{"id":"https://openalex.org/W7130544781","doi":"https://doi.org/10.1109/ictc66702.2025.11388240","title":"Optimizing Object Detection with Multispectral RGB/IR Fusion","display_name":"Optimizing Object Detection with Multispectral RGB/IR Fusion","publication_year":2025,"publication_date":"2025-10-14","ids":{"openalex":"https://openalex.org/W7130544781","doi":"https://doi.org/10.1109/ictc66702.2025.11388240"},"language":null,"primary_location":{"id":"doi:10.1109/ictc66702.2025.11388240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11388240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5126418070","display_name":"Sofia Maria Palomino Chamizo","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sofia Maria Palomino Chamizo","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST),School of Computing,Daejeon,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST),School of Computing,Daejeon,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126427270","display_name":"Daeyoung Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Daeyoung Kim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST),School of Computing,Daejeon,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST),School of Computing,Daejeon,South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.34940001368522644,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.34940001368522644,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.23489999771118164,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.15129999816417694,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6881999969482422},{"id":"https://openalex.org/keywords/multispectral-image","display_name":"Multispectral image","score":0.6832000017166138},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5389999747276306},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4943000078201294},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.48069998621940613},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.47519999742507935},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4675000011920929},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4659999907016754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7466999888420105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7287999987602234},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6881999969482422},{"id":"https://openalex.org/C173163844","wikidata":"https://www.wikidata.org/wiki/Q1761440","display_name":"Multispectral image","level":2,"score":0.6832000017166138},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5490999817848206},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5389999747276306},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4943000078201294},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.48069998621940613},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.47519999742507935},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4675000011920929},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4659999907016754},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.45509999990463257},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.3736000061035156},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.30880001187324524},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.29109999537467957},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27790001034736633},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.26170000433921814},{"id":"https://openalex.org/C2982962833","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information fusion","level":2,"score":0.25859999656677246}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictc66702.2025.11388240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11388240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","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":11,"referenced_works":["https://openalex.org/W1910108985","https://openalex.org/W2176924101","https://openalex.org/W2752782242","https://openalex.org/W2798987894","https://openalex.org/W2963037989","https://openalex.org/W3036931590","https://openalex.org/W3047260603","https://openalex.org/W3209478434","https://openalex.org/W4366378409","https://openalex.org/W4391752451","https://openalex.org/W4402916619"],"related_works":[],"abstract_inverted_index":{"This":[0,88],"paper":[1],"addresses":[2],"the":[3,31,45,56,104],"challenge":[4],"of":[5],"effectively":[6],"fusing":[7],"visible":[8],"and":[9,84,99,107],"infrared":[10],"images":[11],"for":[12,97,128],"robust":[13],"object":[14,94],"detection":[15],"under":[16],"varying":[17],"lighting":[18],"conditions.":[19],"Due":[20],"to":[21,29,80],"their":[22],"distinct":[23],"characteristics,":[24],"existing":[25],"methods":[26],"often":[27],"struggle":[28],"integrate":[30],"complementary":[32],"information":[33],"from":[34],"these":[35,40],"modalities":[36],"fully.":[37],"To":[38],"overcome":[39],"limitations,":[41],"this":[42],"work":[43],"introduces":[44],"Multi-Scale":[46],"Attention":[47],"Fusion":[48],"Transformer":[49],"(MAFT),":[50],"which":[51],"improves":[52],"feature":[53,58,82],"integration":[54],"at":[55],"mid-level":[57],"stage":[59],"(P4/16).":[60],"Unlike":[61],"previous":[62],"transformer-based":[63],"approaches":[64],"that":[65,111],"apply":[66],"uniform":[67],"fusion":[68],"across":[69],"multiple":[70],"levels,":[71],"MAFT":[72,112],"focuses":[73],"on":[74,103],"P4/16,":[75],"incorporating":[76],"multi-scale":[77],"attention":[78],"mechanisms":[79],"refine":[81],"extraction":[83],"strengthen":[85],"RGB-IR":[86],"fusion.":[87],"approach":[89],"results":[90],"in":[91],"more":[92],"precise":[93],"detection,":[95],"particularly":[96],"small":[98],"low-contrast":[100],"targets.":[101],"Evaluations":[102],"VEDAI,":[105],"FLIR-Aligned,":[106],"KAIST":[108],"datasets":[109],"show":[110],"achieves":[113],"state-of-the-art":[114],"mean":[115],"Average":[116],"Precision":[117],"(mAP)":[118],"performance":[119],"while":[120],"maintaining":[121],"competitive":[122],"inference":[123],"speed,":[124],"making":[125],"it":[126],"suitable":[127],"real-time":[129],"applications.":[130]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-20T00:00:00"}