{"id":"https://openalex.org/W7129493984","doi":"https://doi.org/10.1109/icipw68931.2025.11386248","title":"Usodfusenet - A Novel Underwater Salient Object Detection Model","display_name":"Usodfusenet - A Novel Underwater Salient Object Detection Model","publication_year":2025,"publication_date":"2025-09-14","ids":{"openalex":"https://openalex.org/W7129493984","doi":"https://doi.org/10.1109/icipw68931.2025.11386248"},"language":null,"primary_location":{"id":"doi:10.1109/icipw68931.2025.11386248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icipw68931.2025.11386248","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 Image Processing Workshops (ICIPW)","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":"https://openalex.org/A5001523248","display_name":"Rohit Venkata Sai Dulam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162663","display_name":"Chemical Synthesis Lab","ror":"https://ror.org/04kbbt849","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210105704","https://openalex.org/I4210162663","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rohit Venkata Sai Dulam","raw_affiliation_strings":["University of Delaware,Video/Image Modeling and Synthesis (VIMS)Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Delaware,Video/Image Modeling and Synthesis (VIMS)Lab","institution_ids":["https://openalex.org/I4210162663"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076482730","display_name":"Chandra Kambhamettu","orcid":"https://orcid.org/0000-0001-5306-3994"},"institutions":[{"id":"https://openalex.org/I4210162663","display_name":"Chemical Synthesis Lab","ror":"https://ror.org/04kbbt849","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210105704","https://openalex.org/I4210162663","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chandra Kambhamettu","raw_affiliation_strings":["University of Delaware,Video/Image Modeling and Synthesis (VIMS)Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Delaware,Video/Image Modeling and Synthesis (VIMS)Lab","institution_ids":["https://openalex.org/I4210162663"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210162663"],"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":"386","last_page":"391"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.7577999830245972,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.7577999830245972,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.11919999867677689,"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":0.06769999861717224,"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/object-detection","display_name":"Object detection","score":0.692799985408783},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6743000149726868},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5313000082969666},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5188999772071838},{"id":"https://openalex.org/keywords/underwater","display_name":"Underwater","score":0.4934000074863434},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.4332999885082245},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.364300012588501},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3278000056743622}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7664999961853027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.748199999332428},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.692799985408783},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6743000149726868},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5791000127792358},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5313000082969666},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5188999772071838},{"id":"https://openalex.org/C98083399","wikidata":"https://www.wikidata.org/wiki/Q3246517","display_name":"Underwater","level":2,"score":0.4934000074863434},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4332999885082245},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.364300012588501},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.3068999946117401},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2777000069618225},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2752000093460083},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icipw68931.2025.11386248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icipw68931.2025.11386248","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 Image Processing Workshops (ICIPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7724621295928955,"display_name":"Life below water","id":"https://metadata.un.org/sdg/14"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W20683899","https://openalex.org/W1976409045","https://openalex.org/W1993713494","https://openalex.org/W2020950478","https://openalex.org/W2437820655","https://openalex.org/W2893858645","https://openalex.org/W2963529609","https://openalex.org/W2963868681","https://openalex.org/W2998449272","https://openalex.org/W3035422681","https://openalex.org/W3170173308","https://openalex.org/W3173370190","https://openalex.org/W3173382343","https://openalex.org/W3203718853","https://openalex.org/W3206198586","https://openalex.org/W3207493400","https://openalex.org/W4214561053","https://openalex.org/W4283784160","https://openalex.org/W4315606099","https://openalex.org/W4362496243","https://openalex.org/W4365479090","https://openalex.org/W4386072314","https://openalex.org/W4392152057","https://openalex.org/W4392450014","https://openalex.org/W4392824656","https://openalex.org/W4402660119","https://openalex.org/W4402727868","https://openalex.org/W4405139156","https://openalex.org/W4405778882"],"related_works":[],"abstract_inverted_index":{"Underwater":[0],"salient":[1],"object":[2],"detection":[3],"(USOD)":[4],"is":[5,138],"essential":[6],"for":[7,129],"improving":[8],"underwater":[9],"exploration":[10],"and":[11,42,69,106,132],"autonomous":[12],"navigation.":[13],"Many":[14],"existing":[15],"USOD":[16],"methods":[17,52],"rely":[18],"on":[19,28,66,83,103],"large,":[20],"computationally":[21],"intensive":[22],"models,":[23,60],"which":[24],"limits":[25],"their":[26],"use":[27,54],"resource-constrained":[29],"platforms.":[30],"We":[31],"present":[32],"USODFuseNet,":[33],"a":[34,46],"lightweight":[35],"dual-encoder":[36],"model":[37,79],"that":[38,53,118],"efficiently":[39],"combines":[40],"RGB":[41],"depth":[43],"features":[44],"through":[45],"progressive":[47],"fusion":[48],"mechanism.":[49],"Unlike":[50],"previous":[51],"generic":[55],"ImageNet":[56],"or":[57],"large":[58,123],"vision":[59],"our":[61,78],"architecture":[62],"uses":[63],"backbones":[64],"pretrained":[65],"the":[67,84,94,127],"COCO":[68],"OpenImages":[70],"datasets.":[71],"Despite":[72],"being":[73,89],"less":[74],"compute-intensive":[75],"than":[76,93],"Dual-SAM,":[77],"achieves":[80],"state-of-the-art":[81],"performance":[82],"USOD10K":[85],"dataset.":[86],"Furthermore,":[87],"despite":[88],"four":[90],"times":[91],"smaller":[92],"leading":[95],"RGB-D":[96],"model,":[97],"VSCode,":[98],"we":[99],"maintain":[100],"top":[101],"results":[102,116],"NJU2K,":[104],"NLPR,":[105],"STERE":[107],"datasets":[108],"with":[109],"only":[110],"118":[111],"MB":[112],"of":[113],"parameters.":[114],"These":[115],"highlight":[117],"task-specific":[119],"architectures":[120],"can":[121],"rival":[122],"deep":[124],"networks,":[125],"paving":[126],"way":[128],"more":[130],"efficient":[131],"interpretable":[133],"saliency":[134],"models.":[135],"The":[136],"code":[137],"available":[139],"here.":[140]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-02-18T00:00:00"}