{"id":"https://openalex.org/W4414856548","doi":"https://doi.org/10.1109/tgrs.2025.3618269","title":"UMIS-YOLO: Underwater Multimodal Images Instance Segmentation With YOLO","display_name":"UMIS-YOLO: Underwater Multimodal Images Instance Segmentation With YOLO","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414856548","doi":"https://doi.org/10.1109/tgrs.2025.3618269"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2025.3618269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3618269","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":null,"display_name":"Yue Yang","orcid":"https://orcid.org/0009-0008-7643-3722"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Yang","raw_affiliation_strings":["School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0008-7643-3722","affiliations":[{"raw_affiliation_string":"School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101536090","display_name":"Xiaoyi Feng","orcid":"https://orcid.org/0000-0002-0428-6224"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyi Feng","raw_affiliation_strings":["School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-0144-8355"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]},{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210118728","display_name":"State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing","ror":"https://ror.org/02bpap860","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210118728"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["School of Robotics, Wuhan University, Wuhan, China","State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-0144-8355","affiliations":[{"raw_affiliation_string":"School of Robotics, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I196699116","https://openalex.org/I37461747"]},{"raw_affiliation_string":"State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4210118728"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102735163","display_name":"Xiangyun Hu","orcid":"https://orcid.org/0000-0003-3011-0983"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyun Hu","raw_affiliation_strings":["School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-3011-0983","affiliations":[{"raw_affiliation_string":"School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091592521","display_name":"Jiangying Qin","orcid":"https://orcid.org/0000-0002-7044-8105"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210118728","display_name":"State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing","ror":"https://ror.org/02bpap860","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210118728"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangying Qin","raw_affiliation_strings":["State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4210118728"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112591801","display_name":"Armin Gruen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Armin Gruen","raw_affiliation_strings":["Institute of Geodesy and Photogrammetry, ETH Zürich, Zürich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Geodesy and Photogrammetry, ETH Zürich, Zürich, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020355402","display_name":"Deren Li","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deren Li","raw_affiliation_strings":["School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100574336","display_name":"Jianya Gong","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianya Gong","raw_affiliation_strings":["School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6502,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.90211471,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"63","issue":null,"first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11698","display_name":"Underwater Acoustics Research","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11698","display_name":"Underwater Acoustics Research","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11192","display_name":"Underwater Vehicles and Communication Systems","score":0.9580000042915344,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/T12697","display_name":"Water Quality Monitoring Technologies","score":0.9320999979972839,"subfield":{"id":"https://openalex.org/subfields/2312","display_name":"Water Science and Technology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.73089998960495},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.602400004863739},{"id":"https://openalex.org/keywords/underwater","display_name":"Underwater","score":0.5817999839782715},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5698999762535095},{"id":"https://openalex.org/keywords/synthetic-aperture-radar","display_name":"Synthetic aperture radar","score":0.5357000231742859},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.49959999322891235},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4821000099182129},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.4699999988079071}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7893000245094299},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7857000231742859},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.73089998960495},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6144000291824341},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.602400004863739},{"id":"https://openalex.org/C98083399","wikidata":"https://www.wikidata.org/wiki/Q3246517","display_name":"Underwater","level":2,"score":0.5817999839782715},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5698999762535095},{"id":"https://openalex.org/C87360688","wikidata":"https://www.wikidata.org/wiki/Q740686","display_name":"Synthetic aperture radar","level":2,"score":0.5357000231742859},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.49959999322891235},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4821000099182129},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.4699999988079071},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.39750000834465027},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.37540000677108765},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tgrs.2025.3618269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3618269","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/G1141169320","display_name":null,"funder_award_id":"OCE 2224354","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6342734848","display_name":null,"funder_award_id":"62425102","funder_id":"https://openalex.org/F4320336125","funder_display_name":"National Science Fund for Distinguished Young Scholars"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320336125","display_name":"National Science Fund for Distinguished Young Scholars","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2000108174","https://openalex.org/W2027141008","https://openalex.org/W2194775991","https://openalex.org/W2963150697","https://openalex.org/W2989676862","https://openalex.org/W2993182889","https://openalex.org/W3014641072","https://openalex.org/W3039108591","https://openalex.org/W3046768359","https://openalex.org/W3106850582","https://openalex.org/W4311729059","https://openalex.org/W4313476004","https://openalex.org/W4382118992","https://openalex.org/W4384932254","https://openalex.org/W4385454320","https://openalex.org/W4390494417","https://openalex.org/W4390874273","https://openalex.org/W4391559729","https://openalex.org/W4392511248","https://openalex.org/W4394862642","https://openalex.org/W4395056520","https://openalex.org/W4396545724","https://openalex.org/W4396561387","https://openalex.org/W4398756379","https://openalex.org/W4399517126","https://openalex.org/W4400142372","https://openalex.org/W4402352247","https://openalex.org/W4406812022","https://openalex.org/W4406892479","https://openalex.org/W4409073263","https://openalex.org/W4411302755","https://openalex.org/W4413145332","https://openalex.org/W4415050881","https://openalex.org/W4415798746"],"related_works":[],"abstract_inverted_index":{"Underwater":[0],"instance":[1,13,42,75,113],"segmentation":[2,14,43,63,76,189,194,276],"plays":[3],"a":[4,72,89,175,199],"pivotal":[5],"role":[6],"in":[7,19,61,83,153,212],"various":[8],"applications.":[9],"Among":[10],"them,":[11],"coral":[12,35,214],"is":[15,29,81,268],"of":[16,22,34,53,112,150,165,231,246],"great":[17],"significance":[18],"the":[20,50,84,97,110,116,125,134,148,154,162,171,188,219,223,229,238,251,261,266,282],"fields":[21],"marine":[23],"biology":[24],"and":[25,28,55,105,133,167,183,208,243,248,258,274,281],"environmental":[26],"monitoring,":[27],"crucial":[30],"for":[31,40,101,222],"comprehensive":[32],"understanding":[33],"reef":[36],"ecosystems.":[37],"Traditional":[38],"methods":[39],"underwater":[41],"predominantly":[44],"rely":[45],"on":[46,250,260],"RGB":[47,103,206],"images.":[48],"However,":[49],"complex":[51,213],"morphology":[52],"corals":[54],"strong":[56],"background":[57],"interference":[58],"often":[59],"result":[60],"poor":[62],"outcomes.":[64],"To":[65],"tackle":[66],"these":[67],"problems,":[68],"this":[69],"study":[70],"presents":[71],"novel":[73],"multimodal":[74],"method,":[77],"termed":[78],"UMIS-YOLO,":[79],"which":[80,204],"grounded":[82],"YOLO":[85],"architecture.":[86],"UMIS-YOLO":[87,239],"incorporates":[88],"dual":[90],"backbone":[91],"network":[92],"design":[93],"that":[94,237],"substantially":[95],"enhances":[96],"feature":[98],"extraction":[99],"capabilities":[100],"both":[102,151],"images":[104,207,210,221],"depth":[106,209,220],"images,":[107],"thereby":[108,191],"improving":[109,192],"effectiveness":[111,230],"segmentation.":[114],"At":[115],"same":[117],"time,":[118],"we":[119,197,217],"propose":[120],"two":[121],"innovative":[122],"plug-and-play":[123],"modules:":[124],"Frequency":[126],"Domain":[127],"Feature":[128,136],"Enhancement":[129],"Fusion":[130,137],"(FDFEF)":[131],"module":[132,142,173],"Residual":[135],"(RFF)":[138],"module.":[139],"The":[140,233,278],"FDFEF":[141],"leverages":[143],"Fourier":[144],"transform":[145],"to":[146,160,179,187,226],"enhance":[147],"features":[149,185],"modalities":[152],"frequency":[155],"domain,":[156],"employing":[157],"learnable":[158],"weights":[159],"enable":[161],"complementary":[163],"integration":[164],"amplitude":[166],"phase":[168],"information.":[169],"While":[170],"RFF":[172],"utilizes":[174],"residual":[176],"learning":[177],"strategy":[178],"efficiently":[180],"merge":[181],"low-level":[182],"high-level":[184],"prior":[186],"head,":[190],"pixel-level":[193],"accuracy.":[195],"Additionally,":[196],"introduce":[198],"challenging":[200],"high-resolution":[201],"dataset,":[202,253,263],"UMIS-Coral,":[203],"comprises":[205],"captured":[211],"environments.":[215],"Meanwhile,":[216],"expand":[218],"UIIS":[224,262],"dataset":[225,283],"further":[227],"verify":[228],"UMIS-YOLO.":[232],"experimental":[234],"results":[235],"indicate":[236],"model":[240,267],"achieved":[241],"mAP50":[242],"mAP75":[244],"improvements":[245],"2.3":[247],"3.0":[249],"UMIS-Coral":[252],"as":[254,256],"well":[255],"3.9":[257],"2.8":[259],"respectively.":[264],"Furthermore,":[265],"characterized":[269],"by":[270],"its":[271],"lightweight":[272],"architecture":[273],"rapid":[275],"capabilities.":[277],"source":[279],"code":[280],"are":[284],"publicly":[285],"accessible":[286],"at":[287],"https://github.com/zhangsanhulk/UMIS-YOLO.":[288]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}