{"id":"https://openalex.org/W7138363513","doi":"https://doi.org/10.1609/aaai.v40i13.38079","title":"Unaligned UAV RGBT Tracking: A Largescale Benchmark and a Novel Approach","display_name":"Unaligned UAV RGBT Tracking: A Largescale Benchmark and a Novel Approach","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138363513","doi":"https://doi.org/10.1609/aaai.v40i13.38079"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i13.38079","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38079","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i13.38079","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129681626","display_name":"Yun Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yun Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129707015","display_name":"Yuhang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070909695","display_name":"Jiandong Jin","orcid":"https://orcid.org/0000-0001-7829-7164"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiandong Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129702565","display_name":"Wankang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wankang Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129694609","display_name":"Chenglong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenglong Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"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":0.64458689,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"13","first_page":"11014","last_page":"11022"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.8066999912261963,"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":0.8066999912261963,"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/T11133","display_name":"UAV Applications and Optimization","score":0.08590000122785568,"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"}},{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.037700001150369644,"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":0.6305000185966492},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.5504999756813049},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4828000068664551},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.47999998927116394},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.47040000557899475},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.46560001373291016},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.4366999864578247},{"id":"https://openalex.org/keywords/bittorrent-tracker","display_name":"BitTorrent tracker","score":0.41769999265670776},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4124999940395355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8073999881744385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6685000061988831},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6305000185966492},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6266999840736389},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.5504999756813049},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4828000068664551},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.47999998927116394},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47040000557899475},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.46560001373291016},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4366999864578247},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.41769999265670776},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29829999804496765},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.29589998722076416},{"id":"https://openalex.org/C154586513","wikidata":"https://www.wikidata.org/wiki/Q4420972","display_name":"Tracking system","level":3,"score":0.2824999988079071},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.25690001249313354},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i13.38079","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38079","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/38079","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/38079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i13.38079","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38079","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,5,38,69,79,90,134,143,152,171,200,205],"rapid":[2],"development":[3,93],"of":[4,94,102,136,163],"low-altitude":[6],"economy,":[7],"multimodal":[8,195],"visual":[9],"tracking":[10,44,59,76,155,212,223],"in":[11,32,61,147,219],"UAV":[12,62,74,148,222],"scenarios":[13],"has":[14],"attracted":[15],"extensive":[16],"attention.":[17],"UAVs":[18],"are":[19],"typically":[20],"equipped":[21],"with":[22,106],"independent":[23],"visible":[24],"(RGB)":[25],"and":[26,77,84,92,112,121,180,184,193,217],"thermal":[27],"infrared":[28],"(TIR)":[29],"sensors,":[30],"resulting":[31],"an":[33],"inherent":[34],"spatial":[35,123,144,172],"misalignment":[36,124,145],"between":[37],"two":[39,175],"modalities.":[40],"However,":[41],"existing":[42,137,210],"RGBT":[43,58,75,104,154],"methods":[45,138],"generally":[46],"rely":[47],"on":[48,199],"spatially":[49],"aligned":[50],"data":[51],"inputs,":[52],"making":[53],"them":[54],"unsuitable":[55],"for":[56,190],"unaligned":[57,73,82,221],"task":[60,71],"scenarios.":[63,131,224],"In":[64,157],"this":[65,95],"work,":[66],"we":[67,150,159],"introduce":[68],"new":[70],"called":[72],"construct":[78],"first":[80],"large-scale":[81],"RGB":[83],"TIR":[85],"video":[86],"dataset":[87,98,202],"to":[88,126,141,168,187],"promote":[89],"research":[91],"field.":[96],"The":[97],"contains":[99],"1,453":[100],"pairs":[101],"UAV-captured":[103],"sequences":[105],"precise":[107],"dual-modal":[108],"bounding":[109],"box":[110],"annotations,":[111],"covers":[113],"42":[114],"object":[115],"categories,":[116],"22":[117],"typical":[118],"challenge":[119],"attributes,":[120],"diverse":[122],"scales":[125],"better":[127],"simulate":[128],"real-world":[129,220],"challenging":[130],"To":[132],"address":[133],"limitations":[135],"that":[139,204],"fail":[140],"handle":[142],"issue":[146],"scenarios,":[149],"propose":[151],"novel":[153],"approach.":[156],"particular,":[158],"design":[160],"a":[161,181],"mixture":[162],"shift":[164],"estimation":[165],"experts":[166],"module":[167,186],"adaptively":[169],"estimate":[170],"shifts":[173],"across":[174],"modalities":[176],"at":[177],"different":[178],"scales,":[179],"cross-modal":[182],"alignment":[183],"fusion":[185],"further":[188],"compensate":[189],"nonlinear":[191],"deformations":[192],"integrate":[194],"information.":[196],"Extensive":[197],"experiments":[198],"created":[201],"demonstrate":[203],"proposed":[206],"tracker":[207],"significantly":[208],"outperforms":[209],"state-of-the-art":[211],"methods,":[213],"validating":[214],"its":[215],"practicality":[216],"robustness":[218]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}