{"id":"https://openalex.org/W4415047670","doi":"https://doi.org/10.1109/tai.2025.3601075","title":"Single Target Tracking With Contextual Prompts in Scene Understanding","display_name":"Single Target Tracking With Contextual Prompts in Scene Understanding","publication_year":2025,"publication_date":"2025-10-10","ids":{"openalex":"https://openalex.org/W4415047670","doi":"https://doi.org/10.1109/tai.2025.3601075"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2025.3601075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2025.3601075","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/Single_Target_Tracking_with_Contextual_Prompts_in_Scene_Understanding/29929427","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078190224","display_name":"Xuelin Liu","orcid":"https://orcid.org/0000-0001-9491-7626"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuelin Liu","raw_affiliation_strings":["State Key Laboratory of Physical Oceanography and the Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Physical Oceanography and the Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031429868","display_name":"Huiyu Zhou","orcid":"https://orcid.org/0000-0002-9287-5095"},"institutions":[{"id":"https://openalex.org/I153648349","display_name":"University of Leicester","ror":"https://ror.org/04h699437","country_code":"GB","type":"education","lineage":["https://openalex.org/I153648349"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Huiyu Zhou","raw_affiliation_strings":["School of Computing and Mathematical Sciences, University of Leicester, Leicester, U.K"],"raw_orcid":"https://orcid.org/0000-0003-1634-9840","affiliations":[{"raw_affiliation_string":"School of Computing and Mathematical Sciences, University of Leicester, Leicester, U.K","institution_ids":["https://openalex.org/I153648349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029633264","display_name":"Junyu Dong","orcid":"https://orcid.org/0000-0001-7012-2087"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyu Dong","raw_affiliation_strings":["State Key Laboratory of Physical Oceanography and the Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0001-7012-2087","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Physical Oceanography and the Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101668576","display_name":"Jingjing Xiao","orcid":"https://orcid.org/0000-0002-0473-9748"},"institutions":[{"id":"https://openalex.org/I151075929","display_name":"Army Medical University","ror":"https://ror.org/05w21nn13","country_code":"CN","type":"education","lineage":["https://openalex.org/I151075929"]},{"id":"https://openalex.org/I191996457","display_name":"Dalian Medical University","ror":"https://ror.org/04c8eg608","country_code":"CN","type":"education","lineage":["https://openalex.org/I191996457"]},{"id":"https://openalex.org/I4210097509","display_name":"Second Affiliated Hospital of Chongqing Medical University","ror":"https://ror.org/00r67fz39","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210097509"]},{"id":"https://openalex.org/I87780372","display_name":"Chongqing Medical University","ror":"https://ror.org/017z00e58","country_code":"CN","type":"education","lineage":["https://openalex.org/I87780372"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Xiao","raw_affiliation_strings":["Bio-Med Informatics Research Centre & the Clinical Research Centre, The Second Affiliated Hospital of the Army Medical University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0001-5020-638X","affiliations":[{"raw_affiliation_string":"Bio-Med Informatics Research Centre & the Clinical Research Centre, The Second Affiliated Hospital of the Army Medical University, Chongqing, China","institution_ids":["https://openalex.org/I151075929","https://openalex.org/I191996457","https://openalex.org/I4210097509","https://openalex.org/I87780372"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057767079","display_name":"Xinghui Dong","orcid":"https://orcid.org/0000-0003-0170-7422"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinghui Dong","raw_affiliation_strings":["State Key Laboratory of Physical Oceanography and the Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-1047-427X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Physical Oceanography and the Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"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":0.21840504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":"5","first_page":"2523","last_page":"2534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.876800000667572,"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":0.876800000667572,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.8655999898910522,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.8529000282287598,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7250000238418579},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5472000241279602},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5414999723434448},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.4875999987125397},{"id":"https://openalex.org/keywords/tracking-system","display_name":"Tracking system","score":0.4828000068664551},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4350999891757965},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.42739999294281006},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4162999987602234},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41110000014305115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7748000025749207},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7250000238418579},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7221999764442444},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6222000122070312},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5472000241279602},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5414999723434448},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.4875999987125397},{"id":"https://openalex.org/C154586513","wikidata":"https://www.wikidata.org/wiki/Q4420972","display_name":"Tracking system","level":3,"score":0.4828000068664551},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4350999891757965},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.42739999294281006},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4162999987602234},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41110000014305115},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3817000091075897},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.3709999918937683},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.32409998774528503},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2685000002384186},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C71611378","wikidata":"https://www.wikidata.org/wiki/Q5165191","display_name":"Contextual design","level":3,"score":0.25189998745918274},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tai.2025.3601075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2025.3601075","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:figshare.com:article/29929427","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Single_Target_Tracking_with_Contextual_Prompts_in_Scene_Understanding/29929427","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/29929427","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Single_Target_Tracking_with_Contextual_Prompts_in_Scene_Understanding/29929427","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8941315746","display_name":null,"funder_award_id":"42176196","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":{"This":[0],"paper":[1],"presents":[2],"a":[3,44,51,68],"single":[4],"object":[5],"tracker":[6,133],"that":[7],"incorporates":[8],"scene":[9],"understanding,":[10],"referred":[11],"to":[12,55,80,108],"as":[13],"SU-STTrack,":[14],"which":[15],"explicitly":[16],"encodes":[17],"the":[18,22,33,38,88,95,110,140,159,162,167],"contextual":[19,40],"information":[20],"by":[21,85],"given":[23],"or":[24],"Multi-modal":[25],"Large":[26],"Language":[27],"Model":[28],"(MLLM)":[29],"generated":[30],"descriptions":[31],"of":[32,158,170],"tracking":[34,57,83,89,106,187],"scene.":[35],"SU-STTrack":[36,100,173],"merges":[37],"linguistic":[39],"prompts":[41],"encoded":[42],"using":[43,50],"pre-trained":[45],"LLM":[46],"and":[47,59,104,122,124,130,152,178,185,190],"visual":[48],"features":[49],"dual":[52],"attention":[53,63],"mechanism":[54],"strengthen":[56],"robustness":[58],"adaptability,":[60],"where":[61],"channel":[62],"blocks":[64],"are":[65,192],"fixed":[66],"within":[67],"multi-modality":[69],"feature":[70],"fusion":[71],"process.":[72],"The":[73],"experience":[74],"replay":[75],"strategy":[76],"is":[77],"further":[78],"proposed,":[79],"maintain":[81],"long-term":[82],"performance":[84],"periodically":[86],"refreshing":[87],"template":[90],"with":[91,166],"accumulated":[92],"experiences,":[93],"preventing":[94],"model":[96],"from":[97],"catastrophic":[98],"forgetting.":[99],"enables":[101],"both":[102],"vision-only":[103,125],"vision-language":[105,117],"tasks":[107],"share":[109],"same":[111],"parameters.":[112],"Through":[113],"extensive":[114],"experiments":[115],"on":[116,136,139,144,147,150,154],"data":[118,126],"sets":[119,127],"(TNL2k,":[120],"LaSOT":[121],"LaSOText)":[123],"(UAV123,":[128],"NfS":[129,151],"OTB100),":[131],"our":[132],"achieves":[134],"0.569":[135],"TNL2K,":[137],"0.628":[138],"challenging":[141,186],"LaSOT,":[142],"0.528":[143],"LaSOText,":[145],"0.646":[146],"UAV123,":[148],"0.603":[149],"0.718":[153],"OTB100":[155],"in":[156],"terms":[157],"Area":[160],"Under":[161],"Curve":[163],"(AUC)":[164],"metric":[165],"inference":[168],"speed":[169],"36.3":[171],"FPS.":[172],"normally":[174],"surpasses":[175],"state-of-theart":[176],"methods":[177],"shows":[179],"superior":[180],"generalization":[181],"ability":[182],"across":[183],"diverse":[184],"scenarios11The":[188],"code":[189],"models":[191],"available":[193],"athttps://indtlab.github.io/projects/SUSTTrack..":[194]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-11T00:00:00"}