{"id":"https://openalex.org/W7129060509","doi":"https://doi.org/10.1109/jiot.2026.3664965","title":"Modality Interaction Decoupling: Spatiotemporal Memory-Driven Unified Multimodal Tracking Framework","display_name":"Modality Interaction Decoupling: Spatiotemporal Memory-Driven Unified Multimodal Tracking Framework","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W7129060509","doi":"https://doi.org/10.1109/jiot.2026.3664965"},"language":null,"primary_location":{"id":"doi:10.1109/jiot.2026.3664965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2026.3664965","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","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/A5101435823","display_name":"Lifeng Wang","orcid":"https://orcid.org/0000-0001-9979-3183"},"institutions":[{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lifeng Wang","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian Minzu University, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian Minzu University, Dalian, China","institution_ids":["https://openalex.org/I61565387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100415573","display_name":"Binbin Wang","orcid":"https://orcid.org/0000-0002-2035-3511"},"institutions":[{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binbin Wang","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian Minzu University, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian Minzu University, Dalian, China","institution_ids":["https://openalex.org/I61565387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016323852","display_name":"Fasheng Wang","orcid":"https://orcid.org/0000-0002-0946-0789"},"institutions":[{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fasheng Wang","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian Minzu University, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-0946-0789","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian Minzu University, Dalian, China","institution_ids":["https://openalex.org/I61565387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126126289","display_name":"Mengyin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyin Wang","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian Minzu University, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0001-1985-7026","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian Minzu University, Dalian, China","institution_ids":["https://openalex.org/I61565387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113409042","display_name":"Fuming Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuming Sun","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian Minzu University, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-3932-2712","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian Minzu University, Dalian, China","institution_ids":["https://openalex.org/I61565387"]}]},{"author_position":"last","author":{"id":null,"display_name":"Haojie Li","orcid":"https://orcid.org/0000-0003-3882-2205"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haojie Li","raw_affiliation_strings":["School of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-3882-2205","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15452784,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":"10","first_page":"21173","last_page":"21185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.913100004196167,"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":0.913100004196167,"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":0.015599999576807022,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.007699999958276749,"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/feature-extraction","display_name":"Feature extraction","score":0.6579999923706055},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5548999905586243},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5365999937057495},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.44699999690055847},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.41119998693466187},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37950000166893005},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.37389999628067017},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.36500000953674316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8590999841690063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6664000153541565},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6579999923706055},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5548999905586243},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5365999937057495},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4562999904155731},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.44699999690055847},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.41119998693466187},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37950000166893005},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.36500000953674316},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3515999913215637},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3391000032424927},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C2987395694","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Feature tracking","level":3,"score":0.31869998574256897},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.30959999561309814},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.30329999327659607},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.28349998593330383},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C88796919","wikidata":"https://www.wikidata.org/wiki/Q1142907","display_name":"Backbone network","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C38764148","wikidata":"https://www.wikidata.org/wiki/Q17098245","display_name":"Interaction information","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jiot.2026.3664965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2026.3664965","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1489220992","display_name":null,"funder_award_id":"62472067","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3117123538","display_name":"\u8fd0\u52a8\u7a81\u53d8\u4e0e\u5916\u89c2\u5267\u53d8\u7684\u76ee\u6807\u8ddf\u8e2a\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61972068","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/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Current":[0],"designs":[1],"of":[2,19],"multimodal":[3,194],"tracking":[4,195],"networks":[5,102],"primarily":[6],"focus":[7],"on":[8,77,202],"spatial":[9],"feature":[10,42,78,92,119,129],"interaction":[11,79],"within":[12,81],"the":[13,17,41,82,116,128,151,155,185],"backbone":[14,83,91],"and":[15,52,109,143,162,176,198],"lack":[16],"exploitation":[18],"temporal":[20,26,38],"information.":[21],"Although":[22],"some":[23],"approaches":[24],"incorporate":[25],"cues":[27],"by":[28],"introducing":[29],"sequential":[30],"information":[31,54,106],"from":[32,107],"adjacent":[33],"frames":[34],"or":[35],"employ":[36],"updated":[37],"features":[39],"during":[40,127],"extraction":[43,93,130],"stage,":[44],"they":[45],"struggle":[46],"to":[47,104,132,148,157],"capture":[48,158],"dynamic":[49],"object":[50,135,159],"variations":[51,161],"motion":[53,163],"in":[55,192],"complex":[56],"scenarios.":[57,196],"To":[58],"address":[59],"these":[60],"limitations,":[61],"this":[62,85],"paper":[63],"proposes":[64],"a":[65,89,124,139,168],"Spatiotemporal":[66],"Memory-Driven":[67],"Unified":[68],"Multimodal":[69],"Tracking":[70],"Framework":[71],"(SMMTrack).":[72],"Unlike":[73],"existing":[74],"works":[75],"relying":[76],"paradigms":[80],"network,":[84],"study":[86],"innovatively":[87],"introduces":[88],"decoupled":[90],"framework.":[94],"It":[95],"deploys":[96],"parallel,":[97],"independent":[98],"Vision":[99],"Transformer":[100],"(ViT)":[101],"dedicated":[103],"extracting":[105],"RGB":[108],"X":[110],"modalities":[111],"(RGB-T,":[112,174],"RGB-D,":[113,175],"RGB-E),":[114],"abandoning":[115],"conventional":[117],"intra-backbone":[118],"interaction.":[120],"Furthermore,":[121],"we":[122],"introduce":[123],"memory":[125],"mechanism":[126],"stage":[131],"enable":[133],"long-term":[134],"modeling.":[136],"In":[137],"addition,":[138],"Long-term":[140],"Memory":[141],"storage":[142],"retrieval":[144],"module":[145],"is":[146,167],"designed":[147],"dynamically":[149],"update":[150],"Memory-list,":[152],"thereby":[153],"allowing":[154],"model":[156],"appearance":[160],"trends":[164],"comprehensively.":[165],"SMMTrack":[166,183],"unified":[169],"framework":[170],"across":[171],"three":[172],"tasks":[173],"RGB-E":[177],"tracking).":[178],"Experimental":[179],"results":[180,199],"demonstrate":[181],"that":[182],"outperforms":[184],"state-of-the-art":[186],"(SOTA)":[187],"models,":[188],"achieving":[189],"outstanding":[190],"performance":[191],"diverse":[193],"Codes":[197],"are":[200],"released":[201],"https://github.com/qfxb/SMMTrack.":[203]},"counts_by_year":[],"updated_date":"2026-05-09T06:09:20.037420","created_date":"2026-02-17T00:00:00"}