{"id":"https://openalex.org/W4416250655","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227900","title":"Spatio-Temporal Bidirectional Fusion RGB-T Tracking","display_name":"Spatio-Temporal Bidirectional Fusion RGB-T Tracking","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416250655","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227900"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5100605495","display_name":"Fang Dong","orcid":"https://orcid.org/0000-0001-6770-326X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fang Dong","raw_affiliation_strings":["National University of Defense Technology,College of Computer,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019758816","display_name":"Dianxi Shi","orcid":"https://orcid.org/0000-0002-8112-371X"},"institutions":[{"id":"https://openalex.org/I4210096250","display_name":"Beijing Institute of Big Data Research","ror":"https://ror.org/00s1sz824","country_code":"CN","type":"facility","lineage":["https://openalex.org/I20231570","https://openalex.org/I37796252","https://openalex.org/I4210096250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dianxi Shi","raw_affiliation_strings":["Advanced Institute of Big Data,Department of Big Data Intelligence,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Advanced Institute of Big Data,Department of Big Data Intelligence,Beijing,China","institution_ids":["https://openalex.org/I4210096250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083915599","display_name":"Jianqiang Xia","orcid":"https://orcid.org/0009-0001-6719-0238"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqiang Xia","raw_affiliation_strings":["Shanghai Jiao Tong University,College of Computer,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,College of Computer,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115593492","display_name":"Jing Xie","orcid":"https://orcid.org/0000-0001-6113-1336"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Xie","raw_affiliation_strings":["Academy of Military Science,National Innovation Institute of Defense Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Academy of Military Science,National Innovation Institute of Defense Technology,Beijing,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066842073","display_name":"Shiguang Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaowu Yang","raw_affiliation_strings":["National University of Defense Technology,College of Computer,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100605495"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37345133,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9731000065803528,"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":0.9731000065803528,"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":0.008999999612569809,"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":0.002400000113993883,"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/robustness","display_name":"Robustness (evolution)","score":0.6310999989509583},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.6101999878883362},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5149000287055969},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.513700008392334},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4772000014781952},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4652999937534332},{"id":"https://openalex.org/keywords/fusion-mechanism","display_name":"Fusion mechanism","score":0.4544999897480011},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.453900009393692},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.43540000915527344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7534000277519226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6782000064849854},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.670199990272522},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6310999989509583},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.6101999878883362},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5149000287055969},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.513700008392334},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4772000014781952},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4652999937534332},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.4544999897480011},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.453900009393692},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.43540000915527344},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4203999936580658},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4115000069141388},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4009000062942505},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.3310000002384186},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3278000056743622},{"id":"https://openalex.org/C2982962833","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information fusion","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2822999954223633},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C154586513","wikidata":"https://www.wikidata.org/wiki/Q4420972","display_name":"Tracking system","level":3,"score":0.2612000107765198},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2470394683","https://openalex.org/W2527415613","https://openalex.org/W2765667535","https://openalex.org/W2963188742","https://openalex.org/W2963905288","https://openalex.org/W2997131652","https://openalex.org/W3001584168","https://openalex.org/W3035020406","https://openalex.org/W3099671582","https://openalex.org/W3110562975","https://openalex.org/W3153607844","https://openalex.org/W3158472981","https://openalex.org/W3174225630","https://openalex.org/W4283808043","https://openalex.org/W4296337406","https://openalex.org/W4304098539","https://openalex.org/W4312668764","https://openalex.org/W4312751983","https://openalex.org/W4386066459","https://openalex.org/W4386075603","https://openalex.org/W4386075647","https://openalex.org/W4386083135","https://openalex.org/W4392449443","https://openalex.org/W4392931239","https://openalex.org/W4393148493","https://openalex.org/W4393154934","https://openalex.org/W4396951406","https://openalex.org/W4402727444","https://openalex.org/W4402754150"],"related_works":[],"abstract_inverted_index":{"The":[0,90],"goal":[1],"of":[2,11,22,34,55,150],"RGB-T":[3,26,72,181],"tracking":[4,27,73,121],"is":[5,84],"to":[6,18,103,135,144,146,166],"fully":[7,62],"utilize":[8],"the":[9,12,20,32,35,53,66,87,107,115,120,142,147,151],"information":[10,44,58,94,111,118,140],"RGB":[13,36],"and":[14,37,46,98,105,109,114],"TIR":[15,38],"modality":[16,171],"sequences":[17],"enhance":[19],"robustness":[21],"object":[23],"tracking.":[24],"Existing":[25],"methods":[28],"usually":[29],"simply":[30],"fuse":[31,106],"features":[33],"search":[39],"regions,":[40],"resulting":[41],"in":[42],"insufficient":[43],"interaction":[45,95],"introducing":[47],"unnecessary":[48,170],"background":[49,173],"noise.":[50,174],"In":[51,155],"addition,":[52,156],"utilization":[54],"temporal":[56,99,116,138],"context":[57,117,139],"has":[59],"not":[60],"been":[61],"explored.":[63],"To":[64],"address":[65],"above":[67],"limitations,":[68],"we":[69,126,157],"propose":[70,77,127],"an":[71,128],"framework":[74],"STTrack.":[75],"We":[76],"a":[78,159],"Spatio-Temporal":[79],"Bidirectional":[80],"Adapter":[81],"(STA),":[82],"which":[83],"integrated":[85],"into":[86],"ViT":[88],"backbone.":[89],"STA":[91],"conducts":[92],"bidirectional":[93],"between":[96,112],"spatial":[97],"context,":[100],"so":[101],"as":[102],"explore":[104],"synergistic":[108],"complementary":[110],"modalities":[113],"during":[119],"process":[122],"more":[123],"effectively.":[124],"Simultaneously,":[125],"Asynchronous":[129],"Online":[130],"Template":[131],"Update":[132],"(AOTU)":[133],"strategy":[134],"update":[136],"high-quality":[137],"for":[141],"tracker,":[143],"adapt":[145],"appearance":[148],"changes":[149],"target":[152],"over":[153],"time.":[154],"introduce":[158],"Modal":[160],"State":[161],"Guided":[162],"Fusion":[163],"(MSGF)":[164],"module":[165],"adaptively":[167],"filter":[168],"out":[169],"or":[172],"Extensive":[175],"experiments":[176],"conducted":[177],"on":[178],"five":[179],"popular":[180],"benchmark":[182],"datasets":[183],"demonstrate":[184],"that":[185],"STTrack":[186],"outperforms":[187],"existing":[188],"state-of-the-art":[189],"methods.":[190]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}