{"id":"https://openalex.org/W4405332772","doi":"https://doi.org/10.3390/rs16244649","title":"Cross-Modality Data Augmentation for Aerial Object Detection with Representation Learning","display_name":"Cross-Modality Data Augmentation for Aerial Object Detection with Representation Learning","publication_year":2024,"publication_date":"2024-12-12","ids":{"openalex":"https://openalex.org/W4405332772","doi":"https://doi.org/10.3390/rs16244649"},"language":"en","primary_location":{"id":"doi:10.3390/rs16244649","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs16244649","pdf_url":"https://www.mdpi.com/2072-4292/16/24/4649/pdf?version=1733993431","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2072-4292/16/24/4649/pdf?version=1733993431","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101771714","display_name":"Chiheng Wei","orcid":"https://orcid.org/0000-0003-0211-2922"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chiheng Wei","raw_affiliation_strings":["The School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China"],"affiliations":[{"raw_affiliation_string":"The School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113070577","display_name":"Lianfa Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianfa Bai","raw_affiliation_strings":["The School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China"],"affiliations":[{"raw_affiliation_string":"The School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002387716","display_name":"Xiaoyu Chen","orcid":"https://orcid.org/0000-0003-1026-2824"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Chen","raw_affiliation_strings":["The School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China"],"affiliations":[{"raw_affiliation_string":"The School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086464033","display_name":"Jing Han","orcid":"https://orcid.org/0000-0002-2986-2398"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jing Han","raw_affiliation_strings":["The School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China"],"affiliations":[{"raw_affiliation_string":"The School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5086464033"],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":{"value":2500,"currency":"CHF","value_usd":2707},"apc_paid":{"value":2500,"currency":"CHF","value_usd":2707},"fwci":1.6899,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.86087041,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"16","issue":"24","first_page":"4649","last_page":"4649"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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":0.9995999932289124,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9995999932289124,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9991000294685364,"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/computer-science","display_name":"Computer science","score":0.8179320096969604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7380542755126953},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5882221460342407},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5805469155311584},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5399338006973267},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48590460419654846},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4732411801815033},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.434509813785553},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.4235169291496277},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4121955335140228},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3566341996192932}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8179320096969604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7380542755126953},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5882221460342407},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5805469155311584},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5399338006973267},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48590460419654846},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4732411801815033},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.434509813785553},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.4235169291496277},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4121955335140228},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3566341996192932},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/rs16244649","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs16244649","pdf_url":"https://www.mdpi.com/2072-4292/16/24/4649/pdf?version=1733993431","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:9d17e64a16b74340a281a0740549b63e","is_oa":true,"landing_page_url":"https://doaj.org/article/9d17e64a16b74340a281a0740549b63e","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Remote Sensing, Vol 16, Iss 24, p 4649 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/rs16244649","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs16244649","pdf_url":"https://www.mdpi.com/2072-4292/16/24/4649/pdf?version=1733993431","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2774473853","display_name":null,"funder_award_id":"BE2022391","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G436095773","display_name":null,"funder_award_id":"62101256","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5115529456","display_name":null,"funder_award_id":"62101256","funder_id":"https://openalex.org/F4320327777","funder_display_name":"Jiangsu Provincial Key Research and Development Program"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8354038227","display_name":null,"funder_award_id":"BE2022391","funder_id":"https://openalex.org/F4320327777","funder_display_name":"Jiangsu Provincial Key Research and Development Program"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327777","display_name":"Jiangsu Provincial Key Research and Development Program","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405332772.pdf","grobid_xml":"https://content.openalex.org/works/W4405332772.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W2064076387","https://openalex.org/W2133665775","https://openalex.org/W2176924101","https://openalex.org/W2889837429","https://openalex.org/W2944223741","https://openalex.org/W2962793481","https://openalex.org/W2963073614","https://openalex.org/W2963108767","https://openalex.org/W2963188557","https://openalex.org/W2963351448","https://openalex.org/W2963579094","https://openalex.org/W2963800363","https://openalex.org/W2964241181","https://openalex.org/W2964979676","https://openalex.org/W2980280361","https://openalex.org/W2997408160","https://openalex.org/W3034971973","https://openalex.org/W3036167779","https://openalex.org/W3047921400","https://openalex.org/W3118570274","https://openalex.org/W3159674265","https://openalex.org/W3174058041","https://openalex.org/W3176659256","https://openalex.org/W3205338196","https://openalex.org/W3207919963","https://openalex.org/W4200631567","https://openalex.org/W4205274524","https://openalex.org/W4225125774","https://openalex.org/W4283075937","https://openalex.org/W4304080716","https://openalex.org/W4307823382","https://openalex.org/W4312596062","https://openalex.org/W4312685069","https://openalex.org/W4312804044","https://openalex.org/W4313007055","https://openalex.org/W4313015984","https://openalex.org/W4313156423","https://openalex.org/W4323666945","https://openalex.org/W4376106313","https://openalex.org/W4379261328","https://openalex.org/W4382458928","https://openalex.org/W4390787329","https://openalex.org/W4392005856","https://openalex.org/W4392796741","https://openalex.org/W4401878967","https://openalex.org/W6639102338","https://openalex.org/W6743440100","https://openalex.org/W6779823529","https://openalex.org/W6862832148"],"related_works":["https://openalex.org/W1556451512","https://openalex.org/W1555349535","https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W4234091740","https://openalex.org/W4213350282","https://openalex.org/W2230171082","https://openalex.org/W2583128298","https://openalex.org/W2022275305","https://openalex.org/W1604115909"],"abstract_inverted_index":{"Data":[0],"augmentation":[1,33,106,116,178,191,215],"methods":[2,192,212],"offer":[3],"a":[4,113,234,240,245],"cost-effective":[5],"and":[6,19,41,66,140,187,196,238,263],"efficient":[7],"alternative":[8],"to":[9,45,99],"the":[10,38,51,58,70,84,101,134,156,159,163,185,220,225,257],"acquisition":[11],"of":[12,77,104,137,158,259],"additional":[13],"data,":[14],"significantly":[15,249],"enhancing":[16,155],"data":[17,32,56,105,115,152,177,190,194],"diversity":[18],"model":[20],"generalization,":[21],"making":[22],"them":[23,142],"particularly":[24],"favored":[25],"in":[26,54,179,193,229,270],"object":[27,47,121,272],"detection":[28,48,273],"tasks.":[29,60,274],"However,":[30],"existing":[31,201,226],"techniques":[34],"primarily":[35],"focus":[36,132],"on":[37,133],"visible":[39,144],"spectrum":[40],"are":[42,75],"directly":[43],"applied":[44],"RGB-T":[46,120],"tasks,":[49],"overlooking":[50],"inherent":[52],"differences":[53,186],"image":[55,88,125,165],"between":[57,189],"two":[59],"Visible":[61],"images":[62,74,139,145,170],"capture":[63],"rich":[64],"color":[65],"texture":[67],"information":[68,89],"during":[69,83],"daytime,":[71],"while":[72],"infrared":[73,138],"capable":[76],"imaging":[78],"under":[79,146],"low-light":[80],"complex":[81],"scenarios":[82],"nighttime.":[85],"By":[86],"integrating":[87,172],"from":[90],"both":[91],"modalities,":[92],"their":[93],"complementary":[94],"characteristics":[95],"can":[96],"be":[97],"exploited":[98],"improve":[100],"overall":[102],"effectiveness":[103,258],"methods.":[107],"To":[108],"address":[109,219],"this,":[110],"we":[111,131,168,183,204,218],"propose":[112,205],"cross-modality":[114,176,271],"method":[117,228,243,262],"tailored":[118],"for":[119,150,213,267],"detection,":[122],"leveraging":[123],"masked":[124,164],"modeling":[126,166],"within":[127],"representation":[128],"learning.":[129],"Specifically,":[130],"temporal":[135],"consistency":[136],"combine":[141],"with":[143,224],"varying":[147],"lighting":[148],"conditions":[149],"joint":[151],"augmentation,":[153],"thereby":[154],"realism":[157],"augmented":[160],"images.":[161],"Utilizing":[162],"method,":[167],"reconstruct":[169],"by":[171,232],"multimodal":[173],"features,":[174],"achieving":[175],"feature":[180,197],"space.":[181,198],"Additionally,":[182],"investigate":[184],"complementarities":[188],"space":[195],"Building":[199],"upon":[200],"theoretical":[202],"foundations,":[203],"an":[206],"integrative":[207],"framework":[208],"that":[209],"combines":[210],"these":[211],"improved":[214],"effectiveness.":[216],"Furthermore,":[217],"slow":[221],"convergence":[222],"observed":[223],"Mosaic":[227,242],"aerial":[230],"imagery":[231],"introducing":[233],"multi-scale":[235],"training":[236],"strategy":[237],"proposing":[239],"full-scale":[241],"as":[244],"complement.":[246],"This":[247],"optimization":[248],"accelerates":[250],"network":[251],"convergence.":[252],"The":[253],"experimental":[254],"results":[255],"validate":[256],"our":[260],"proposed":[261],"highlight":[264],"its":[265],"potential":[266],"further":[268],"advancements":[269]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}