{"id":"https://openalex.org/W4415748131","doi":"https://doi.org/10.1109/tcsvt.2025.3627667","title":"State Space Models for Long-Term Temporal Context in 3D Single Object Tracking","display_name":"State Space Models for Long-Term Temporal Context in 3D Single Object Tracking","publication_year":2025,"publication_date":"2025-10-31","ids":{"openalex":"https://openalex.org/W4415748131","doi":"https://doi.org/10.1109/tcsvt.2025.3627667"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2025.3627667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3627667","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/A5112305275","display_name":"Jingshan Xiao","orcid":"https://orcid.org/0000-0001-9384-8665"},"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":"Jie Xiao","raw_affiliation_strings":["School of Information Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-9384-8665","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/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/A5100514151","display_name":"Yuyang Tang","orcid":"https://orcid.org/0000-0001-5292-2873"},"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":"Yuyang Tang","raw_affiliation_strings":["School of Information Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5292-2873","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/A5007421671","display_name":"Chuxin Wang","orcid":"https://orcid.org/0000-0003-1431-7677"},"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":"Chuxin Wang","raw_affiliation_strings":["School of Information Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1431-7677","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":"https://openalex.org/A5100648981","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":0.28570813,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"4","first_page":"4941","last_page":"4955"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.6366000175476074,"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":0.6366000175476074,"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":0.15219999849796295,"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":0.0414000004529953,"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/leverage","display_name":"Leverage (statistics)","score":0.5896000266075134},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4472000002861023},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.44209998846054077},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.42980000376701355},{"id":"https://openalex.org/keywords/serialization","display_name":"Serialization","score":0.4250999987125397},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.3978999853134155},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.392300009727478},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.3898000121116638},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.3840000033378601},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3765000104904175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7522000074386597},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.593500018119812},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5896000266075134},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4472000002861023},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.44209998846054077},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.42980000376701355},{"id":"https://openalex.org/C52723943","wikidata":"https://www.wikidata.org/wiki/Q1127410","display_name":"Serialization","level":2,"score":0.4250999987125397},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3978999853134155},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.392300009727478},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3898000121116638},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3840000033378601},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3765000104904175},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.3621000051498413},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3246000111103058},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3086000084877014},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2915000021457672},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2892000079154968},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.2590000033378601},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3627667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3627667","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/G3828173677","display_name":null,"funder_award_id":"62121002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8386678807","display_name":null,"funder_award_id":"62394354","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/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"3D":[0,65],"single":[1],"object":[2],"tracking":[3],"(3D":[4],"SOT)":[5],"remains":[6],"a":[7,63,81,92,106,122],"challenging":[8],"task":[9],"due":[10],"to":[11,37,99,110],"the":[12,23],"sparsity":[13],"of":[14,25],"point":[15],"clouds,":[16],"appearance":[17],"variations":[18],"caused":[19],"by":[20],"occlusions,":[21],"and":[22,44,53,94,104,162],"difficulty":[24],"modeling":[26],"long-term":[27,77],"temporal":[28,39,54,78,117,160],"context.":[29],"Although":[30],"recent":[31],"Transformer-based":[32],"approaches":[33],"leverage":[34],"memory":[35],"mechanisms":[36],"propagate":[38],"information,":[40],"their":[41],"quadratic":[42],"complexity":[43],"reliance":[45],"on":[46,148],"discrete":[47],"historical":[48,132],"snapshots":[49],"limit":[50],"both":[51],"efficiency":[52],"coherence.":[55],"To":[56],"address":[57],"these":[58],"limitations,":[59],"we":[60,90,120],"propose":[61,121],"SSMTrack,":[62],"novel":[64],"SOT":[66],"framework":[67],"built":[68],"upon":[69,170],"state":[70,85],"space":[71],"models":[72,76],"(SSMs),":[73],"which":[74],"efficiently":[75],"dependencies":[79],"through":[80],"continuously":[82],"evolving":[83],"hidden":[84],"with":[86,158],"linear":[87],"complexity.":[88],"Specifically,":[89],"introduce":[91],"serialization":[93],"bidirectional":[95],"scanning":[96],"(SBS)":[97],"strategy":[98],"enhance":[100],"intra-frame":[101],"feature":[102,142],"interactions":[103],"design":[105],"Target-Aware":[107],"Encoder":[108],"(TAE)":[109],"extract":[111],"target":[112,141],"cues":[113],"while":[114,134],"maintaining":[115],"stable":[116],"representations.":[118],"Furthermore,":[119],"Temporal":[123],"Causal":[124],"Shape":[125],"Learning":[126],"(TCSL)":[127],"mechanism":[128],"that":[129,153],"preserves":[130],"critical":[131],"information":[133],"adaptively":[135],"integrating":[136],"current":[137],"inputs,":[138],"progressively":[139],"enriching":[140],"representations":[143],"over":[144],"time.":[145],"Extensive":[146],"experiments":[147],"three":[149],"benchmark":[150],"datasets":[151],"demonstrate":[152],"SSMTrack":[154],"achieves":[155],"state-of-the-art":[156],"performance":[157],"strong":[159],"coherence":[161],"high":[163],"efficiency.":[164],"The":[165],"code":[166],"will":[167],"be":[168],"released":[169],"publication.":[171]},"counts_by_year":[],"updated_date":"2026-04-07T06:01:17.266235","created_date":"2025-10-31T00:00:00"}