{"id":"https://openalex.org/W4409257348","doi":"https://doi.org/10.1109/tai.2025.3558482","title":"Adaptive Perception for Unified Visual Multimodal Object Tracking","display_name":"Adaptive Perception for Unified Visual Multimodal Object Tracking","publication_year":2025,"publication_date":"2025-04-08","ids":{"openalex":"https://openalex.org/W4409257348","doi":"https://doi.org/10.1109/tai.2025.3558482"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2025.3558482","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2025.3558482","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102797916","display_name":"Xiantao Hu","orcid":"https://orcid.org/0009-0007-1541-1717"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiantao Hu","raw_affiliation_strings":["Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","Key Laboratory of Education Blockchain, Guangxi Normal University, Guilin, China"],"raw_orcid":"https://orcid.org/0009-0007-1541-1717","affiliations":[{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]},{"raw_affiliation_string":"Key Laboratory of Education Blockchain, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bineng Zhong","orcid":"https://orcid.org/0000-0002-4387-407X"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bineng Zhong","raw_affiliation_strings":["Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","Key Laboratory of Education Blockchain, Guangxi Normal University, Guilin, China"],"raw_orcid":"https://orcid.org/0000-0002-4387-407X","affiliations":[{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]},{"raw_affiliation_string":"Key Laboratory of Education Blockchain, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049287545","display_name":"Qihua Liang","orcid":"https://orcid.org/0000-0003-2353-5246"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qihua Liang","raw_affiliation_strings":["Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","Key Laboratory of Education Blockchain, Guangxi Normal University, Guilin, China"],"raw_orcid":"https://orcid.org/0000-0003-2353-5246","affiliations":[{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]},{"raw_affiliation_string":"Key Laboratory of Education Blockchain, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046443025","display_name":"Liangtao Shi","orcid":"https://orcid.org/0009-0003-5934-8837"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangtao Shi","raw_affiliation_strings":["Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","Key Laboratory of Education Blockchain, Guangxi Normal University, Guilin, China"],"raw_orcid":"https://orcid.org/0009-0003-5934-8837","affiliations":[{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]},{"raw_affiliation_string":"Key Laboratory of Education Blockchain, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019827327","display_name":"Zhiyi Mo","orcid":"https://orcid.org/0009-0008-6123-363X"},"institutions":[{"id":"https://openalex.org/I4210107865","display_name":"Wuzhou University","ror":"https://ror.org/01vv37n49","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210107865"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyi Mo","raw_affiliation_strings":["School of Data Science and Software Engineering, Wuzhou University, Wuzhou, China","School of Data Science, Wuzhou University, Wuzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-6123-363X","affiliations":[{"raw_affiliation_string":"School of Data Science and Software Engineering, Wuzhou University, Wuzhou, China","institution_ids":["https://openalex.org/I4210107865"]},{"raw_affiliation_string":"School of Data Science, Wuzhou University, Wuzhou, China","institution_ids":["https://openalex.org/I4210107865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029021362","display_name":"Ying Tai","orcid":"https://orcid.org/0000-0002-4665-6852"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Tai","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4665-6852","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Suzhou, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jian Yang","orcid":"https://orcid.org/0000-0003-4800-832X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","School of Computer Science, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4800-832X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"School of Computer Science, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5102797916"],"corresponding_institution_ids":["https://openalex.org/I29739308"],"apc_list":null,"apc_paid":null,"fwci":11.3325,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.98548673,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"6","issue":"10","first_page":"2819","last_page":"2829"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9833999872207642,"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":0.9833999872207642,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9606000185012817,"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":0.9596999883651733,"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/modal","display_name":"Modal","score":0.6819963455200195},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6496554613113403},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.566897988319397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5644100904464722},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5511611104011536},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5467610955238342},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5235114693641663},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5083052515983582},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.4592052102088928},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.24249160289764404},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.05753323435783386}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6819963455200195},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6496554613113403},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.566897988319397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5644100904464722},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5511611104011536},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5467610955238342},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5235114693641663},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5083052515983582},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.4592052102088928},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.24249160289764404},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.05753323435783386},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2025.3558482","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2025.3558482","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W2130026429","https://openalex.org/W2765667535","https://openalex.org/W2794744029","https://openalex.org/W2891033863","https://openalex.org/W2898200825","https://openalex.org/W2962766617","https://openalex.org/W2963351448","https://openalex.org/W2963905288","https://openalex.org/W3158472981","https://openalex.org/W3183152796","https://openalex.org/W3214586131","https://openalex.org/W4214737929","https://openalex.org/W4214759957","https://openalex.org/W4289535600","https://openalex.org/W4304098539","https://openalex.org/W4312323989","https://openalex.org/W4312504063","https://openalex.org/W4312532041","https://openalex.org/W4312751983","https://openalex.org/W4312771325","https://openalex.org/W4312805142","https://openalex.org/W4312872160","https://openalex.org/W4313046728","https://openalex.org/W4313839160","https://openalex.org/W4382119472","https://openalex.org/W4382240192","https://openalex.org/W4386066081","https://openalex.org/W4386066459","https://openalex.org/W4386071707","https://openalex.org/W4386075603","https://openalex.org/W4386075647","https://openalex.org/W4386076209","https://openalex.org/W4387587572","https://openalex.org/W4387717805","https://openalex.org/W4389104919","https://openalex.org/W4393149992","https://openalex.org/W4393154017","https://openalex.org/W4393154934","https://openalex.org/W4393159185","https://openalex.org/W4396598146","https://openalex.org/W4399151664","https://openalex.org/W4400912592","https://openalex.org/W4402592965","https://openalex.org/W4402704627","https://openalex.org/W4402715800","https://openalex.org/W4402727444","https://openalex.org/W4402753948","https://openalex.org/W4402754150","https://openalex.org/W4402979808","https://openalex.org/W4403758852","https://openalex.org/W4405003157","https://openalex.org/W4405286952","https://openalex.org/W4409366577","https://openalex.org/W4409367071","https://openalex.org/W4409367158","https://openalex.org/W4409368360","https://openalex.org/W4409368393","https://openalex.org/W4409369928","https://openalex.org/W4413010666","https://openalex.org/W4413156100"],"related_works":["https://openalex.org/W2084086966","https://openalex.org/W4285271403","https://openalex.org/W2542007731","https://openalex.org/W2968379562","https://openalex.org/W2091015105","https://openalex.org/W4388689193","https://openalex.org/W2110899030","https://openalex.org/W29633852","https://openalex.org/W2985362983","https://openalex.org/W4327670844"],"abstract_inverted_index":{"Recently,":[0],"many":[1],"multi-modal":[2,19,63,79,139,156,165],"trackers":[3,157,161],"prioritize":[4],"RGB":[5],"as":[6,13],"the":[7,27,48,98],"dominant":[8],"modality,":[9],"treating":[10],"other":[11],"modalities":[12,105],"auxiliary,":[14],"and":[15,106,145],"fine-tuning":[16,111],"separately":[17],"various":[18,62,104],"tasks.":[20,65,114,166],"This":[21,95],"imbalance":[22],"in":[23,39,61],"modality":[24,38,121],"dependence":[25],"limits":[26],"ability":[28],"of":[29,50],"methods":[30],"to":[31,45,100,103],"dynamically":[32,101],"utilize":[33],"complementary":[34],"information":[35],"from":[36],"each":[37],"complex":[40],"scenarios,":[41],"making":[42],"it":[43],"challenging":[44],"fully":[46],"perceive":[47],"advantages":[49],"multi-modal.":[51],"As":[52],"a":[53,55,73,87],"result,":[54],"unified":[56,75,88,155],"parameter":[57],"model":[58,99],"often":[59],"underperforms":[60],"tracking":[64],"To":[66],"address":[67],"this":[68],"issue,":[69],"we":[70],"propose":[71],"APTrack,":[72],"novel":[74],"tracker":[76,117],"designed":[77,162],"for":[78,163],"adaptive":[80,120],"perception.":[81],"Unlike":[82],"previous":[83],"methods,":[84],"APTrack":[85,149],"explores":[86],"representation":[89],"through":[90],"an":[91,119],"equal":[92],"modeling":[93],"strategy.":[94],"strategy":[96],"allows":[97],"adapt":[102],"tasks":[107],"without":[108],"requiring":[109],"additional":[110],"between":[112],"different":[113],"Moreover,":[115],"our":[116],"integrates":[118],"interaction":[122],"(AMI)":[123],"module":[124],"that":[125,148],"efficiently":[126],"bridges":[127],"cross-modality":[128],"interactions":[129],"by":[130],"generating":[131],"learnable":[132],"tokens.":[133],"Experiments":[134],"conducted":[135],"on":[136],"five":[137],"diverse":[138],"datasets":[140],"(RGBT234,":[141],"LasHeR,":[142],"VisEvent,":[143],"DepthTrack,":[144],"VOT-RGBD2022)":[146],"demonstrate":[147],"not":[150],"only":[151],"surpasses":[152],"existing":[153],"state-of-the-art":[154],"but":[158],"also":[159],"outperforms":[160],"specific":[164]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}