{"id":"https://openalex.org/W4415538861","doi":"https://doi.org/10.1145/3746027.3758220","title":"UEMM-Air: Enable UAVs to Undertake More Multi-modal Tasks","display_name":"UEMM-Air: Enable UAVs to Undertake More Multi-modal Tasks","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538861","doi":"https://doi.org/10.1145/3746027.3758220"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3758220","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-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/A5113012148","display_name":"Lin Yao","orcid":"https://orcid.org/0000-0002-4588-3658"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Yao","raw_affiliation_strings":["Hohai University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-4588-3658","affiliations":[{"raw_affiliation_string":"Hohai University, Nanjing, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371024","display_name":"Fan Liu","orcid":"https://orcid.org/0000-0001-8746-9845"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Liu","raw_affiliation_strings":["Hohai University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-8746-9845","affiliations":[{"raw_affiliation_string":"Hohai University, Nanjing, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103689239","display_name":"S N Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengxiang Xu","raw_affiliation_strings":["Hohai University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0003-4964-8406","affiliations":[{"raw_affiliation_string":"Hohai University, Nanjing, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101465467","display_name":"Chuanyi Zhang","orcid":"https://orcid.org/0000-0001-8724-5796"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanyi Zhang","raw_affiliation_strings":["Hohai University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-8724-5796","affiliations":[{"raw_affiliation_string":"Hohai University, Nanjing, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006260400","display_name":"Shimin Di","orcid":"https://orcid.org/0000-0002-7394-0082"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shimin Di","raw_affiliation_strings":["Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-7394-0082","affiliations":[{"raw_affiliation_string":"Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100564697","display_name":"Xing Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Ma","raw_affiliation_strings":["Hohai University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0005-7059-2317","affiliations":[{"raw_affiliation_string":"Hohai University, Nanjing, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianyu Jiang","orcid":"https://orcid.org/0009-0001-4053-6227"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianyu Jiang","raw_affiliation_strings":["Hohai University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0001-4053-6227","affiliations":[{"raw_affiliation_string":"Hohai University, Nanjing, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029552982","display_name":"Z. X. Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zequan Wang","raw_affiliation_strings":["Hohai University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0005-3031-0848","affiliations":[{"raw_affiliation_string":"Hohai University, Nanjing, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100781212","display_name":"Jun Zhou","orcid":"https://orcid.org/0000-0001-5822-8233"},"institutions":[{"id":"https://openalex.org/I11701301","display_name":"Griffith University","ror":"https://ror.org/02sc3r913","country_code":"AU","type":"education","lineage":["https://openalex.org/I11701301"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jun Zhou","raw_affiliation_strings":["Griffith University, Nathan, Australia"],"raw_orcid":"https://orcid.org/0000-0001-5822-8233","affiliations":[{"raw_affiliation_string":"Griffith University, Nathan, Australia","institution_ids":["https://openalex.org/I11701301"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5311,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.85451804,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"12792","last_page":"12798"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.996399998664856,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.996399998664856,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9957000017166138,"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/T11133","display_name":"UAV Applications and Optimization","score":0.9854999780654907,"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/modalities","display_name":"Modalities","score":0.6407999992370605},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6194000244140625},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5950000286102295},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5508999824523926},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5407000184059143},{"id":"https://openalex.org/keywords/license","display_name":"License","score":0.46700000762939453},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.396699994802475},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.3702999949455261},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.35850000381469727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6912999749183655},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6407999992370605},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6194000244140625},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5950000286102295},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5508999824523926},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5407000184059143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5022000074386597},{"id":"https://openalex.org/C2780560020","wikidata":"https://www.wikidata.org/wiki/Q79719","display_name":"License","level":2,"score":0.46700000762939453},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4374000132083893},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.35850000381469727},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.35089999437332153},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3352000117301941},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33239999413490295},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2809000015258789},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3758220","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7400425163","display_name":null,"funder_award_id":"62372155","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2999545631","https://openalex.org/W3183898570","https://openalex.org/W4287322212","https://openalex.org/W4323767874","https://openalex.org/W4366598917","https://openalex.org/W4382236920","https://openalex.org/W4387653592","https://openalex.org/W4388039304","https://openalex.org/W4390189932","https://openalex.org/W4396232007","https://openalex.org/W4403991011","https://openalex.org/W4409796197","https://openalex.org/W4415537011"],"related_works":[],"abstract_inverted_index":{"The":[0,173],"development":[1],"of":[2,153],"multi-modal":[3,48,155,171],"Unmanned":[4],"Aerial":[5],"Vehicles":[6],"(UAVs)":[7],"environment":[8,50],"perception":[9,51,91,157],"systems":[10],"is":[11],"hindered":[12],"by":[13,116],"three":[14],"critical":[15],"gaps":[16],"in":[17],"existing":[18,95,106],"datasets:":[19],"(1)":[20],"insufficient":[21],"modalities":[22,87],"and":[23,29,45,60,76,88,159,175],"pixel":[24],"misalignment,":[25],"(2)":[26],"noisy":[27,118],"labels,":[28],"(3)":[30],"limited":[31],"task":[32],"types.":[33],"To":[34],"address":[35],"these":[36],"gaps,":[37],"we":[38],"propose":[39],"an":[40],"automatic":[41],"data":[42,74,82],"construction":[43],"approach":[44],"construct":[46],"a":[47,130,183],"UAV-based":[49],"dataset,":[52],"UEMM-Air.":[53],"Its":[54],"synthetic":[55,107,139],"nature":[56],"ensures":[57],"scalability,":[58],"reproducibility,":[59],"rare-event":[61],"coverage,":[62],"making":[63],"it":[64],"suitable":[65],"for":[66],"large-scale":[67],"model":[68],"pre-training.":[69],"Benefiting":[70],"from":[71,120],"our":[72],"automated":[73],"collection":[75],"annotation":[77],"pipeline,":[78],"UEMM-Air":[79,111,128],"encompasses":[80],"120k":[81],"pairs":[83],"across":[84],"6":[85],"aligned":[86],"supports":[89],"4":[90],"tasks,":[92],"significantly":[93],"exceeding":[94],"datasets":[96,108],"(max":[97],"60k":[98],"data,":[99],"3":[100],"modalities,":[101],"2":[102],"tasks).":[103],"Compared":[104],"to":[105,135,168],"like":[109],"SynDrone,":[110],"provides":[112],"more":[113,162,170],"accurate":[114],"annotations":[115],"avoiding":[117],"labels":[119],"direct":[121],"coordinate":[122],"computation.":[123],"Notably,":[124],"models":[125],"pre-trained":[126],"on":[127],"achieve":[129],"5.8%":[131],"accuracy":[132],"improvement":[133],"compared":[134],"those":[136],"utilizing":[137],"other":[138],"datasets,":[140],"while":[141],"requiring":[142],"less":[143],"than":[144],"half":[145],"the":[146],"data.":[147],"This":[148],"benchmark":[149],"establishes":[150],"performance":[151],"evaluation":[152],"UAV":[154],"environmental":[156],"models,":[158],"hopefully":[160],"encourages":[161],"research":[163],"efforts":[164],"towards":[165],"enabling":[166],"UAVs":[167],"undertake":[169],"tasks.":[172],"dataset":[174],"its":[176],"generation":[177],"engine":[178],"are":[179],"openly":[180],"accessible":[181],"under":[182],"permissive":[184],"license":[185],"at":[186],"https://github.com/1e12Leon/UEMM-Air.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-25T00:00:00"}