{"id":"https://openalex.org/W4414603541","doi":"https://doi.org/10.1109/tgrs.2025.3615481","title":"IM-CMDet: An Intramodal Enhancement and Cross-Modal Fusion Network for Small Object Detection in UAV Aerial Visible-Infrared Imagery","display_name":"IM-CMDet: An Intramodal Enhancement and Cross-Modal Fusion Network for Small Object Detection in UAV Aerial Visible-Infrared Imagery","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414603541","doi":"https://doi.org/10.1109/tgrs.2025.3615481"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2025.3615481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3615481","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"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 Geoscience and Remote Sensing","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":"https://openalex.org/A5019091193","display_name":"M. X. Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Minchao Luo","raw_affiliation_strings":["Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, Zhejiang, China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086031494","display_name":"Rui Zhao","orcid":"https://orcid.org/0000-0002-9577-7714"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhao","raw_affiliation_strings":["Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, Zhejiang, China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027880590","display_name":"Shenfu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenfu Zhang","raw_affiliation_strings":["Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, Zhejiang, China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102841919","display_name":"Liang Chen","orcid":"https://orcid.org/0000-0002-2974-8616"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Chen","raw_affiliation_strings":["Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, Zhejiang, China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049898953","display_name":"Feng Shao","orcid":"https://orcid.org/0000-0002-2495-9924"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Shao","raw_affiliation_strings":["Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, Zhejiang, China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018282808","display_name":"Xiangchao Meng","orcid":"https://orcid.org/0000-0002-7405-3143"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangchao Meng","raw_affiliation_strings":["Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, Zhejiang, China","institution_ids":["https://openalex.org/I109935558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5019091193"],"corresponding_institution_ids":["https://openalex.org/I109935558"],"apc_list":null,"apc_paid":null,"fwci":25.5316,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.99268323,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"63","issue":null,"first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9968000054359436,"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"}},"topics":[{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9968000054359436,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.991100013256073,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9779000282287598,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.8192999958992004},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.574400007724762},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5572999715805054},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5364999771118164},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5026000142097473},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.477400004863739},{"id":"https://openalex.org/keywords/aerial-image","display_name":"Aerial image","score":0.46970000863075256},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42719998955726624},{"id":"https://openalex.org/keywords/drone","display_name":"Drone","score":0.415800005197525},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.40849998593330383}],"concepts":[{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.8192999958992004},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7993999719619751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7656000256538391},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7376000285148621},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.574400007724762},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5572999715805054},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5364999771118164},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5026000142097473},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.477400004863739},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.46970000863075256},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42719998955726624},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.415800005197525},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.40849998593330383},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.3921000063419342},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.3808000087738037},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3434000015258789},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.336899995803833},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.28700000047683716},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C2780156472","wikidata":"https://www.wikidata.org/wiki/Q2355550","display_name":"Pedestrian detection","level":3,"score":0.2815000116825104},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2759000062942505},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.27079999446868896},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.26980000734329224},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.25780001282691956},{"id":"https://openalex.org/C2778857364","wikidata":"https://www.wikidata.org/wiki/Q974850","display_name":"Missile","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tgrs.2025.3615481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3615481","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"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 Geoscience and Remote Sensing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5658660871","display_name":null,"funder_award_id":"2022J076","funder_id":"https://openalex.org/F4320332587","funder_display_name":"Natural Science Foundation of Ningbo"},{"id":"https://openalex.org/G713033493","display_name":null,"funder_award_id":"42171326","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8051218275","display_name":null,"funder_award_id":"42301376","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/F4320332587","display_name":"Natural Science Foundation of Ningbo","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2601564443","https://openalex.org/W2962766617","https://openalex.org/W2963351448","https://openalex.org/W2982220924","https://openalex.org/W2982770724","https://openalex.org/W2987131085","https://openalex.org/W2989676862","https://openalex.org/W3009396058","https://openalex.org/W3035396860","https://openalex.org/W3089893234","https://openalex.org/W3116967329","https://openalex.org/W3138516171","https://openalex.org/W3181167066","https://openalex.org/W3207919963","https://openalex.org/W4200631567","https://openalex.org/W4282571178","https://openalex.org/W4285099087","https://openalex.org/W4285792526","https://openalex.org/W4288325606","https://openalex.org/W4294114292","https://openalex.org/W4294676930","https://openalex.org/W4295123323","https://openalex.org/W4304084055","https://openalex.org/W4312594135","https://openalex.org/W4312596062","https://openalex.org/W4312668764","https://openalex.org/W4313007055","https://openalex.org/W4313506322","https://openalex.org/W4323022579","https://openalex.org/W4362500629","https://openalex.org/W4375809357","https://openalex.org/W4376131895","https://openalex.org/W4385245566","https://openalex.org/W4385801610","https://openalex.org/W4386083029","https://openalex.org/W4386591405","https://openalex.org/W4386737234","https://openalex.org/W4387068250","https://openalex.org/W4387553256","https://openalex.org/W4388039304","https://openalex.org/W4390488653","https://openalex.org/W4390908082","https://openalex.org/W4391559729","https://openalex.org/W4391769355","https://openalex.org/W4391974567","https://openalex.org/W4392796741","https://openalex.org/W4393148032","https://openalex.org/W4396564062","https://openalex.org/W4396754494","https://openalex.org/W4398760112","https://openalex.org/W4400525915","https://openalex.org/W4401567633","https://openalex.org/W4402775842","https://openalex.org/W4404177154","https://openalex.org/W4405111152","https://openalex.org/W4406457942","https://openalex.org/W4407606208","https://openalex.org/W4409474240","https://openalex.org/W4410089822","https://openalex.org/W4410861041","https://openalex.org/W4411055457","https://openalex.org/W4411541102","https://openalex.org/W4411922047"],"related_works":[],"abstract_inverted_index":{"UAV":[0,22],"aerial":[1,23,226],"Visible-Infrared":[2],"(RGBT)":[3],"object":[4,25,61,103,138],"detection":[5,26,104,200,223],"has":[6],"been":[7],"widely":[8],"applied":[9],"in":[10,32,54,75,105,224],"fields":[11],"such":[12],"as":[13],"military":[14],"operations":[15],"and":[16,45,97,127,162,183,206],"rescue":[17],"missions.":[18],"However,":[19],"although":[20],"numerous":[21],"RGBT":[24,107],"methods":[27],"exist,":[28],"several":[29],"challenges":[30],"remain":[31],"this":[33,90],"field.":[34],"On":[35,63],"the":[36,64,79,83,87,114,120,128,173,179,188,194],"one":[37],"hand,":[38,66],"drones":[39],"typically":[40],"operate":[41],"at":[42,232],"high":[43],"altitudes,":[44],"objects":[46],"only":[47],"occupy":[48],"a":[49,57,72],"small":[50,80,102,137,177],"number":[51],"of":[52,82,196],"pixels":[53],"imaging,":[55],"posing":[56],"significant":[58],"challenge":[59],"to":[60,158,176,186],"detection.":[62],"other":[65],"spatial":[67,184],"misalignment":[68],"between":[69],"modalities":[70],"remains":[71],"major":[73],"obstacle":[74],"cross-modal":[76,98,218],"fusion\u2014especially":[77],"given":[78],"size":[81],"objects.":[84],"To":[85,170],"address":[86],"above":[88],"issues,":[89],"paper":[91],"proposes":[92],"IM-CMDet,":[93],"an":[94],"intra-modal":[95],"enhancement":[96],"fusion":[99,190],"network":[100],"for":[101],"UAV-based":[106],"imagery,":[108],"which":[109],"comprises":[110],"three":[111],"effective":[112,217],"modules:":[113],"Detail-Semantics":[115],"Joint":[116],"Enhancement":[117],"module":[118,125,135,155],"(DSJE),":[119],"Differential-based":[121],"Fusion":[122],"Weight":[123],"Generation":[124],"(DFWG)":[126],"Feature":[129],"Reconstruction":[130],"Network":[131],"(FRN).":[132],"The":[133,153,228],"DSJE":[134],"prevents":[136],"features":[139],"from":[140],"being":[141],"overwhelmed":[142],"by":[143],"background":[144,197],"noise":[145,198],"through":[146,216],"optimizing":[147],"feature":[148],"representations":[149],"across":[150],"different":[151],"levels.":[152],"FRN":[154],"is":[156,230],"designed":[157],"overcome":[159],"modality":[160],"differences":[161],"build":[163],"inter-modality":[164],"information":[165],"correlation":[166],"via":[167],"swin-Transformer":[168],"architecture.":[169],"further":[171],"enhance":[172],"network\u2019s":[174],"sensitivity":[175],"objects,":[178],"DFWG":[180],"combines":[181],"differential":[182],"attention":[185],"generate":[187],"final":[189],"weights":[191],"while":[192],"reducing":[193],"impact":[195],"on":[199,204],"performance.":[201],"Extensive":[202],"experiments":[203],"RGBTDronePerson":[205],"two":[207],"additional":[208],"benchmarks":[209],"demonstrate":[210],"that":[211],"IM-CMDet":[212],"achieves":[213],"state-of-the-art":[214],"performance":[215],"fusion,":[219],"significantly":[220],"advancing":[221],"small-object":[222],"complex":[225],"scenarios.":[227],"code":[229],"available":[231],"https://github.com/RS-Minchao/IM-CMDet.":[233]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}