{"id":"https://openalex.org/W4415428960","doi":"https://doi.org/10.3233/faia250829","title":"Memory Prompt for Multi-Modal Visual Object Tracking","display_name":"Memory Prompt for Multi-Modal Visual Object Tracking","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428960","doi":"https://doi.org/10.3233/faia250829"},"language":null,"primary_location":{"id":"doi:10.3233/faia250829","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250829","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia250829","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100453922","display_name":"Xueqi Li","orcid":"https://orcid.org/0000-0002-4825-6887"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xueqi Li","raw_affiliation_strings":["Academy of Military Science"],"affiliations":[{"raw_affiliation_string":"Academy of Military Science","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320371","display_name":"Yongjun Zhang","orcid":"https://orcid.org/0000-0002-1079-4137"},"institutions":[{"id":"https://openalex.org/I4210098863","display_name":"National Defense Institute","ror":"https://ror.org/013spkf41","country_code":"PT","type":"government","lineage":["https://openalex.org/I4210098863","https://openalex.org/I4210166979"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Yongjun Zhang","raw_affiliation_strings":["National Innovation Institute of Defense Technology"],"affiliations":[{"raw_affiliation_string":"National Innovation Institute of Defense Technology","institution_ids":["https://openalex.org/I4210098863"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071223948","display_name":"Jianqiang Xia","orcid":null},"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"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","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":false,"raw_author_name":"Fang Dong","raw_affiliation_strings":["College of Computer, National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054558662","display_name":"Yuanyuan Wang","orcid":"https://orcid.org/0000-0002-9705-4050"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanyuan Wang","raw_affiliation_strings":["Academy of Military Science"],"affiliations":[{"raw_affiliation_string":"Academy of Military Science","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089974506","display_name":"Yushe Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yushe Cao","raw_affiliation_strings":["School of computing, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"School of computing, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000367973","display_name":"Junze Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junze Zhang","raw_affiliation_strings":["Academy of Military Science"],"affiliations":[{"raw_affiliation_string":"Academy of Military Science","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019758816","display_name":"Dianxi Shi","orcid":"https://orcid.org/0000-0002-8112-371X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dianxi Shi","raw_affiliation_strings":["Academy of Military Science"],"affiliations":[{"raw_affiliation_string":"Academy of Military Science","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100453922"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.64735336,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9153000116348267,"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"}},"topics":[{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9153000116348267,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9010999798774719,"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/bittorrent-tracker","display_name":"BitTorrent tracker","score":0.7820000052452087},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4839000105857849},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4758000075817108},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.45829999446868896},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43880000710487366},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4120999872684479},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.40860000252723694},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.38449999690055847},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.36309999227523804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8148999810218811},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.7820000052452087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7355999946594238},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5710999965667725},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4839000105857849},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4758000075817108},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.45829999446868896},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43880000710487366},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4120999872684479},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.40860000252723694},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.38449999690055847},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.36309999227523804},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.2892000079154968},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.273499995470047},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia250829","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250829","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia250829","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250829","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"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":{"Multi-modal":[0],"trackers":[1,15,48],"have":[2],"drawn":[3],"widespread":[4],"attention":[5],"for":[6,63],"robust":[7],"tracking":[8,44,189,196],"in":[9,43],"challenging":[10],"scenarios.":[11],"However,":[12],"existing":[13],"multi-modal":[14,188],"often":[16],"rely":[17],"solely":[18],"on":[19],"spatial":[20],"matching":[21],"between":[22],"the":[23,28,56,131,147,161,169],"initial":[24,118],"target":[25,92,119],"template":[26],"and":[27,182,194],"search":[29],"regions,":[30],"or":[31,59,104],"incorporate":[32],"only":[33],"single-frame":[34],"historical":[35,91,123],"information,":[36],"failing":[37],"to":[38,126,145,165,168],"fully":[39],"exploit":[40],"temporal":[41,51,64,98,107,180],"correlations":[42],"sequences.":[45],"Additionally,":[46],"most":[47],"that":[49,87,159,175],"introduce":[50],"modeling":[52],"require":[53],"either":[54],"retraining":[55],"entire":[57],"network":[58,164],"designing":[60],"specialized":[61],"modules":[62],"feature":[65,102],"extraction,":[66],"which":[67],"incurs":[68],"additional":[69],"computational":[70,148],"costs.":[71],"To":[72],"alleviate":[73],"these":[74],"limitations,":[75],"inspired":[76],"by":[77],"human":[78],"visual":[79],"memory,":[80],"we":[81,153],"propose":[82],"MPTrack,":[83],"a":[84,155],"novel":[85],"tracker":[86],"directly":[88],"reuses":[89],"pre-extracted":[90],"features":[93],"as":[94],"memory":[95,124,157],"prompts,":[96],"establishing":[97],"dependencies":[99],"without":[100],"redundant":[101],"extraction":[103,108],"specially":[105],"designed":[106],"networks.":[109],"Our":[110],"proposed":[111],"Memory":[112],"Prompt":[113],"Fusion":[114],"module":[115],"effectively":[116,178],"combines":[117],"templates":[120],"with":[121],"multiple":[122],"cues":[125],"generate":[127],"enhanced":[128],"templates,":[129],"enabling":[130],"perception":[132],"of":[133,150],"long-term":[134],"appearance":[135],"dynamics":[136],"while":[137],"mitigating":[138],"potential":[139],"interference":[140],"from":[141],"individual":[142],"memory.":[143],"Simultaneously,":[144],"avoid":[146],"cost":[149],"full-model":[151],"training,":[152],"design":[154],"lightweight":[156],"adapter":[158],"allows":[160],"frozen":[162],"backbone":[163],"efficiently":[166],"adapt":[167],"memory-enhanced":[170],"template.":[171],"Extensive":[172],"experiments":[173],"demonstrate":[174],"our":[176],"method":[177],"incorporates":[179],"information":[181],"achieves":[183],"promising":[184],"results":[185],"across":[186],"different":[187],"scenarios,":[190],"including":[191],"RGB+Thermal,":[192],"RGB+Event,":[193],"RGB+Depth":[195],"tasks.":[197]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}