{"id":"https://openalex.org/W7147189313","doi":"https://doi.org/10.1109/iccbn67217.2025.11447526","title":"MMS-DETR: Fusing State Space Model and Mixed Aggregation for Small Object Detection on USVs","display_name":"MMS-DETR: Fusing State Space Model and Mixed Aggregation for Small Object Detection on USVs","publication_year":2025,"publication_date":"2025-11-27","ids":{"openalex":"https://openalex.org/W7147189313","doi":"https://doi.org/10.1109/iccbn67217.2025.11447526"},"language":null,"primary_location":{"id":"doi:10.1109/iccbn67217.2025.11447526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccbn67217.2025.11447526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 13th International Conference on Communications and Broadband Networking (ICCBN)","raw_type":"proceedings-article"},"type":"conference-paper","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":"Jizhang Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I96733725","display_name":"Shanghai Maritime University","ror":"https://ror.org/04z7qrj66","country_code":"CN","type":"education","lineage":["https://openalex.org/I96733725"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jizhang Luo","raw_affiliation_strings":["College of Information Engineering, Shanghai Maritime University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Engineering, Shanghai Maritime University,Shanghai,China","institution_ids":["https://openalex.org/I96733725"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132659478","display_name":"Feng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I96733725","display_name":"Shanghai Maritime University","ror":"https://ror.org/04z7qrj66","country_code":"CN","type":"education","lineage":["https://openalex.org/I96733725"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Liu","raw_affiliation_strings":["College of Information Engineering, Shanghai Maritime University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Engineering, Shanghai Maritime University,Shanghai,China","institution_ids":["https://openalex.org/I96733725"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I96733725"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"154","last_page":"159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8579999804496765,"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":0.8579999804496765,"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":0.06459999829530716,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.011500000022351742,"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/robustness","display_name":"Robustness (evolution)","score":0.6644999980926514},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6589000225067139},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6470999717712402},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4724000096321106},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.41370001435279846},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3718999922275543},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3675000071525574},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3425000011920929},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.33809998631477356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7271000146865845},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6644999980926514},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6589000225067139},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6470999717712402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.574999988079071},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4724000096321106},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4544000029563904},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.41370001435279846},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3675000071525574},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3425000011920929},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.33629998564720154},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.287200003862381},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2840999960899353},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2833999991416931},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.2669000029563904},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2531000077724457},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccbn67217.2025.11447526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccbn67217.2025.11447526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 13th International Conference on Communications and Broadband Networking (ICCBN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life below water","id":"https://metadata.un.org/sdg/14","score":0.8193638920783997}],"awards":[{"id":"https://openalex.org/G8296817548","display_name":null,"funder_award_id":"62271303","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W3042011474","https://openalex.org/W3096609285","https://openalex.org/W4206706211","https://openalex.org/W4210598935","https://openalex.org/W4221013072","https://openalex.org/W4385268303","https://openalex.org/W4386047745","https://openalex.org/W4402754006","https://openalex.org/W4402754177","https://openalex.org/W4405907339","https://openalex.org/W4413146579"],"related_works":[],"abstract_inverted_index":{"Unmanned":[0],"Surface":[1],"Vehicles(USVs)":[2],"are":[3],"playing":[4],"an":[5,75],"increasingly":[6],"crucial":[7],"role":[8],"in":[9,97,165,243],"key":[10],"areas":[11],"such":[12,30],"as":[13,31],"marine":[14],"monitoring":[15],"and":[16,19,23,34,58,65,177,219,229,234],"maritime":[17],"search":[18],"rescue.":[20],"The":[21],"accurate":[22],"realtime":[24],"detection":[25,83,246],"of":[26,109,122,138,185,193],"small":[27,35,81,194,244],"water-surface":[28],"objects,":[29],"persons":[32],"overboard":[33],"obstacles,":[36],"is":[37],"a":[38,153,172,178],"core":[39],"technical":[40],"bottleneck":[41],"for":[42,80],"achieving":[43],"autonomous":[44],"navigation.":[45],"Currently,":[46],"this":[47,71,131],"task":[48],"faces":[49],"severe":[50],"challenges,":[51],"including":[52],"minute":[53],"target":[54,195],"scales,":[55],"sparse":[56],"features,":[57],"complex":[59,148],"dynamic":[60],"background":[61],"interference":[62],"from":[63,147],"waves":[64],"reflections.":[66],"To":[67],"address":[68],"these":[69],"issues,":[70],"paper":[72],"proposes":[73],"MMS-DETR,":[74],"end-to-end":[76],"network":[77],"specifically":[78],"designed":[79,90],"object":[82,245],"on":[84,199,247],"the":[85,91,98,103,110,117,123,135,161,166,183,191,200,207,210],"water":[86,248],"surface.":[87],"First,":[88],"we":[89,151],"MambaVision":[92],"Cross":[93],"Stage":[94],"Partial(M-CSP)":[95],"module":[96,158,169],"backbone":[99],"network,":[100,175],"which":[101],"integrates":[102,171],"powerful":[104],"long-range":[105],"dependency":[106],"modeling":[107],"capability":[108],"Vision":[111],"State":[112],"Space":[113],"Model":[114],"(MambaVision)":[115],"with":[116],"efficient":[118],"feature":[119,163,186],"reuse":[120],"concept":[121],"CSP":[124],"architecture.":[125],"While":[126],"maintaining":[127],"high":[128],"computational":[129,230],"efficiency,":[130],"integration":[132],"significantly":[133],"enhances":[134],"model's":[136],"perception":[137],"global":[139],"context,":[140],"thereby":[141],"more":[142],"effectively":[143,189],"distinguishing":[144],"minuscule":[145],"targets":[146],"backgrounds.":[149],"Second,":[150],"introduced":[152],"Mixed":[154],"Aggregation":[155],"RepC":[156],"(MA-RepC)":[157],"to":[159,206,251],"optimize":[160],"multi-scale":[162],"fusion":[164],"neck.":[167],"This":[168],"deeply":[170],"mixed":[173],"aggregation":[174],"Faster-Block,":[176],"convolutional":[179],"gated":[180],"unit,":[181],"improving":[182],"robustness":[184],"representation":[187],"while":[188,226],"preventing":[190],"loss":[192],"information.":[196],"Experimental":[197],"results":[198],"Flow-Image":[201],"dataset":[202],"show":[203],"that,":[204],"compared":[205,250],"original":[208],"RT-DETR-r18,":[209],"proposed":[211],"model":[212],"improves":[213],"mAP":[214,220],"@":[215,221],"0.5":[216],"by":[217,224,232],"3.7%":[218],"0.5:":[222],"0.95":[223],"3.1%,":[225],"reducing":[227],"parameters":[228],"cost":[231],"19%":[233],"5.":[235],"6%,":[236],"respectively.":[237],"It":[238],"also":[239],"demonstrates":[240],"superior":[241],"performance":[242],"surfaces":[249],"other":[252],"mainstream":[253],"algorithms.":[254]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-04-02T00:00:00"}