{"id":"https://openalex.org/W7128630943","doi":"https://doi.org/10.1109/tip.2026.3661868","title":"Adaptive Fine-Grained Fusion Network for Multimodal UAV Object Detection","display_name":"Adaptive Fine-Grained Fusion Network for Multimodal UAV Object Detection","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7128630943","doi":"https://doi.org/10.1109/tip.2026.3661868","pmid":"https://pubmed.ncbi.nlm.nih.gov/41671144"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3661868","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3661868","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5113151819","display_name":"Zhanyan Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhanyan Tang","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhihao Wu","orcid":"https://orcid.org/0000-0002-2704-0614"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Wu","raw_affiliation_strings":["School of Artificial Intelligence and the National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2704-0614","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and the National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125647887","display_name":"Mu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mu Li","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-7327-3304","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125642631","display_name":"Jie Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Wen","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-9554-2379","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121821800","display_name":"Bob Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Bob Zhang","raw_affiliation_strings":["PAMI Research Group, Department of Computer and Information Science, University of Macau, Taipa, Macau, China"],"raw_orcid":"https://orcid.org/0000-0003-2497-9519","affiliations":[{"raw_affiliation_string":"PAMI Research Group, Department of Computer and Information Science, University of Macau, Taipa, Macau, China","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yong Xu","orcid":"https://orcid.org/0000-0003-0530-2123"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Xu","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-0530-2123","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jianqiang Li","orcid":"https://orcid.org/0000-0002-2208-962X"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqiang Li","raw_affiliation_strings":["School of Artificial Intelligence and the National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2208-962X","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and the National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I4210152380"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5113151819"],"corresponding_institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":32.4097,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.99020448,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"35","issue":null,"first_page":"1870","last_page":"1882"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7555000185966492,"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":0.7555000185966492,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.05139999836683273,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.022700000554323196,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.632099986076355},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5325999855995178},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5109000205993652},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.5092999935150146},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49459999799728394},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4691999852657318},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4620000123977661},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4578000009059906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7540000081062317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7333999872207642},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6787999868392944},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.632099986076355},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5325999855995178},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5109000205993652},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.5092999935150146},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49459999799728394},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4691999852657318},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4620000123977661},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4578000009059906},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41990000009536743},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.400299996137619},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.37560001015663147},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3643999993801117},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3003000020980835},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C2982962833","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information fusion","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.251800000667572},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3661868","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3661868","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:41671144","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41671144","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2620661441","display_name":null,"funder_award_id":"62371157","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4701649649","display_name":null,"funder_award_id":"62527809","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5618573370","display_name":null,"funder_award_id":"62372136","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2102605133","https://openalex.org/W2176924101","https://openalex.org/W2194775991","https://openalex.org/W2531409750","https://openalex.org/W2944087553","https://openalex.org/W2962749812","https://openalex.org/W2963351448","https://openalex.org/W2969704791","https://openalex.org/W2987131085","https://openalex.org/W3042011474","https://openalex.org/W3094502228","https://openalex.org/W3116963012","https://openalex.org/W3136761610","https://openalex.org/W3158080681","https://openalex.org/W3159018159","https://openalex.org/W3163843793","https://openalex.org/W3194077607","https://openalex.org/W3203608457","https://openalex.org/W3207919963","https://openalex.org/W3210997132","https://openalex.org/W3213472242","https://openalex.org/W4200631567","https://openalex.org/W4214648418","https://openalex.org/W4292387403","https://openalex.org/W4292829089","https://openalex.org/W4296391893","https://openalex.org/W4313506322","https://openalex.org/W4319336343","https://openalex.org/W4327785494","https://openalex.org/W4362009341","https://openalex.org/W4385257519","https://openalex.org/W4386189887","https://openalex.org/W4391974567","https://openalex.org/W4392523614","https://openalex.org/W4398760112","https://openalex.org/W4400179543","https://openalex.org/W4404688003","https://openalex.org/W4408442637","https://openalex.org/W4409261930"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"perception":[1],"and":[2,33,51],"fusion":[3,20,63,74,89,95],"play":[4],"a":[5,84,118],"vital":[6],"role":[7],"in":[8,46,150],"uncrewed":[9],"aerial":[10],"vehicle":[11],"(UAV)":[12],"object":[13,79,148,159],"detection.":[14,80],"Existing":[15],"methods":[16],"typically":[17],"adopt":[18],"global":[19,62],"strategies":[21],"across":[22,38,105],"modalities.":[23],"However,":[24],"due":[25],"to":[26,58,98,124],"illumination":[27],"variation,":[28],"the":[29,42,99,126,132,140,145],"effectiveness":[30],"of":[31,61,102,112,128,147],"RGB":[32],"infrared":[34],"modalities":[35],"may":[36],"differ":[37],"local":[39,85,94],"regions":[40,104],"within":[41],"same":[43],"image,":[44],"particularly":[45],"UAV":[47,78,151,158],"perspectives":[48],"where":[49],"occlusions":[50],"dense":[52],"small":[53],"objects":[54],"are":[55],"prevalent,":[56],"leading":[57],"suboptimal":[59],"performance":[60,155],"methods.":[64],"To":[65],"address":[66],"this":[67],"issue,":[68],"we":[69,82,116],"propose":[70],"an":[71],"adaptive":[72],"fine-grained":[73],"network":[75],"for":[76],"multimodal":[77,157],"First,":[81],"design":[83],"feature":[86,121],"consistency-based":[87],"modality":[88],"module,":[90],"which":[91],"adaptively":[92],"assigns":[93],"weights":[96],"according":[97],"structural":[100],"consistency":[101],"high-response":[103],"modalities,":[106],"thereby":[107],"enabling":[108],"more":[109],"effective":[110],"aggregation":[111],"object-relevant":[113],"features.":[114],"Second,":[115],"introduce":[117],"mutual":[119],"information-guided":[120],"contrastive":[122],"loss":[123],"encourage":[125],"preservation":[127],"modality-specific":[129],"information":[130],"during":[131],"early":[133],"training":[134],"phase.":[135],"Experimental":[136],"results":[137],"demonstrate":[138],"that":[139],"proposed":[141],"method":[142],"effectively":[143],"addresses":[144],"issue":[146],"occlusion":[149],"perspectives,":[152],"achieving":[153],"state-of-the-art":[154],"on":[156],"detection":[160],"benchmarks.":[161],"Code":[162],"will":[163],"be":[164],"available":[165],"at":[166],"https://github.com/lingf5877/AFFNet.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-02-12T00:00:00"}