{"id":"https://openalex.org/W7204449429","doi":"https://doi.org/10.48550/arxiv.2608.25367","title":"RSFusionDet: Underwater RGB-Sonar Multimodal Object Detection","display_name":"RSFusionDet: Underwater RGB-Sonar Multimodal Object Detection","publication_year":2026,"publication_date":"2026-08-26","ids":{"openalex":"https://openalex.org/W7204449429","doi":"https://doi.org/10.48550/arxiv.2608.25367"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.25367","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.25367","pdf_url":"https://arxiv.org/pdf/2608.25367","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.25367","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068517649","display_name":"Zhuoyan Liu","orcid":"https://orcid.org/0009-0001-0312-7854","observed_orcids":["https://orcid.org/0009-0001-0312-7854"]},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Zhuoyan","raw_affiliation_strings":["National Key Laboratory of Autonomous Marine Vehicle Technology , Harbin Engineering University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Autonomous Marine Vehicle Technology , Harbin Engineering University","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130844559","display_name":"Yihan Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Yihan","raw_affiliation_strings":["National Key Laboratory of Autonomous Marine Vehicle Technology , Harbin Engineering University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Autonomous Marine Vehicle Technology , Harbin Engineering University","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148884913","display_name":"Bo Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]},{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Wang, Bo","raw_affiliation_strings":["Department of Aeronautical and Aviation Engineering , Hong Kong Polytechnic University","National Key Laboratory of Autonomous Marine Vehicle Technology , Harbin Engineering University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Aeronautical and Aviation Engineering , Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"National Key Laboratory of Autonomous Marine Vehicle Technology , Harbin Engineering University","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122549985","display_name":"Bing Wang","orcid":"https://orcid.org/0000-0003-4621-9115","observed_orcids":["https://orcid.org/0000-0003-4621-9115"]},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]},{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Wang, Bing","raw_affiliation_strings":["Department of Aeronautical and Aviation Engineering , Hong Kong Polytechnic University","National Key Laboratory of Autonomous Marine Vehicle Technology , Harbin Engineering University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Aeronautical and Aviation Engineering , Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"National Key Laboratory of Autonomous Marine Vehicle Technology , Harbin Engineering University","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122461780","display_name":"Ye Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Ye","raw_affiliation_strings":["National Key Laboratory of Autonomous Marine Vehicle Technology , Harbin Engineering University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Autonomous Marine Vehicle Technology , Harbin Engineering University","institution_ids":["https://openalex.org/I151727225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.3970000147819519,"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":0.3970000147819519,"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/T11192","display_name":"Underwater Vehicles and Communication Systems","score":0.23270000517368317,"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/T11698","display_name":"Underwater Acoustics Research","score":0.19210000336170197,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/underwater-object-detection","display_name":"underwater object detection","score":0.9879999756813049},{"id":"https://openalex.org/keywords/multimodal-object-detection","display_name":"multimodal object detection","score":0.9700000286102295},{"id":"https://openalex.org/keywords/sonar-imagery","display_name":"sonar images","score":0.7009999752044678},{"id":"https://openalex.org/keywords/underwater-imaging","display_name":"underwater imaging","score":0.5289999842643738},{"id":"https://openalex.org/keywords/cross-attention-fusion","display_name":"cross-attention fusion","score":0.7639999985694885},{"id":"https://openalex.org/keywords/multimodal-dataset","display_name":"multimodal dataset","score":0.6150000095367432}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.8036999702453613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7730000019073486},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7416999936103821},{"id":"https://openalex.org/C555745239","wikidata":"https://www.wikidata.org/wiki/Q133220","display_name":"Sonar","level":2,"score":0.7240999937057495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6765000224113464},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6722999811172485},{"id":"https://openalex.org/C98083399","wikidata":"https://www.wikidata.org/wiki/Q3246517","display_name":"Underwater","level":2,"score":0.623199999332428},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.5295000076293945},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.510699987411499},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.45969998836517334},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.39579999446868896},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3747999966144562},{"id":"https://openalex.org/C123403432","wikidata":"https://www.wikidata.org/wiki/Q654068","display_name":"Visibility","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.357699990272522},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.34439998865127563},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.28769999742507935},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.26600000262260437},{"id":"https://openalex.org/C14551309","wikidata":"https://www.wikidata.org/wiki/Q4636325","display_name":"3D single-object recognition","level":4,"score":0.2644999921321869},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C53073257","wikidata":"https://www.wikidata.org/wiki/Q7075021","display_name":"Object-oriented design","level":3,"score":0.2538999915122986}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.25367","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.25367","pdf_url":"https://arxiv.org/pdf/2608.25367","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.25367","doi":"https://doi.org/10.48550/arxiv.2608.25367","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.25367","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.25367","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.25367","pdf_url":"https://arxiv.org/pdf/2608.25367","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1530759603","display_name":null,"funder_award_id":"52371350","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G1636187402","display_name":null,"funder_award_id":"2023YFC2809104","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6041615479","display_name":null,"funder_award_id":"2023YFC2809104","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G920824821","display_name":null,"funder_award_id":"52371350","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204449429.pdf","grobid_xml":"https://content.openalex.org/works/W7204449429.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W2796347433","https://openalex.org/W2950141105","https://openalex.org/W3037932933","https://openalex.org/W3184439416"],"related_works":["https://openalex.org/W7131097464","https://openalex.org/W7167275272","https://openalex.org/W7164759926","https://openalex.org/W7128495183","https://openalex.org/W7204263641","https://openalex.org/W7222794460","https://openalex.org/W7202160015","https://openalex.org/W7167689281","https://openalex.org/W7162294974","https://openalex.org/W4410300962"],"abstract_inverted_index":{"Underwater":[0],"unimodal":[1],"object":[2,27,35,73,99,106,153,159,166,186],"detection":[3,74,100,154,167],"faces":[4],"many":[5],"challenges":[6],"in":[7,143],"sensor":[8],"imaging,":[9],"such":[10],"as":[11],"optical":[12,31],"images":[13,23,32,40,60],"limited":[14,24],"by":[15,25,44,177],"underwater":[16,45],"noise":[17,46],"and":[18,21,38,47,56,79,114,118,131,155,190],"visible":[19,51],"distance,":[20],"sonar":[22,39,57],"less":[26,42],"structural":[28,36],"information.":[29],"While,":[30],"have":[33,48,61],"rich":[34],"information,":[37,117],"are":[41,192],"affected":[43],"a":[49,95,120],"longer":[50],"distance.":[52],"Optical":[53],"(RGB":[54],"modality)":[55,59],"(Sonar":[58],"complementary":[62],"information":[63],"underwater.":[64],"In":[65],"this":[66],"paper,":[67],"we":[68,87],"create":[69],"an":[70],"RGB-Sonar":[71,97,104,127,144],"multimodal":[72,98,105],"dataset,":[75],"\\textbf{R}GB-\\textbf{S}onar":[76,90],"\\textbf{Fusion}":[77,91],"(RSFusion)":[78],"propose":[80,88],"evaluation":[81],"metrics":[82],"for":[83,103,152,158],"the":[84,89,110,171],"benchmark.":[85],"And":[86],"\\textbf{Det}ector":[92],"(RSFusionDet)":[93],"with":[94,136,170],"new":[96],"result":[101],"expression":[102],"detection.":[107],"We":[108],"analyze":[109],"features":[111,130],"of":[112],"RGB":[113],"Sonar":[115],"modal":[116],"design":[119],"Cross-Attention":[121],"Fusion":[122],"(CAFusion)":[123],"module":[124],"to":[125,139],"fuse":[126],"spatial":[128],"misalignment":[129],"Object":[132],"Matching":[133],"Head":[134],"(OMHead)":[135],"Loss":[137],"(OMLoss)":[138],"match":[140],"identical":[141],"objects":[142],"modalities.":[145],"Our":[146],"RSFusionDet":[147],"achieves":[148],"76.4/48.6":[149],"AP":[150,179],"(RGB/Sonar)":[151,180],"83.4":[156],"\\(\\text{F1-Score}_{match}\\)":[157],"matching,":[160],"on":[161],"RSFusion,":[162],"which":[163],"outperforms":[164],"other":[165],"models.":[168],"Compared":[169],"DINO":[172],"baseline,":[173],"our":[174],"method":[175],"improves":[176],"0.7/1.4":[178],"while":[181],"simultaneously":[182],"providing":[183],"reliable":[184],"cross-modal":[185],"matching.":[187],"The":[188],"code":[189],"datasets":[191],"publicly":[193],"available":[194],"at":[195],"https://github.com/LEFTeyex/RSFusionDet.":[196]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-28T00:00:00"}
