{"id":"https://openalex.org/W4407737370","doi":"https://doi.org/10.1109/whispers65427.2024.10876537","title":"Spectral-Enhanced Transformers: Leveraging Large-Scale Pretrained Models for Hyperspectral Object Tracking","display_name":"Spectral-Enhanced Transformers: Leveraging Large-Scale Pretrained Models for Hyperspectral Object Tracking","publication_year":2024,"publication_date":"2024-12-09","ids":{"openalex":"https://openalex.org/W4407737370","doi":"https://doi.org/10.1109/whispers65427.2024.10876537"},"language":"en","primary_location":{"id":"doi:10.1109/whispers65427.2024.10876537","is_oa":false,"landing_page_url":"https://doi.org/10.1109/whispers65427.2024.10876537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 14th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS)","raw_type":"proceedings-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/A5015209051","display_name":"Shaheer Mohamed","orcid":"https://orcid.org/0009-0000-8775-7441"},"institutions":[{"id":"https://openalex.org/I2802348851","display_name":"Vision Australia","ror":"https://ror.org/05vje5x10","country_code":"AU","type":"nonprofit","lineage":["https://openalex.org/I2802348851"]},{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Shaheer Mohamed","raw_affiliation_strings":["Signal Processing, Artificial Intelligence and Vision Technologies, Queensland University of Technology,Brisbane,Australia"],"affiliations":[{"raw_affiliation_string":"Signal Processing, Artificial Intelligence and Vision Technologies, Queensland University of Technology,Brisbane,Australia","institution_ids":["https://openalex.org/I2802348851","https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000736425","display_name":"Tharindu Fernando","orcid":"https://orcid.org/0000-0002-6935-1816"},"institutions":[{"id":"https://openalex.org/I2802348851","display_name":"Vision Australia","ror":"https://ror.org/05vje5x10","country_code":"AU","type":"nonprofit","lineage":["https://openalex.org/I2802348851"]},{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tharindu Fernando","raw_affiliation_strings":["Signal Processing, Artificial Intelligence and Vision Technologies, Queensland University of Technology,Brisbane,Australia"],"affiliations":[{"raw_affiliation_string":"Signal Processing, Artificial Intelligence and Vision Technologies, Queensland University of Technology,Brisbane,Australia","institution_ids":["https://openalex.org/I2802348851","https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055128383","display_name":"Sridha Sridharan","orcid":"https://orcid.org/0000-0003-4316-9001"},"institutions":[{"id":"https://openalex.org/I2802348851","display_name":"Vision Australia","ror":"https://ror.org/05vje5x10","country_code":"AU","type":"nonprofit","lineage":["https://openalex.org/I2802348851"]},{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sridha Sridharan","raw_affiliation_strings":["Signal Processing, Artificial Intelligence and Vision Technologies, Queensland University of Technology,Brisbane,Australia"],"affiliations":[{"raw_affiliation_string":"Signal Processing, Artificial Intelligence and Vision Technologies, Queensland University of Technology,Brisbane,Australia","institution_ids":["https://openalex.org/I2802348851","https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008586469","display_name":"Peyman Moghadam","orcid":"https://orcid.org/0000-0002-8169-3560"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"funder","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Peyman Moghadam","raw_affiliation_strings":["Robotics and Autonomous Systems, Data61, CSIRO,Brisbane,QLD,Australia"],"affiliations":[{"raw_affiliation_string":"Robotics and Autonomous Systems, Data61, CSIRO,Brisbane,QLD,Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I1292875679"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034095159","display_name":"Clinton Fookes","orcid":"https://orcid.org/0000-0002-8515-6324"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]},{"id":"https://openalex.org/I2802348851","display_name":"Vision Australia","ror":"https://ror.org/05vje5x10","country_code":"AU","type":"nonprofit","lineage":["https://openalex.org/I2802348851"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Clinton Fookes","raw_affiliation_strings":["Signal Processing, Artificial Intelligence and Vision Technologies, Queensland University of Technology,Brisbane,Australia"],"affiliations":[{"raw_affiliation_string":"Signal Processing, Artificial Intelligence and Vision Technologies, Queensland University of Technology,Brisbane,Australia","institution_ids":["https://openalex.org/I2802348851","https://openalex.org/I160993911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5015209051"],"corresponding_institution_ids":["https://openalex.org/I160993911","https://openalex.org/I2802348851"],"apc_list":null,"apc_paid":null,"fwci":0.3383,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.68418253,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9753999710083008,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9753999710083008,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9165999889373779,"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/hyperspectral-imaging","display_name":"Hyperspectral imaging","score":0.9254262447357178},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.687768816947937},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5599053502082825},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5496255159378052},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4835667312145233},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4133705496788025},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3621166944503784},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11356279253959656},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.07211199402809143},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06365826725959778}],"concepts":[{"id":"https://openalex.org/C159078339","wikidata":"https://www.wikidata.org/wiki/Q959005","display_name":"Hyperspectral imaging","level":2,"score":0.9254262447357178},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.687768816947937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5599053502082825},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5496255159378052},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4835667312145233},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4133705496788025},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3621166944503784},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11356279253959656},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.07211199402809143},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06365826725959778},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/whispers65427.2024.10876537","is_oa":false,"landing_page_url":"https://doi.org/10.1109/whispers65427.2024.10876537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 14th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W3089799197","https://openalex.org/W3168663926","https://openalex.org/W3184813465","https://openalex.org/W3214586131","https://openalex.org/W4214612132","https://openalex.org/W4312323989","https://openalex.org/W4312751983","https://openalex.org/W4377000481","https://openalex.org/W4380434643","https://openalex.org/W4390357303","https://openalex.org/W4391876866","https://openalex.org/W4394595160","https://openalex.org/W4400073491","https://openalex.org/W6805147364","https://openalex.org/W6852835101"],"related_works":["https://openalex.org/W2072166414","https://openalex.org/W3209970181","https://openalex.org/W2060875994","https://openalex.org/W3034375524","https://openalex.org/W4230131218","https://openalex.org/W2404757046","https://openalex.org/W2044184146","https://openalex.org/W2070598848","https://openalex.org/W2019190440","https://openalex.org/W3034864990"],"abstract_inverted_index":{"Hyperspectral":[0,49],"object":[1,50,71,111],"tracking":[2],"using":[3],"snapshot":[4],"mosaic":[5],"cameras":[6],"is":[7,64],"emerging":[8],"as":[9,84],"it":[10],"provides":[11],"enhanced":[12],"spectral":[13],"information":[14],"alongside":[15],"spatial":[16],"data,":[17],"contributing":[18],"to":[19,45,126],"a":[20,85,142],"more":[21],"comprehensive":[22],"understanding":[23],"of":[24,76,92,162],"material":[25],"properties.":[26],"Using":[27],"transformers,":[28],"which":[29],"have":[30],"consistently":[31],"outperformed":[32],"convolutional":[33],"neural":[34],"networks":[35],"(CNNs)":[36],"in":[37,79,87,135],"learning":[38,131,149],"better":[39],"feature":[40],"representations,":[41],"would":[42],"be":[43,46,124],"expected":[44],"effective":[47,100,148],"for":[48,67,109,130],"tracking.":[51,112],"However,":[52],"training":[53,61,144,185],"large":[54,77,104],"transformers":[55],"necessitates":[56],"extensive":[57],"datasets":[58,78,152],"and":[59,73],"prolonged":[60],"periods.":[62],"This":[63,96,158],"particularly":[65],"critical":[66],"complex":[68],"tasks":[69],"like":[70],"tracking,":[72],"the":[74,80,89,160],"scarcity":[75],"hyperspectral":[81,110,136,151],"domain":[82],"acts":[83],"bottleneck":[86],"achieving":[88],"full":[90],"potential":[91],"powerful":[93],"transformer":[94],"models.":[95],"paper":[97],"proposes":[98],"an":[99,115],"methodology":[101],"that":[102,122,146],"adapts":[103],"pretrained":[105],"transformer-based":[106,128],"foundation":[107],"models":[108],"We":[113],"propose":[114],"adaptive,":[116],"learnable":[117],"spatial-spectral":[118,133],"token":[119],"fusion":[120],"module":[121],"can":[123],"extended":[125],"any":[127],"backbone":[129],"inherent":[132],"features":[134],"data.":[137],"Furthermore,":[138],"our":[139],"model":[140,178],"incorporates":[141],"cross-modality":[143],"pipeline":[145],"facilitates":[147],"across":[150],"collected":[153],"with":[154,183],"different":[155],"sensor":[156],"modalities.":[157],"enables":[159],"extraction":[161],"complementary":[163],"knowledge":[164],"from":[165],"additional":[166],"modalities,":[167],"whether":[168],"or":[169],"not":[170],"they":[171],"are":[172],"present":[173],"during":[174],"testing.":[175],"Our":[176],"proposed":[177],"also":[179],"achieves":[180],"superior":[181],"performance":[182],"minimal":[184],"iterations.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}