{"id":"https://openalex.org/W4410253654","doi":"https://doi.org/10.1109/tip.2026.3698359","title":"Marine Saliency Segmenter: Object-Focused Conditional Diffusion With Region-Level Semantic Knowledge Distillation","display_name":"Marine Saliency Segmenter: Object-Focused Conditional Diffusion With Region-Level Semantic Knowledge Distillation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4410253654","doi":"https://doi.org/10.1109/tip.2026.3698359","pmid":"https://pubmed.ncbi.nlm.nih.gov/42241268"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3698359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3698359","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.02391","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072913037","display_name":"Laibin Chang","orcid":"https://orcid.org/0000-0002-6510-4359"},"institutions":[{"id":"https://openalex.org/I117357259","display_name":"National Institute of Japanese Literature","ror":"https://ror.org/01464wm64","country_code":"JP","type":"archive","lineage":["https://openalex.org/I117357259","https://openalex.org/I1319490839","https://openalex.org/I4210148627"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Laibin Chang","raw_affiliation_strings":["School of Computer Science, Institute of Artificial Intelligence, National Engineering Research Center for Multimedia Software, and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-6510-4359","affiliations":[{"raw_affiliation_string":"School of Computer Science, Institute of Artificial Intelligence, National Engineering Research Center for Multimedia Software, and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I117357259"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077062257","display_name":"Yunke Wang","orcid":"https://orcid.org/0009-0003-9796-530X"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yunke Wang","raw_affiliation_strings":["School of Computer Science, The University of Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0009-0003-9796-530X","affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiaxing Huang","orcid":"https://orcid.org/0000-0002-8681-0471"},"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"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiaxing Huang","raw_affiliation_strings":["Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong, SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-8681-0471","affiliations":[{"raw_affiliation_string":"Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Longxiang Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I117357259","display_name":"National Institute of Japanese Literature","ror":"https://ror.org/01464wm64","country_code":"JP","type":"archive","lineage":["https://openalex.org/I117357259","https://openalex.org/I1319490839","https://openalex.org/I4210148627"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Longxiang Deng","raw_affiliation_strings":["School of Computer Science, Institute of Artificial Intelligence, National Engineering Research Center for Multimedia Software, and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Institute of Artificial Intelligence, National Engineering Research Center for Multimedia Software, and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I117357259"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100537228","display_name":"Du Bo","orcid":null},"institutions":[{"id":"https://openalex.org/I117357259","display_name":"National Institute of Japanese Literature","ror":"https://ror.org/01464wm64","country_code":"JP","type":"archive","lineage":["https://openalex.org/I117357259","https://openalex.org/I1319490839","https://openalex.org/I4210148627"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Bo Du","raw_affiliation_strings":["School of Computer Science, Institute of Artificial Intelligence, National Engineering Research Center for Multimedia Software, and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-0059-8458","affiliations":[{"raw_affiliation_string":"School of Computer Science, Institute of Artificial Intelligence, National Engineering Research Center for Multimedia Software, and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I117357259"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001529504","display_name":"Chang Xu","orcid":"https://orcid.org/0000-0002-4756-0609"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chang Xu","raw_affiliation_strings":["School of Computer Science, The University of Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4756-0609","affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.00685044,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"35","issue":null,"first_page":"6789","last_page":"6800"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.5070000290870667,"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"}},"topics":[{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.5070000290870667,"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/T12316","display_name":"Oil Spill Detection and Mitigation","score":0.5052000284194946,"subfield":{"id":"https://openalex.org/subfields/2310","display_name":"Pollution"},"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","display_name":"Object (grammar)","score":0.6591435670852661},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5020036697387695},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4963069558143616},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.43340927362442017},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36421120166778564},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.1610739529132843},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.11928513646125793}],"concepts":[{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6591435670852661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5020036697387695},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4963069558143616},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.43340927362442017},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36421120166778564},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.1610739529132843},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.11928513646125793}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tip.2026.3698359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3698359","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:42241268","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42241268","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null},{"id":"pmh:oai:arXiv.org:2504.02391","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.02391","pdf_url":"https://arxiv.org/pdf/2504.02391","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.02391","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.02391","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.02391","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.02391","pdf_url":"https://arxiv.org/pdf/2504.02391","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1836220556","display_name":null,"funder_award_id":"62225113","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410253654.pdf","grobid_xml":"https://content.openalex.org/works/W4410253654.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Marine":[0],"Saliency":[1,112],"Segmentation":[2],"(MSS)":[3],"plays":[4],"a":[5,9,83,169],"pivotal":[6],"role":[7],"in":[8,53,196],"wide":[10],"range":[11],"of":[12,24,32,66,102,165,191],"vision-based":[13],"marine":[14,85,103,166],"exploration":[15],"tasks.":[16],"However,":[17],"existing":[18],"techniques":[19],"often":[20],"face":[21],"the":[22,29,90,100,109,120,124,137,188],"dilemma":[23],"imprecise":[25],"boundaries":[26],"due":[27],"to":[28,58,98,142,159,177],"interference-rich":[30],"nature":[31],"underwater":[33],"environments,":[34],"where":[35],"suspended":[36],"particles,":[37],"low":[38],"contrast,":[39],"and":[40,145,181,199,204],"color":[41],"distortion":[42],"hinder":[43],"accurate":[44,144],"segmentation.":[45],"Although":[46],"diffusion":[47,91,148],"models":[48,206],"have":[49],"shown":[50],"impressive":[51],"performance":[52,190],"visual":[54],"tasks,":[55],"their":[56],"potential":[57],"incorporate":[59],"contextual":[60],"semantics":[61],"for":[62],"enhancing":[63],"feature":[64],"learning":[65],"region-level":[67],"salient":[68,104,117],"objects":[69],"remains":[70],"underexplored,":[71],"thereby":[72],"hindering":[73],"segmentation":[74,163],"outcomes.":[75],"Building":[76],"on":[77,89,210],"this":[78],"insight,":[79],"we":[80,107],"propose":[81],"DiffMSS,":[82],"novel":[84],"saliency":[86],"segmenter":[87],"based":[88],"model,":[92],"which":[93],"utilizes":[94],"semantic":[95,132],"knowledge":[96],"distillation":[97],"guide":[99],"detection":[101],"objects.":[105],"Specifically,":[106],"design":[108],"Word-level":[110],"Semantic":[111],"Extraction":[113],"module":[114,154],"that":[115],"identifies":[116],"terms":[118],"at":[119],"word":[121],"level":[122],"from":[123],"captions":[125],"by":[126],"computing":[127],"region-word":[128],"similarity.":[129],"These":[130],"high-level":[131],"features":[133],"are":[134],"distilled":[135],"into":[136],"Conditional":[138,152],"Feature":[139],"Learning":[140],"Network":[141],"generate":[143,161],"semantically":[146],"informed":[147],"conditions.":[149],"The":[150],"Object-Focused":[151],"Diffusion":[153],"then":[155],"leverages":[156],"these":[157],"conditions":[158],"iteratively":[160],"fine-grained":[162],"masks":[164],"instances,":[167],"while":[168],"Consensus":[170],"Deterministic":[171],"Sampling":[172],"scheme":[173],"is":[174],"further":[175],"employed":[176],"suppress":[178],"overconfident":[179],"mis-segmentations":[180],"enhance":[182],"structural":[183],"fidelity.":[184],"Extensive":[185],"experiments":[186],"demonstrate":[187],"superior":[189],"DiffMSS":[192],"over":[193],"state-of-the-art":[194],"methods":[195],"both":[197],"quantitative":[198],"qualitative":[200],"evaluations.":[201],"Our":[202],"code":[203],"pre-trained":[205],"will":[207],"be":[208],"released":[209],"GitHub.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}