{"id":"https://openalex.org/W7126050512","doi":"https://doi.org/10.1109/lsp.2026.3659814","title":"Modality-Aware Dynamic Fusion for Weakly Aligned RGB-T Tiny Object Detection","display_name":"Modality-Aware Dynamic Fusion for Weakly Aligned RGB-T Tiny Object Detection","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7126050512","doi":"https://doi.org/10.1109/lsp.2026.3659814"},"language":null,"primary_location":{"id":"doi:10.1109/lsp.2026.3659814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3659814","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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":"Yuting Xie","orcid":"https://orcid.org/0009-0004-5918-3750"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuting Xie","raw_affiliation_strings":["College of Electronic Science and Technology, National University of Defense Technology, Hunan, China"],"raw_orcid":"https://orcid.org/0009-0004-5918-3750","affiliations":[{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123376529","display_name":"Zhili Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhili Zhang","raw_affiliation_strings":["College of Electronic Science and Technology, National University of Defense Technology, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124210250","display_name":"Yi Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Hou","raw_affiliation_strings":["College of Electronic Science and Technology, National University of Defense Technology, Hunan, China"],"raw_orcid":"https://orcid.org/0009-0009-6720-1759","affiliations":[{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078951034","display_name":"Puzuo Wang","orcid":"https://orcid.org/0000-0002-0971-4013"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Puzuo Wang","raw_affiliation_strings":["College of Electronic Science and Technology, National University of Defense Technology, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123416173","display_name":"Hanxiao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanxiao Zhang","raw_affiliation_strings":["College of Electronic Science and Technology, National University of Defense Technology, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electronic Science and Technology, National University of Defense Technology, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09373564,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"1023","last_page":"1027"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9660999774932861,"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":0.9660999774932861,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.003599999938160181,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.003100000089034438,"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/object-detection","display_name":"Object detection","score":0.7613000273704529},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6313999891281128},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6304000020027161},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5839999914169312},{"id":"https://openalex.org/keywords/fusion-mechanism","display_name":"Fusion mechanism","score":0.5228000283241272},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4934000074863434},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4724999964237213},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.47200000286102295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8152999877929688},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7613000273704529},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6935999989509583},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6313999891281128},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6304000020027161},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5839999914169312},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5587000250816345},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.5228000283241272},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4934000074863434},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4724999964237213},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.47200000286102295},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.45320001244544983},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4499000012874603},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3928999900817871},{"id":"https://openalex.org/C2779769447","wikidata":"https://www.wikidata.org/wiki/Q3813641","display_name":"Foreground detection","level":4,"score":0.376800000667572},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.3725000023841858},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2831000089645386},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.2718999981880188},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.2587999999523163}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2026.3659814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3659814","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2963351448","https://openalex.org/W2987131085","https://openalex.org/W3035396860","https://openalex.org/W3116967329","https://openalex.org/W3159018159","https://openalex.org/W3207919963","https://openalex.org/W3213472242","https://openalex.org/W4293363567","https://openalex.org/W4312549624","https://openalex.org/W4312596062","https://openalex.org/W4312823573","https://openalex.org/W4313007055","https://openalex.org/W4313172897","https://openalex.org/W4327785494","https://openalex.org/W4376872192","https://openalex.org/W4385801610","https://openalex.org/W4386072246","https://openalex.org/W4386232111","https://openalex.org/W4386591405","https://openalex.org/W4387968493","https://openalex.org/W4390872937","https://openalex.org/W4390873752","https://openalex.org/W4392796741","https://openalex.org/W4395447471","https://openalex.org/W4396754494","https://openalex.org/W4402754006","https://openalex.org/W4402775842","https://openalex.org/W4408245958","https://openalex.org/W4409367242","https://openalex.org/W4409640748","https://openalex.org/W4410861041","https://openalex.org/W4411922047","https://openalex.org/W7081988055"],"related_works":[],"abstract_inverted_index":{"RGB-T":[0,113,221],"object":[1,63,108,223],"detection":[2,64,89,109,224],"demonstrates":[3],"strong":[4],"potential":[5,218],"by":[6,39,201],"leveraging":[7],"the":[8,85,118,137,178,189,209],"complementary":[9],"strengths":[10],"of":[11,211],"visible":[12,102],"(RGB)":[13],"and":[14,25,35,51,72,103,216],"thermal":[15,36,104],"(T)":[16],"modalities":[17],"for":[18,106,219],"applications":[19],"in":[20,61,110,183],"intelligent":[21],"surveillance,":[22],"autonomous":[23],"driving,":[24],"search-and-rescue.":[26],"However,":[27],"most":[28],"existing":[29,199],"approaches":[30],"rely":[31],"on":[32,188],"aligning":[33],"RGB":[34],"features":[37,105],"followed":[38],"global":[40],"feature":[41,67,134,179],"fusion,":[42],"which":[43,154],"often":[44],"fail":[45],"to":[46,75,99,159],"capture":[47],"fine-grained":[48],"spatial":[49,77,175],"misalignments":[50],"generate":[52],"reliable":[53],"fusion":[54,215],"weights.":[55],"These":[56,144,206],"limitations":[57],"become":[58],"particularly":[59],"pronounced":[60],"tiny":[62,107,222],"scenarios,":[65],"where":[66],"representations":[68],"are":[69],"inherently":[70],"sparse":[71],"highly":[73],"sensitive":[74],"cross-modal":[76,129],"misalignment.":[78],"To":[79],"address":[80],"these":[81],"challenges,":[82],"we":[83],"propose":[84],"Modality-Aware":[86,97,149],"Dynamic":[87,120],"Fusion":[88,121],"(MDFDet)":[90],"network,":[91],"an":[92],"end-to-end":[93],"framework":[94],"that":[95,171,193],"leverages":[96],"Queries":[98],"adaptively":[100,155],"fuse":[101],"weakly":[111],"aligned":[112],"images.":[114],"At":[115],"its":[116,217],"core,":[117],"Modality-Decoupled":[119],"Decoder":[122],"employs":[123],"dual":[124],"self-attention":[125],"mechanisms":[126],"coupled":[127],"with":[128],"deformable":[130],"attention,":[131],"enabling":[132],"alignment-free":[133],"aggregation":[135],"at":[136],"region":[138],"level":[139],"through":[140],"dynamically":[141],"decoupled":[142,163,214],"queries.":[143,164],"queries":[145],"originate":[146],"from":[147],"our":[148],"Paired":[150],"Query":[151],"Selection":[152],"module,":[153],"balances":[156],"multimodal":[157],"contributions":[158],"select":[160],"semantically":[161],"rich,":[162],"Additionally,":[165],"a":[166],"Tiny":[167],"Object":[168],"Detection":[169],"Layer":[170],"preserves":[172],"critical":[173],"low-level":[174],"details,":[176],"addressing":[177],"degradation":[180],"commonly":[181],"observed":[182],"deep":[184],"networks.":[185],"Extensive":[186],"experiments":[187],"RGBT-Tiny":[190],"benchmark":[191],"demonstrate":[192],"MDFDet":[194],"achieves":[195],"state-of-the-art":[196],"performance,":[197],"outperforming":[198],"methods":[200],"more":[202],"than":[203],"3%":[204],"in$\\text{AP}_{50}^{s}$.":[205],"results":[207],"highlight":[208],"effectiveness":[210],"modality-aware":[212],"dynamic":[213],"real-world":[220],"tasks.":[225]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-01-30T00:00:00"}