{"id":"https://openalex.org/W4415536853","doi":"https://doi.org/10.1145/3746027.3755467","title":"FSCDiff: Frequency-Spatial Entangled Conditional Diffusion model for Underwater Salient Object Detection","display_name":"FSCDiff: Frequency-Spatial Entangled Conditional Diffusion model for Underwater Salient Object Detection","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536853","doi":"https://doi.org/10.1145/3746027.3755467"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755467","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755467","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5078094074","display_name":"Hua Li","orcid":"https://orcid.org/0000-0003-0740-0691"},"institutions":[{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hua Li","raw_affiliation_strings":["Hainan University, Haikou, China"],"raw_orcid":"https://orcid.org/0000-0003-0740-0691","affiliations":[{"raw_affiliation_string":"Hainan University, Haikou, China","institution_ids":["https://openalex.org/I20942203"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Gaowei Lin","orcid":"https://orcid.org/0009-0001-1511-0646"},"institutions":[{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaowei Lin","raw_affiliation_strings":["Hainan University, Haikou, China"],"raw_orcid":"https://orcid.org/0009-0001-1511-0646","affiliations":[{"raw_affiliation_string":"Hainan University, Haikou, China","institution_ids":["https://openalex.org/I20942203"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004360977","display_name":"Zhiyuan Li","orcid":"https://orcid.org/0009-0009-2804-376X"},"institutions":[{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Li","raw_affiliation_strings":["Hainan University, Haikou, China"],"raw_orcid":"https://orcid.org/0009-0009-2804-376X","affiliations":[{"raw_affiliation_string":"Hainan University, Haikou, China","institution_ids":["https://openalex.org/I20942203"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008386708","display_name":"Sam Kwong","orcid":"https://orcid.org/0000-0001-7484-7261"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sam Kwong","raw_affiliation_strings":["Lingnan University, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-7484-7261","affiliations":[{"raw_affiliation_string":"Lingnan University, Hong Kong, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091558139","display_name":"Runmin Cong","orcid":"https://orcid.org/0000-0003-0972-4008"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runmin Cong","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0003-0972-4008","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5078094074"],"corresponding_institution_ids":["https://openalex.org/I20942203"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29551017,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8379","last_page":"8388"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11698","display_name":"Underwater Acoustics Research","score":0.9907000064849854,"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":0.9907000064849854,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9882000088691711,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.9835000038146973,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.70660001039505},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6115000247955322},{"id":"https://openalex.org/keywords/underwater","display_name":"Underwater","score":0.5867000222206116},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.580299973487854},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45190000534057617},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.42179998755455017},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4205999970436096},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4146000146865845},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.3871000111103058}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7245000004768372},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.70660001039505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6665999889373779},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6115000247955322},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.611299991607666},{"id":"https://openalex.org/C98083399","wikidata":"https://www.wikidata.org/wiki/Q3246517","display_name":"Underwater","level":2,"score":0.5867000222206116},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.580299973487854},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45190000534057617},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.42179998755455017},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4205999970436096},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4146000146865845},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3725999891757965},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.34549999237060547},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.34360000491142273},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3353999853134155},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3312999904155731},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.2759000062942505},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2685000002384186},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.25780001282691956},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755467","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755467","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2982993655","https://openalex.org/W3175515048","https://openalex.org/W4391468387","https://openalex.org/W4393156066","https://openalex.org/W4394773652","https://openalex.org/W4407614753"],"related_works":[],"abstract_inverted_index":{"Salient":[0],"object":[1,27,41,70,87],"detection":[2,28,88],"(SOD)":[3],"plays":[4],"a":[5,59],"crucial":[6],"role":[7],"in":[8,84],"image":[9],"understanding":[10],"and":[11,36,80,93,117,135,142,165,186],"visual":[12],"guidance.":[13],"However,":[14],"due":[15],"to":[16,75,130,161],"the":[17,22,34,45,77,94,111,118,133,153,163,168,180,184],"complexity":[18],"of":[19,24,38,100,107,139,152,158,167],"underwater":[20,25,39,68,85],"environments,":[21],"accuracy":[23,35,164],"salient":[26,40,69,86],"is":[29,192],"often":[30],"low.":[31],"To":[32],"improve":[33],"robustness":[37,166],"detection,":[42],"different":[43],"from":[44],"existing":[46],"spatial":[47,136],"domain":[48,137],"aware":[49],"RGB-D":[50],"methods":[51],"that":[52,175],"rely":[53],"on":[54,183],"pixel-level":[55],"probabilities,":[56],"we":[57],"propose":[58],"novel":[60],"Fourier-Spatial":[61],"Entangled":[62],"Conditional":[63],"Diffusion":[64],"model":[65],"(FSCDiff)":[66],"for":[67],"detection.":[71],"The":[72,103,189],"FSCDiff":[73,104,177],"aims":[74],"address":[76],"insufficient":[78],"representation":[79],"boundary":[81],"shift":[82],"issues":[83],"by":[89],"leveraging":[90],"Fourier-domain":[91],"information":[92,138],"powerful":[95],"multi-step":[96,155],"iterative":[97,156],"generation":[98],"capability":[99],"diffusion":[101,159],"models.":[102],"framework":[105],"consists":[106],"two":[108],"key":[109],"components:":[110],"Dual-Domain":[112],"Entanglement":[113],"Enhancement":[114],"Block":[115],"(DTEB)":[116],"Stable":[119],"Time-step":[120],"Mask":[121],"Prediction":[122],"Module":[123],"(STMP).":[124],"DTEB":[125],"utilizes":[126],"Fourier-spatial":[127],"entanglement":[128],"learning":[129],"fully":[131],"exploit":[132],"Fourier":[134],"RGB":[140],"images":[141],"depth":[143],"maps,":[144],"thereby":[145],"optimizing":[146],"feature":[147],"representation.":[148],"STMP":[149],"takes":[150],"advantage":[151],"excellent":[154],"mechanism":[157],"models":[160],"enhance":[162],"segmentation":[169],"results.":[170],"Comprehensive":[171],"experimental":[172],"results":[173],"indicate":[174],"our":[176],"method":[178],"outperforms":[179],"state-of-the-art":[181],"approaches":[182],"USOD10K":[185],"USOD":[187],"datasets.":[188],"source":[190],"code":[191],"available":[193],"at:":[194],"https://github.com/lgwplay/FSCDiff.":[195]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}