{"id":"https://openalex.org/W4400668214","doi":"https://doi.org/10.1145/3678176","title":"Multi-Level Fusion for Robust RGBT Tracking via Enhanced Thermal Representation","display_name":"Multi-Level Fusion for Robust RGBT Tracking via Enhanced Thermal Representation","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4400668214","doi":"https://doi.org/10.1145/3678176"},"language":"en","primary_location":{"id":"doi:10.1145/3678176","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3678176","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5074731752","display_name":"Zhangyong Tang","orcid":"https://orcid.org/0000-0001-8187-9384"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhangyong Tang","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049469328","display_name":"Tianyang Xu","orcid":"https://orcid.org/0000-0002-9015-3128"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyang Xu","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103810189","display_name":"Xiao-Jun Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Jun Wu","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028209738","display_name":"Josef Kittler","orcid":"https://orcid.org/0000-0002-8110-9205"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Josef Kittler","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5074731752"],"corresponding_institution_ids":["https://openalex.org/I111599522"],"apc_list":null,"apc_paid":null,"fwci":3.4644,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.93803419,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"20","issue":"10","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9998999834060669,"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":0.9998999834060669,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9952999949455261,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/fusion","display_name":"Fusion","score":0.7069459557533264},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6101488471031189},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.49040770530700684},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4787099361419678},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4529378414154053},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4027111530303955},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09576788544654846},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.04438355565071106}],"concepts":[{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.7069459557533264},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6101488471031189},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.49040770530700684},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4787099361419678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4529378414154053},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4027111530303955},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09576788544654846},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.04438355565071106},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3678176","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3678176","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2619132863","display_name":null,"funder_award_id":"62020106012, 62332008, 62106089, U1836218, 62336004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4770326006","display_name":null,"funder_award_id":"EP/N007743/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G764753648","display_name":null,"funder_award_id":"EP/R018456/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1857884451","https://openalex.org/W2152887597","https://openalex.org/W2194775991","https://openalex.org/W2470394683","https://openalex.org/W2527415613","https://openalex.org/W2558899534","https://openalex.org/W2754279782","https://openalex.org/W2765667535","https://openalex.org/W2794744029","https://openalex.org/W2805902878","https://openalex.org/W2888456413","https://openalex.org/W2938696568","https://openalex.org/W2963188742","https://openalex.org/W2963905288","https://openalex.org/W2964423614","https://openalex.org/W2969871771","https://openalex.org/W2988310840","https://openalex.org/W2996575194","https://openalex.org/W2997131652","https://openalex.org/W2997248655","https://openalex.org/W2998027361","https://openalex.org/W2998756268","https://openalex.org/W3002567850","https://openalex.org/W3005080107","https://openalex.org/W3012425959","https://openalex.org/W3035020406","https://openalex.org/W3035571898","https://openalex.org/W3064498204","https://openalex.org/W3099671582","https://openalex.org/W3099681648","https://openalex.org/W3101990647","https://openalex.org/W3110562975","https://openalex.org/W3127317646","https://openalex.org/W3132864630","https://openalex.org/W3153607844","https://openalex.org/W3158472981","https://openalex.org/W3171106688","https://openalex.org/W3183904268","https://openalex.org/W3187284461","https://openalex.org/W3214586131","https://openalex.org/W4214872590","https://openalex.org/W4226089683","https://openalex.org/W4226126595","https://openalex.org/W4242177601","https://openalex.org/W4283808043","https://openalex.org/W4287556358","https://openalex.org/W4297811796","https://openalex.org/W4306907926","https://openalex.org/W4312532041","https://openalex.org/W4312751983","https://openalex.org/W4312796324","https://openalex.org/W4319934144","https://openalex.org/W4361003656","https://openalex.org/W4372342213","https://openalex.org/W4376131895","https://openalex.org/W4376647170","https://openalex.org/W4380884766","https://openalex.org/W4382240192","https://openalex.org/W4386075603","https://openalex.org/W4386075647","https://openalex.org/W4392058084","https://openalex.org/W4393154017","https://openalex.org/W4393154934"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Due":[0],"to":[1,115,169,199],"the":[2,17,34,39,60,73,85,100,119,129,140,147,158,178,191,200],"limitations":[3],"of":[4,77,87,142,146,202,208],"visible":[5],"(RGB)":[6],"sensors":[7],"in":[8,45,68],"challenging":[9,222],"scenarios,":[10],"such":[11],"as":[12,25],"nighttime":[13],"and":[14,41,57,79,105,121,180,216],"foggy":[15],"environments,":[16],"thermal":[18,91,149],"infrared":[19],"(TIR)":[20],"modality":[21,101],"draws":[22],"increasing":[23],"attention":[24],"an":[26,106],"auxiliary":[27],"source":[28],"for":[29,90,112,185],"robust":[30],"tracking":[31],"systems.":[32],"Currently,":[33],"existing":[35],"methods":[36],"extract":[37],"both":[38,177],"RGB":[40,78],"TIR":[42,80,113,130,135],"(RGBT)":[43],"clues":[44],"a":[46,64,69,151,170,186],"similar":[47],"approach,":[48],"i.e.,":[49],"utilising":[50],"RGB-pretrained":[51,88],"models":[52,89],"with":[53,133,139],"or":[54],"without":[55],"finetuning,":[56],"then":[58],"aggregate":[59],"multi-modal":[61,203],"information":[62],"through":[63],"fusion":[65,153,162,174,188,193],"block":[66],"embedded":[67],"single":[70],"level.":[71],"However,":[72],"different":[74,165],"imaging":[75],"principles":[76],"data":[81,114,136],"raise":[82],"questions":[83],"about":[84],"suitability":[86],"data.":[92],"In":[93],"this":[94],"article,":[95],"it":[96],"is":[97,103,110,125,155,195,211],"argued":[98],"that":[99,160],"gap":[102],"overlooked,":[104],"alternative":[107],"training":[108,120],"paradigm":[109],"proposed":[111],"ensure":[116],"consistency":[117],"between":[118],"test":[122],"data,":[123],"which":[124],"achieved":[126],"by":[127,157,213],"optimising":[128],"feature":[131,179],"extractor":[132],"only":[134],"involved.":[137],"Furthermore,":[138],"goal":[141],"making":[143],"better":[144,171],"use":[145],"enhanced":[148],"representations,":[150],"multi-level":[152],"strategy":[154,194],"inspired":[156],"observation":[159],"various":[161],"strategies":[163],"at":[164,176,228],"levels":[166,182],"can":[167],"contribute":[168],"performance.":[172],"Specifically,":[173],"modules":[175],"decision":[181],"are":[183],"derived":[184],"comprehensive":[187],"procedure":[189],"while":[190],"pixel-level":[192],"not":[196],"considered":[197],"due":[198],"misalignment":[201],"image":[204],"pairs.":[205],"The":[206],"effectiveness":[207],"our":[209],"method":[210],"demonstrated":[212],"extensive":[214],"qualitative":[215],"quantitative":[217],"experiments":[218],"conducted":[219],"on":[220],"several":[221],"benchmarks.":[223],"Code":[224],"will":[225],"be":[226],"released":[227],"https://github.com/Zhangyong-Tang/MELT":[229],".":[230]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}
