{"id":"https://openalex.org/W4415538712","doi":"https://doi.org/10.1145/3746027.3755841","title":"Multimodal Decomposed Distillation with Instance Alignment and Uncertainty Compensation for Thermal Object Detection","display_name":"Multimodal Decomposed Distillation with Instance Alignment and Uncertainty Compensation for Thermal Object Detection","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538712","doi":"https://doi.org/10.1145/3746027.3755841"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755841","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5036015170","display_name":"Yanfeng Liu","orcid":"https://orcid.org/0000-0003-0122-4463"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanfeng Liu","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, Hubei, China"],"raw_orcid":"https://orcid.org/0000-0003-0122-4463","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024278302","display_name":"Lefei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lefei Zhang","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, Hubei, China"],"raw_orcid":"https://orcid.org/0000-0003-0542-2280","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5036015170"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":1.0626,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82451689,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2294","last_page":"2303"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9642000198364258,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9642000198364258,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T11667","display_name":"Advanced Chemical Sensor Technologies","score":0.9578999876976013,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T11053","display_name":"Process Optimization and Integration","score":0.9377999901771545,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/boosting","display_name":"Boosting (machine learning)","score":0.5672000050544739},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5533999800682068},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5224000215530396},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.47440001368522644},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.4650999903678894},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4636000096797943},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4530999958515167},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45179998874664307},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.39079999923706055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.745199978351593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6660000085830688},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5672000050544739},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5541999936103821},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5533999800682068},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5224000215530396},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.47440001368522644},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4650999903678894},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4636000096797943},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45179998874664307},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.39079999923706055},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3546000123023987},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.3537999987602234},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33059999346733093},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.25769999623298645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755841","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4018567684","display_name":null,"funder_award_id":"2042025kf0030","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G457964128","display_name":null,"funder_award_id":"62431020","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"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2176924101","https://openalex.org/W2806070179","https://openalex.org/W2884561390","https://openalex.org/W3190537575","https://openalex.org/W4321770555","https://openalex.org/W4360995216","https://openalex.org/W4385453417","https://openalex.org/W4402667890","https://openalex.org/W4402772396","https://openalex.org/W4403390534","https://openalex.org/W4411055457"],"related_works":[],"abstract_inverted_index":{"RGB-Thermal":[0],"images":[1],"leverage":[2],"complementary":[3],"optical":[4],"and":[5,24,65,88,126,144],"thermal":[6,115],"modalities":[7],"to":[8,26,40,74,104,118,136,150],"identify":[9],"objects.":[10],"While":[11],"achieving":[12],"superior":[13],"performance,":[14],"the":[15,57,112,138,163],"reliance":[16],"on":[17,159],"multimodal":[18,36,49],"fusion":[19],"inherently":[20],"limits":[21],"inference":[22],"efficiency":[23],"adaptability":[25],"harsh":[27],"RGB-failure":[28],"environments.":[29],"In":[30],"this":[31],"work,":[32],"we":[33,55,80,129],"propose":[34,145],"a":[35,89,131],"decomposed":[37,94],"distillation":[38,135,149],"framework":[39,167],"develop":[41],"robust":[42],"thermal-only":[43],"detectors":[44],"by":[45],"transferring":[46],"knowledge":[47,95,108,122],"from":[48],"teachers.":[50],"Unlike":[51],"conventional":[52],"one-to-one":[53],"distillation,":[54],"decouple":[56],"tasks":[58],"of":[59,114,165],"simultaneously":[60],"mimicking":[61],"RGB-T":[62],"teacher":[63],"representations":[64],"preserving":[66,111],"thermal-specific":[67],"student":[68],"feature":[69,125,142],"integrity":[70,113],"into":[71],"dual":[72],"branches":[73],"avoid":[75],"intrinsic":[76],"semantic":[77],"conflicts.":[78],"Specifically,":[79],"present":[81],"channel-adaptive":[82],"prompt":[83],"learning":[84],"for":[85,93,152],"cross-modal":[86,107],"decomposition":[87],"frequency-guided":[90],"dynamic":[91],"module":[92],"integration.":[96],"The":[97],"dual-branch":[98],"architecture":[99],"employs":[100],"asymmetric":[101],"training":[102],"objectives":[103],"ensure":[105],"effective":[106],"transfer":[109],"while":[110],"information.":[116],"Furthermore,":[117],"exploit":[119],"finer-grained":[120],"instance":[121,133],"across":[123],"both":[124],"prediction":[127],"levels,":[128],"introduce":[130],"customized":[132],"alignment":[134],"enhance":[137],"local":[139],"discriminability":[140],"in":[141,155,168],"pyramids,":[143],"an":[146],"uncertainty-aware":[147],"logit":[148],"compensate":[151],"ambiguous":[153],"predictions":[154],"detection":[156],"heads.":[157],"Experiments":[158],"three":[160],"datasets":[161],"validate":[162],"effectiveness":[164],"our":[166],"boosting":[169],"thermal-based":[170],"detectors.":[171],"Code":[172],"is":[173],"released":[174],"at":[175],"https://github.com/lyf0801/DecomKD.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-25T00:00:00"}