{"id":"https://openalex.org/W4415708718","doi":"https://doi.org/10.1109/icme59968.2025.11209195","title":"IMTrack: Interlayer Interoperability and Multi-scene Optimization for Visual Multimodal Target Tracking","display_name":"IMTrack: Interlayer Interoperability and Multi-scene Optimization for Visual Multimodal Target Tracking","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708718","doi":"https://doi.org/10.1109/icme59968.2025.11209195"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5046553417","display_name":"Rui Zhu","orcid":"https://orcid.org/0000-0002-6114-6412"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhu","raw_affiliation_strings":["Yunnan University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yunnan University,China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113990942","display_name":"Zhehao Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaokang Lu","raw_affiliation_strings":["Yunnan University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yunnan University,China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101582907","display_name":"Bohan Liu","orcid":"https://orcid.org/0000-0002-4810-8374"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bohan Liu","raw_affiliation_strings":["Yunnan University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yunnan University,China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675701","display_name":"Yun Yang","orcid":"https://orcid.org/0000-0002-9893-3436"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Yang","raw_affiliation_strings":["Yunnan University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yunnan University,China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005903391","display_name":"Yue Hua","orcid":"https://orcid.org/0000-0003-0728-9591"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hua Yue","raw_affiliation_strings":["KSEC Intelligent Technology Co.. Ltd,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KSEC Intelligent Technology Co.. Ltd,China","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004740349","display_name":"Chaogang Wang","orcid":"https://orcid.org/0000-0002-2207-3732"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaogang Wang","raw_affiliation_strings":["Yunnan University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yunnan University,China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zixin Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixin Zhou","raw_affiliation_strings":["Yunnan University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yunnan University,China","institution_ids":["https://openalex.org/I189210763"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9000999927520752,"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":0.9000999927520752,"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":0.026599999517202377,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.011900000274181366,"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":0.7656000256538391},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5407999753952026},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.39340001344680786},{"id":"https://openalex.org/keywords/interoperability","display_name":"Interoperability","score":0.38109999895095825},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.34360000491142273},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.34290000796318054},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.33660000562667847},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.3100000023841858}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7717000246047974},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7656000256538391},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5788999795913696},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5407999753952026},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41370001435279846},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.39340001344680786},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.38109999895095825},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.367900013923645},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.33660000562667847},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32100000977516174},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.3100000023841858},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2734000086784363},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2963905288","https://openalex.org/W3012425959","https://openalex.org/W3035020406","https://openalex.org/W3110562975","https://openalex.org/W3132864630","https://openalex.org/W3158472981","https://openalex.org/W3209993199","https://openalex.org/W4214689917","https://openalex.org/W4214737929","https://openalex.org/W4283808043","https://openalex.org/W4304098539","https://openalex.org/W4312751983","https://openalex.org/W4313156423","https://openalex.org/W4320036905","https://openalex.org/W4382240192","https://openalex.org/W4386075647","https://openalex.org/W4387587572","https://openalex.org/W4390874204","https://openalex.org/W4393154934","https://openalex.org/W4402727444","https://openalex.org/W4402753948","https://openalex.org/W4402754293"],"related_works":[],"abstract_inverted_index":{"In":[0],"the":[1,26,47,139,159],"domain":[2],"of":[3,28,49,141,161],"target":[4],"tracking,":[5],"leveraging":[6],"auxiliary":[7,105,165],"modalities":[8,59],"such":[9],"as":[10,63],"depth,":[11],"thermal,":[12],"and":[13,99,104,108,116],"event":[14],"data":[15],"to":[16,25,39,51,76,112,127,164],"enhance":[17,128],"tracking":[18],"robustness":[19,129,160],"has":[20],"garnered":[21],"substantial":[22],"attention.":[23],"Due":[24],"scarcity":[27],"visual":[29,87],"multimodal":[30,88],"datasets,":[31,53],"state-of-the-art":[32,156],"approaches":[33],"primarily":[34],"rely":[35],"on":[36,57,135],"parameter-efficient":[37],"fine-tuning":[38,50,102],"adapt":[40],"models.":[41],"However,":[42],"existing":[43,150],"studies":[44],"often":[45],"neglect":[46],"adaptation":[48,75],"specific":[52],"frequently":[54],"focusing":[55],"only":[56],"non-RGB":[58],"or":[60],"employing":[61],"them":[62],"prompts.":[64],"Additionally,":[65],"current":[66],"methods":[67,151],"overly":[68],"emphasize":[69],"modal":[70],"balance":[71],"while":[72],"disregarding":[73],"modality":[74],"environmental":[77],"conditions.":[78],"To":[79],"address":[80],"these":[81],"limitations,":[82],"we":[83,119],"propose":[84],"a":[85,121],"unified":[86],"detection":[89],"framework":[90],"named":[91],"IMTrack.":[92],"This":[93],"model":[94,163],"incorporates":[95],"LoRA":[96],"(Low-Rank":[97],"Adaptation)":[98],"Adapter":[100],"for":[101],"RGB":[103],"modalities,":[106],"respectively,":[107],"employs":[109],"confidence-based":[110],"cross-attention":[111],"strengthen":[113],"feature":[114],"interaction":[115],"adaptability.":[117],"Furthermore,":[118],"introduce":[120],"complementary":[122],"masking":[123],"multi-scene":[124],"optimization":[125],"strategy":[126],"in":[130,152],"complex":[131],"environments.":[132],"Extensive":[133],"experiments":[134],"five":[136],"datasets":[137],"validate":[138],"efficacy":[140],"our":[142,162],"model.":[143],"The":[144],"results":[145],"demonstrate":[146],"that":[147],"IMTrack":[148],"surpasses":[149],"many":[153],"indicators,":[154],"achieving":[155],"performance.":[157],"Notably,":[158],"modes":[166],"is":[167,176],"improved":[168],"by":[169],"more":[170],"than":[171],"2%.":[172],"Our":[173],"source":[174],"code":[175],"available":[177],"at:":[178],"https://github.com/cxy-lzk/IMTrack.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}