{"id":"https://openalex.org/W4411171894","doi":"https://doi.org/10.1109/tcsvt.2025.3578340","title":"Confidence-Driven Unimodal Interference Removal for Enhanced Multimodal Object Detection","display_name":"Confidence-Driven Unimodal Interference Removal for Enhanced Multimodal Object Detection","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4411171894","doi":"https://doi.org/10.1109/tcsvt.2025.3578340"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3578340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3578340","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-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":null,"display_name":"Yu Wang","orcid":"https://orcid.org/0009-0005-7282-0176"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-7282-0176","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006854141","display_name":"Shikui Wei","orcid":"https://orcid.org/0000-0003-3803-9763"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shikui Wei","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3803-9763","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103085039","display_name":"Sen Xu","orcid":"https://orcid.org/0000-0002-4522-5460"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sen Xu","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4522-5460","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013250925","display_name":"Ying Qin","orcid":"https://orcid.org/0000-0003-4606-7174"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Qin","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4606-7174","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100362745","display_name":"Yao Zhao","orcid":"https://orcid.org/0000-0002-8581-9554"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Zhao","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8581-9554","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":2.0042,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.85490577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"35","issue":"11","first_page":"11041","last_page":"11053"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.7441999912261963,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.7441999912261963,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.7432000041007996,"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/T13382","display_name":"Robotics and Automated Systems","score":0.6891999840736389,"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/object-detection","display_name":"Object detection","score":0.5789411067962646},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5501575469970703},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5309110879898071},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.526546061038971},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5006837844848633},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.476388156414032},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3341146409511566},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10169100761413574}],"concepts":[{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5789411067962646},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5501575469970703},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5309110879898071},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.526546061038971},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5006837844848633},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.476388156414032},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3341146409511566},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10169100761413574},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3578340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3578340","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G361765533","display_name":null,"funder_award_id":"2018AAA0102100","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G634209715","display_name":null,"funder_award_id":"No.62120106009","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/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W1910108985","https://openalex.org/W1988790447","https://openalex.org/W2102605133","https://openalex.org/W2109255472","https://openalex.org/W2161969291","https://openalex.org/W2168356304","https://openalex.org/W2176924101","https://openalex.org/W2884367402","https://openalex.org/W2891834928","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2986674040","https://openalex.org/W3018757597","https://openalex.org/W3034937135","https://openalex.org/W3035673257","https://openalex.org/W3036931590","https://openalex.org/W3096609285","https://openalex.org/W3116967329","https://openalex.org/W3118570274","https://openalex.org/W3138516171","https://openalex.org/W3158128549","https://openalex.org/W3204415296","https://openalex.org/W3207919963","https://openalex.org/W3213472242","https://openalex.org/W4200631567","https://openalex.org/W4200632941","https://openalex.org/W4226294111","https://openalex.org/W4233467483","https://openalex.org/W4239510810","https://openalex.org/W4284898017","https://openalex.org/W4285253679","https://openalex.org/W4307552296","https://openalex.org/W4312549624","https://openalex.org/W4312594135","https://openalex.org/W4312818263","https://openalex.org/W4313007055","https://openalex.org/W4313032837","https://openalex.org/W4320002812","https://openalex.org/W4322123798","https://openalex.org/W4327785494","https://openalex.org/W4383890466","https://openalex.org/W4385245566","https://openalex.org/W4385801610","https://openalex.org/W4386038403","https://openalex.org/W4386076325","https://openalex.org/W4386076504","https://openalex.org/W4386179772","https://openalex.org/W4386189887","https://openalex.org/W4386737234","https://openalex.org/W4387967872","https://openalex.org/W4387968049","https://openalex.org/W4387968493","https://openalex.org/W4387968982","https://openalex.org/W4402260847","https://openalex.org/W4407247101"],"related_works":["https://openalex.org/W2375786911","https://openalex.org/W2737719445","https://openalex.org/W2898210368","https://openalex.org/W2367630196","https://openalex.org/W4239098401","https://openalex.org/W756944427","https://openalex.org/W2349547031","https://openalex.org/W2382480268","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Multi-spectral":[0],"imaging":[1],"senses":[2],"objects":[3],"from":[4,145],"different":[5],"perspectives,":[6],"exhibiting":[7],"the":[8,22,30,53,108,121,131,135,138,150,155,159],"advantages":[9],"of":[10,24,32,56,111,116,137,161],"cross-modal":[11,16,85],"collaboration.":[12],"However,":[13],"most":[14],"existing":[15],"detection":[17,69,181],"algorithms":[18],"focus":[19],"mainly":[20],"on":[21,176],"design":[23],"fusion":[25,104,127],"mechanisms,":[26],"neglecting":[27],"to":[28,42,106,129,133,203],"assess":[29],"effectiveness":[31],"individual":[33],"modalities.":[34,58],"In":[35,114],"fact,":[36],"if":[37],"a":[38,189,194],"certain":[39],"modality":[40,166],"fails":[41],"provide":[43],"distinguishable":[44],"features,":[45],"it":[46],"will":[47,208],"introduce":[48,120],"unimodal":[49,73,81,170],"interference":[50,144,171],"and":[51,88,123,152,167],"weaken":[52],"feature":[54,125],"representation":[55],"dominate":[57],"To":[59],"address":[60],"this":[61],"problem,":[62],"we":[63,78,99,119],"propose":[64],"an":[65,101],"enhanced":[66],"multi-spectral":[67,179],"object":[68,180],"algorithm":[70],"via":[71],"Confidence-driven":[72],"Interference":[74],"Removal":[75],"(CIRDet).":[76],"Specifically,":[77],"explicitly":[79],"decompose":[80],"visual":[82,92],"contents":[83,93],"into":[84],"consensus":[86],"features":[87,151],"conflict":[89],"features.":[90],"For":[91],"where":[94],"both":[95],"modalities":[96],"express":[97],"confidence,":[98],"employ":[100],"equal":[102],"weighting":[103],"strategy":[105],"exploit":[107],"synergistic":[109],"effect":[110],"modal":[112,117],"information.":[113],"cases":[115],"discrepancy,":[118],"global":[122],"local":[124],"confidence":[126],"mechanisms":[128],"induce":[130],"network":[132],"follow":[134],"guidance":[136],"dominant":[139],"modality,":[140],"thereby":[141],"removing":[142],"conflicted":[143],"inferior":[146,165],"modality.":[147],"By":[148],"decoupling":[149],"processing":[153],"separately,":[154],"proposed":[156],"method":[157,185],"prevents":[158],"loss":[160],"valid":[162],"information":[163],"in":[164],"filters":[168],"out":[169],"more":[172],"accurately.":[173],"Extensive":[174],"experiments":[175],"three":[177],"widely-used":[178],"benchmarks":[182],"demonstrate":[183],"our":[184],"outperforms":[186],"state-of-the-arts":[187],"by":[188],"large":[190],"margin,":[191],"e.g.,":[192],"with":[193],"CNN":[195],"backbone,":[196],"CIRDet":[197],"achieves":[198],"4.2":[199],"mAP@[0.5:0.95]":[200],"improvement":[201],"compared":[202],"Transformer-based":[204],"methods.":[205],"The":[206],"code":[207],"be":[209],"released":[210],"after":[211],"possible":[212],"publication.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}