{"id":"https://openalex.org/W4414140852","doi":"https://doi.org/10.1109/icmew68306.2025.11152273","title":"FusionAttNet: A Water Surface Object Detection Model with Dynamic Fusion and Cross-Modal Attention","display_name":"FusionAttNet: A Water Surface Object Detection Model with Dynamic Fusion and Cross-Modal Attention","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4414140852","doi":"https://doi.org/10.1109/icmew68306.2025.11152273"},"language":"en","primary_location":{"id":"doi:10.1109/icmew68306.2025.11152273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew68306.2025.11152273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","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/A5013525368","display_name":"Jinan Guan","orcid":"https://orcid.org/0000-0003-1094-733X"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingge Guan","raw_affiliation_strings":["Xidian University,School of Electronic Engineering,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Xidian University,School of Electronic Engineering,Xi’an,China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100690519","display_name":"Bing Han","orcid":"https://orcid.org/0000-0002-6526-4432"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Han","raw_affiliation_strings":["Xidian University,School of Electronic Engineering,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Xidian University,School of Electronic Engineering,Xi’an,China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101313930","display_name":"Xinbo Gao","orcid":"https://orcid.org/0000-0002-7985-0037"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinbo Gao","raw_affiliation_strings":["Xidian University,School of Electronic Engineering,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Xidian University,School of Electronic Engineering,Xi’an,China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011145004","display_name":"Zhi\u2010Hui Zhan","orcid":"https://orcid.org/0000-0003-0862-0514"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi-Hui Zhan","raw_affiliation_strings":["Nankai University,College of Artificial Intelligence,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Nankai University,College of Artificial Intelligence,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5013525368"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23031454,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9980999827384949,"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":0.9980999827384949,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9886000156402588,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12697","display_name":"Water Quality Monitoring Technologies","score":0.9830999970436096,"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/object-detection","display_name":"Object detection","score":0.7386999726295471},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6281999945640564},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5855000019073486},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5550000071525574},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5267000198364258},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5167999863624573},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4699000120162964},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4505999982357025},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.43540000915527344},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3986999988555908}],"concepts":[{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7386999726295471},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7264999747276306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7041000127792358},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6281999945640564},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6279000043869019},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5855000019073486},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5550000071525574},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5267000198364258},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5167999863624573},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4699000120162964},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4505999982357025},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.43540000915527344},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3986999988555908},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.366100013256073},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3222000002861023},{"id":"https://openalex.org/C2776799497","wikidata":"https://www.wikidata.org/wiki/Q484298","display_name":"Surface (topology)","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.3005000054836273},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.29600000381469727},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.29440000653266907},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.28690001368522644},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2565999925136566},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmew68306.2025.11152273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew68306.2025.11152273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322857","display_name":"Aeronautical Science Foundation of China","ror":"https://ror.org/02wq41p38"},{"id":"https://openalex.org/F4320329783","display_name":"Key Industry Innovation Chain of Shaanxi","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1975104905","https://openalex.org/W2294752183","https://openalex.org/W2333417593","https://openalex.org/W2549139847","https://openalex.org/W3034971973","https://openalex.org/W3038288066","https://openalex.org/W3080711308","https://openalex.org/W3092365515","https://openalex.org/W3096609285","https://openalex.org/W3114992566","https://openalex.org/W3122239467","https://openalex.org/W3138516171","https://openalex.org/W3174904875","https://openalex.org/W3203188564","https://openalex.org/W3204885083","https://openalex.org/W4221146106","https://openalex.org/W4226224676","https://openalex.org/W4312956471","https://openalex.org/W4386065815","https://openalex.org/W4386076222","https://openalex.org/W4386159748","https://openalex.org/W4387855642","https://openalex.org/W4390873750","https://openalex.org/W4400035744","https://openalex.org/W4401991026","https://openalex.org/W4402716047","https://openalex.org/W4404303854","https://openalex.org/W4408353014","https://openalex.org/W4412651483"],"related_works":["https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W2737719445","https://openalex.org/W2099421762","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Water":[0],"surface":[1,48],"object":[2,49,60],"detection":[3,50,61,86],"is":[4,73,98],"critical":[5],"to":[6,36,75,100,134],"the":[7,11,110],"intelligent":[8],"advancement":[9],"of":[10,87,112,126],"shipping":[12],"industry,":[13],"with":[14],"extensive":[15],"military":[16],"and":[17,34,56,68,80,114,128,148],"civilian":[18],"applications.":[19],"However,":[20],"existing":[21],"methods":[22],"face":[23],"challenges":[24],"in":[25,31,145],"detecting":[26,146],"small,":[27],"densely":[28],"distributed":[29],"objects":[30,150],"complex":[32],"environments":[33],"generalizing":[35],"real-world":[37],"scenarios.":[38],"To":[39],"address":[40],"these":[41],"issues,":[42],"we":[43],"propose":[44],"FusionAttNet,":[45],"a":[46,66,118],"water":[47],"model":[51],"that":[52,140],"integrates":[53],"dynamic":[54,70],"fusion":[55,71],"cross-modal":[57,120],"attention,":[58],"enabling":[59],"under":[62],"text":[63],"guidance.":[64],"Specifically,":[65],"convolution":[67],"self-attention":[69],"module":[72,97,122],"incorporated":[74],"simultaneously":[76],"capture":[77],"local":[78],"details":[79],"global":[81],"context":[82],"information,":[83],"ensuring":[84],"precise":[85],"multi-scale":[88],"objects.":[89,116],"An":[90],"aggregation":[91],"based":[92],"on":[93],"shared":[94],"attention":[95,121],"matching":[96],"introduced":[99],"adaptively":[101],"select":[102],"key":[103],"features":[104],"while":[105,151],"suppressing":[106],"background":[107],"noise,":[108],"enhancing":[109],"perception":[111],"small":[113,147],"dense":[115,149],"Additionally,":[117],"dual-way":[119],"facilitates":[123],"deep":[124],"integration":[125],"visual":[127],"linguistic":[129],"features,":[130],"significantly":[131],"improving":[132],"generalization":[133,154],"unseen":[135],"categories.":[136],"Experimental":[137],"results":[138],"show":[139],"FusionAttNet":[141],"achieves":[142],"superior":[143],"performance":[144],"exhibiting":[152],"strong":[153],"capabilities,":[155],"validating":[156],"its":[157],"effectiveness.":[158]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}