern Polytechnical University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124746017","display_name":"Ding Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ding Ma","raw_affiliation_strings":["National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology (ASGO) and the School of Computer Science, Northwestern Polytechnical University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0009-0007-1501-0470","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology (ASGO) and the School of Computer Science, Northwestern Polytechnical University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014604035","display_name":"Yufei Zha","orcid":"https://orcid.org/0000-0001-5013-2501"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufei Zha","raw_affiliation_strings":["National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology (ASGO) and the School of Computer Science, Northwestern Polytechnical University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0001-5013-2501","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology (ASGO) and the School of Computer Science, Northwestern Polytechnical University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125449328","display_name":"Peng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology (ASGO) and the School of Computer Science, Northwestern Polytechnical University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0001-9690-7026","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology (ASGO) and the School of Computer Science, Northwestern Polytechnical University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13088108,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"6","first_page":"9072","last_page":"9086"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9560999870300293,"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":0.9560999870300293,"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":0.007300000172108412,"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":0.00570000009611249,"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/encoder","display_name":"Encoder","score":0.6168000102043152},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6110000014305115},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5304999947547913},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5214999914169312},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4925999939441681},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.42820000648498535},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3901999890804291},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3889000117778778},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3824999928474426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7943000197410583},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6168000102043152},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6110000014305115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5777000188827515},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5304999947547913},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5214999914169312},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4925999939441681},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.42820000648498535},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41850000619888306},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3889000117778778},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3433000147342682},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3353999853134155},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.2985000014305115},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2743000090122223},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25600001215934753},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3662479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3662479","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Temporal":[0],"context":[1],"modeling":[2,65,72,101],"constitutes":[3],"a":[4,17,55],"fundamental":[5],"issue":[6],"for":[7,67],"robust":[8],"visual":[9,68,90],"tracking.":[10,69],"However,":[11],"existing":[12],"approaches":[13],"are":[14],"plagued":[15],"by":[16],"critical":[18],"granularity":[19],"trade-off:":[20],"frame-level":[21],"template":[22],"update":[23],"mechanisms":[24,38],"inevitably":[25],"introduce":[26],"background":[27,80],"redundancy":[28],"due":[29],"to":[30],"global":[31],"frame":[32],"information":[33],"aggregation,":[34],"while":[35,77],"token-level":[36],"propagation":[37],"undermine":[39],"inherent":[40],"local":[41],"spatial":[42,75],"correlations":[43,76],"via":[44],"independent":[45],"feature":[46],"transmission.":[47],"To":[48],"resolve":[49],"this":[50],"challenge,":[51],"we":[52,83],"propose":[53],"WmLSTM,":[54],"plug-and-play":[56,107],"Window-level":[57],"mLSTM-based":[58],"temporal":[59,64],"encoder":[60],"that":[61,97,126],"reconfigures":[62],"the":[63,85,165,170],"paradigm":[66],"First,":[70],"window-centric":[71],"retains":[73],"intra-window":[74],"adaptively":[78],"suppressing":[79],"clutter.":[81],"Second,":[82],"pioneer":[84],"application":[86],"of":[87,172],"mLSTM":[88],"in":[89],"tracking,":[91],"exploiting":[92],"its":[93],"explicit":[94],"memory":[95],"architecture":[96],"outperforms":[98],"implicit":[99],"sequence":[100],"alternatives":[102],"(e.g.,":[103],"Mamba).":[104],"Third,":[105],"our":[106],"design":[108],"enables":[109],"seamless":[110],"integration":[111],"with":[112,115,192],"state-of-the-art":[113,139],"trackers":[114],"minor":[116],"computational":[117],"overhead.":[118],"Extensive":[119],"experiments":[120],"on":[121,141,181,188],"seven":[122],"benchmark":[123],"datasets":[124],"validate":[125],"WmLSTMTrack":[127],"achieves":[128],"an":[129],"excellent":[130],"balance":[131],"among":[132],"accuracy,":[133],"speed,":[134],"and":[135,157],"parameter":[136],"efficiency,":[137],"attaining":[138],"accuracy":[140],"five":[142],"benchmarks,":[143],"superior":[144],"real-time":[145,176],"speed":[146],"(GPU:":[147],"201":[148],"<italic":[149,154],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[150,155,190],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">fps</i>,":[151],"CPU:":[152],"47":[153],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">fps</i>),":[156],"compact":[158],"model":[159],"size":[160],"(8.22":[161],"M":[162],"parameters).":[163],"Moreover,":[164],"WMLSTM":[166],"module":[167],"consistently":[168],"enhances":[169],"performance":[171],"diverse":[173],"trackers,":[174],"e.g.,":[175],"FERMT-256:":[177],"+2.3":[178],"points":[179,186],"SR75":[180],"GOT-10k,":[182],"non-real-time":[183],"EVPTrack-224:":[184],"+1.8":[185],"P":[187],"LaSOT<italic":[189],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><sub>ext</sub></i>,":[191],"merely":[193],"30":[194],"training":[195],"epochs.":[196],"The":[197],"source":[198],"code":[199],"is":[200],"available":[201],"at":[202],"https://github.com/Xiaochen918/WmLSTM.":[203]},"counts_by_year":[],"updated_date":"2026-06-06T06:22:57.294733","created_date":"2026-02-10T00:00:00"}