{"id":"https://openalex.org/W4416748736","doi":"https://doi.org/10.1109/tip.2025.3635483","title":"Quality-Aware Spatio-Temporal Transformer Network for RGBT Tracking","display_name":"Quality-Aware Spatio-Temporal Transformer Network for RGBT Tracking","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416748736","doi":"https://doi.org/10.1109/tip.2025.3635483","pmid":"https://pubmed.ncbi.nlm.nih.gov/41308105"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2025.3635483","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3635483","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5114336034","display_name":"Zhaodong Ding","orcid":"https://orcid.org/0009-0001-5642-7869"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaodong Ding","raw_affiliation_strings":["School of Artificial Intelligence, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, China","School of Artificial Intelligence, State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0001-5642-7869","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]},{"raw_affiliation_string":"School of Artificial Intelligence, State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398932","display_name":"Chenglong Li","orcid":"https://orcid.org/0000-0002-7233-2739"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglong Li","raw_affiliation_strings":["School of Artificial Intelligence, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, China","School of Artificial Intelligence, State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-7233-2739","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]},{"raw_affiliation_string":"School of Artificial Intelligence, State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453705","display_name":"Tao Wang","orcid":"https://orcid.org/0000-0003-4200-3712"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Wang","raw_affiliation_strings":["School of Artificial Intelligence, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, China","School of Artificial Intelligence, State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]},{"raw_affiliation_string":"School of Artificial Intelligence, State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073752594","display_name":"Futian Wang","orcid":"https://orcid.org/0000-0003-4181-8485"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Futian Wang","raw_affiliation_strings":["School of Computer Science and Technology, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-4181-8485","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9349,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.81432337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"34","issue":null,"first_page":"7845","last_page":"7858"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.909500002861023,"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":0.909500002861023,"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":0.015300000086426735,"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":0.007899999618530273,"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/security-token","display_name":"Security token","score":0.8248999714851379},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5929999947547913},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5404999852180481},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5067999958992004},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.492000013589859},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.48159998655319214},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45719999074935913},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.451200008392334},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41350001096725464}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.8248999714851379},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7738999724388123},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5929999947547913},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5404999852180481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5213000178337097},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5067999958992004},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.492000013589859},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.48159998655319214},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45719999074935913},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.451200008392334},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.3440000116825104},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C2780092901","wikidata":"https://www.wikidata.org/wiki/Q3433612","display_name":"Correlation coefficient","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C77246614","wikidata":"https://www.wikidata.org/wiki/Q1409400","display_name":"Gramian matrix","level":3,"score":0.26649999618530273},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.25920000672340393},{"id":"https://openalex.org/C3020028006","wikidata":"https://www.wikidata.org/wiki/Q9158","display_name":"Electronic mail","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2025.3635483","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3635483","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:41308105","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41308105","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5856189220","display_name":null,"funder_award_id":"62572004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G845944294","display_name":null,"funder_award_id":"62376004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":39,"referenced_works":["https://openalex.org/W2527415613","https://openalex.org/W2555361934","https://openalex.org/W2765667535","https://openalex.org/W2922509574","https://openalex.org/W2963905288","https://openalex.org/W2996575194","https://openalex.org/W2997131652","https://openalex.org/W2998756268","https://openalex.org/W3012425959","https://openalex.org/W3099671582","https://openalex.org/W3101990647","https://openalex.org/W3110562975","https://openalex.org/W3158472981","https://openalex.org/W3183152796","https://openalex.org/W4283808043","https://openalex.org/W4286974493","https://openalex.org/W4304098539","https://openalex.org/W4312668764","https://openalex.org/W4312751983","https://openalex.org/W4386066081","https://openalex.org/W4386066394","https://openalex.org/W4386066459","https://openalex.org/W4386075603","https://openalex.org/W4386075647","https://openalex.org/W4386083135","https://openalex.org/W4387969861","https://openalex.org/W4393147957","https://openalex.org/W4393148493","https://openalex.org/W4393154934","https://openalex.org/W4393159185","https://openalex.org/W4398765815","https://openalex.org/W4400447303","https://openalex.org/W4402702990","https://openalex.org/W4402704627","https://openalex.org/W4402727444","https://openalex.org/W4402753948","https://openalex.org/W4402754150","https://openalex.org/W4406955142","https://openalex.org/W4409367071"],"related_works":[],"abstract_inverted_index":{"Transformer-based":[0],"RGBT":[1,85,219],"tracking":[2,234],"has":[3],"attracted":[4],"much":[5],"attention":[6,15,18,21,148],"due":[7],"to":[8,28,71,131,188,202,231],"the":[9,24,55,65,73,92,106,115,123,133,142,147,151,158,165,174,179,196,209,224],"strong":[10],"modeling":[11],"capacity":[12],"of":[13,58,76,97,108,126,136,150,182,211],"self":[14],"and":[16,100,112,128,157,162,238],"cross":[17],"mechanisms.":[19],"These":[20],"mechanisms":[22],"utilize":[23,203],"correlations":[25],"among":[26],"tokens":[27,59,70,78,96,103,130,153,184],"construct":[29],"powerful":[30],"feature":[31,81],"representations,":[32,82],"but":[33],"are":[34,241],"easily":[35],"affected":[36],"by":[37],"low-quality":[38,77,137,212],"tokens.":[39,138,191],"To":[40],"address":[41],"this":[42],"issue,":[43],"we":[44,89,140,194],"propose":[45,195],"a":[46],"novel":[47],"Quality-aware":[48,116],"Spatio-temporal":[49,198],"Transformer":[50],"Network":[51],"(QSTNet),":[52],"which":[53,177],"calculates":[54],"quality":[56,107,166],"weights":[57],"in":[60,79],"search":[61,95,110,127,152,170,183],"regions":[62],"based":[63,121,172],"on":[64,122,173,217],"correlation":[66,93,124,181],"with":[67],"multimodal":[68,101,159,189,205],"template":[69,102,129,160,190],"suppress":[72,132],"negative":[74,134],"effects":[75,135],"spatio-temporal":[80,204,213],"for":[83,168],"robust":[84],"tracking.":[86],"In":[87,192],"particular,":[88],"argue":[90],"that":[91,223],"between":[94],"one":[98],"modality":[99],"could":[104],"reflect":[105],"these":[109],"tokens,":[111,161],"thus":[113],"design":[114],"Token":[117],"Weighting":[118],"Module":[119,200],"(QTWM)":[120],"matrix":[125,144],"Specifically,":[139],"calculate":[141],"difference":[143,175],"derived":[145],"from":[146,154,185],"matrices":[149],"both":[155],"modalities":[156,187],"then":[163],"assign":[164],"weight":[167],"each":[169],"token":[171],"matrix,":[176],"reflects":[178],"relative":[180],"different":[186],"addition,":[193],"Prompt-based":[197],"Encoder":[199],"(PSEM)":[201],"information":[206],"while":[207],"alleviating":[208],"impact":[210],"features.":[214],"Extensive":[215],"experiments":[216],"four":[218],"benchmark":[220],"datasets":[221],"demonstrate":[222],"proposed":[225],"QSTNet":[226],"exhibits":[227],"superior":[228],"performance":[229],"compared":[230],"other":[232],"state-of-the-art":[233],"methods.":[235],"Our":[236],"code":[237],"supplementary":[239],"video":[240],"now":[242],"available:":[243],"https://zhaodongah.github.io/QSTNet.":[244]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}