{"id":"https://openalex.org/W7137915530","doi":"https://doi.org/10.1609/aaai.v40i5.37376","title":"Empowering Semantic-Sensitive Underwater Image Enhancement with VLM","display_name":"Empowering Semantic-Sensitive Underwater Image Enhancement with VLM","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137915530","doi":"https://doi.org/10.1609/aaai.v40i5.37376"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i5.37376","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37376","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37376/41338","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37376/41338","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129711461","display_name":"Guodong Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I83776822","display_name":"Shandong Institute of Business and Technology","ror":"https://ror.org/03rrkrc24","country_code":"CN","type":"education","lineage":["https://openalex.org/I83776822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guodong Fan","raw_affiliation_strings":["Shandong Technology and Business University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong Technology and Business University","institution_ids":["https://openalex.org/I83776822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103447672","display_name":"Shengning Zhou","orcid":"https://orcid.org/0009-0001-8012-047X"},"institutions":[{"id":"https://openalex.org/I83776822","display_name":"Shandong Institute of Business and Technology","ror":"https://ror.org/03rrkrc24","country_code":"CN","type":"education","lineage":["https://openalex.org/I83776822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengning Zhou","raw_affiliation_strings":["Shandong Technology and Business University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong Technology and Business University","institution_ids":["https://openalex.org/I83776822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014798392","display_name":"Genji Yuan","orcid":"https://orcid.org/0000-0002-8710-2266"},"institutions":[{"id":"https://openalex.org/I83776822","display_name":"Shandong Institute of Business and Technology","ror":"https://ror.org/03rrkrc24","country_code":"CN","type":"education","lineage":["https://openalex.org/I83776822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Genji Yuan","raw_affiliation_strings":["Shandong Technology and Business University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong Technology and Business University","institution_ids":["https://openalex.org/I83776822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129749420","display_name":"Huiyu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I59483232","display_name":"Shandong University of Finance and Economics","ror":"https://ror.org/02e2nnq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I59483232"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huiyu Li","raw_affiliation_strings":["Shandong University of Finance and Economics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University of Finance and Economics","institution_ids":["https://openalex.org/I59483232"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129655664","display_name":"Jingchun Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingchun Zhou","raw_affiliation_strings":["Dalian Maritime University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian Maritime University","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129716522","display_name":"Jinjiang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I83776822","display_name":"Shandong Institute of Business and Technology","ror":"https://ror.org/03rrkrc24","country_code":"CN","type":"education","lineage":["https://openalex.org/I83776822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinjiang Li","raw_affiliation_strings":["Shandong Technology and Business University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong Technology and Business University","institution_ids":["https://openalex.org/I83776822"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13319088,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"5","first_page":"3759","last_page":"3767"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.957099974155426,"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/T11019","display_name":"Image Enhancement Techniques","score":0.957099974155426,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.020999999716877937,"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":0.004100000020116568,"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/image-restoration","display_name":"Image restoration","score":0.5184999704360962},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5103999972343445},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5084999799728394},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.5076000094413757},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5034999847412109},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.49939998984336853},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4885999858379364},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.460999995470047},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.43709999322891235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7204999923706055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6520000100135803},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6323999762535095},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.5184999704360962},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5103999972343445},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5084999799728394},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5076000094413757},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5034999847412109},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.49939998984336853},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4885999858379364},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.460999995470047},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.43709999322891235},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.40070000290870667},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3935999870300293},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3765999972820282},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.36910000443458557},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.36629998683929443},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C98083399","wikidata":"https://www.wikidata.org/wiki/Q3246517","display_name":"Underwater","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C3017601658","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image enhancement","level":3,"score":0.30730000138282776},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C123403432","wikidata":"https://www.wikidata.org/wiki/Q654068","display_name":"Visibility","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25600001215934753},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i5.37376","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37376","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37376/41338","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37376","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37376","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i5.37376","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37376","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37376/41338","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4724435806274414,"id":"https://metadata.un.org/sdg/14","display_name":"Life below water"}],"awards":[{"id":"https://openalex.org/G1801226835","display_name":null,"funder_award_id":"62301105","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3206296086","display_name":null,"funder_award_id":"62272281","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7500618102","display_name":null,"funder_award_id":"U24A20219","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G944836803","display_name":null,"funder_award_id":"62202268","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"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137915530.pdf","grobid_xml":"https://content.openalex.org/works/W7137915530.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"learning-based":[3],"underwater":[4],"image":[5,77,93,133],"enhancement":[6,37],"(UIE)":[7],"techniques":[8],"have":[9],"rapidly":[10],"evolved.":[11],"However,":[12],"distribution":[13],"shifts":[14],"between":[15],"high-quality":[16],"enhanced":[17],"outputs":[18],"and":[19,115,179,185],"natural":[20],"images":[21],"can":[22],"hinder":[23],"semantic":[24,98],"cue":[25],"extraction":[26],"for":[27],"downstream":[28],"vision":[29],"tasks,":[30,181],"thereby":[31,142],"limiting":[32],"the":[33,92,105,122,144],"adaptability":[34],"of":[35,71,147],"existing":[36],"models.":[38],"To":[39,62],"address":[40],"this":[41,43],"challenge,":[42],"work":[44],"proposes":[45],"a":[46,75,79,82,96,109,138],"new":[47],"learning":[48],"mechanism":[49],"that":[50,153],"leverages":[51],"Vision-Language":[52],"Models":[53],"(VLMs)":[54],"to":[55,94,124,159],"empower":[56],"UIE":[57,106,161],"models":[58],"with":[59],"semantic-sensitive":[60,130],"capabilities.":[61],"be":[63],"concrete,":[64],"our":[65,155],"strategy":[66,156],"first":[67],"generates":[68],"textual":[69],"descriptions":[70,89],"key":[72,148],"objects":[73],"from":[74],"degraded":[76],"via":[78],"VLM.":[80],"Subsequently,":[81],"text-image":[83],"alignment":[84,118],"model":[85],"remaps":[86],"these":[87],"relevant":[88],"back":[90],"onto":[91],"produce":[95],"spatial":[97],"guidance":[99],"map.":[100],"This":[101,120],"map":[102],"then":[103],"steers":[104],"network":[107,123],"through":[108],"dual-guidance":[110],"mechanism,":[111],"which":[112],"combines":[113],"cross-attention":[114],"an":[116],"explicit":[117],"loss.":[119],"forces":[121],"focus":[125],"its":[126,183],"restorative":[127],"power":[128],"on":[129,167,177],"regions":[131],"during":[132],"reconstruction,":[134],"rather":[135],"than":[136],"pursuing":[137],"globally":[139],"uniform":[140],"improvement,":[141],"ensuring":[143],"faithful":[145],"restoration":[146],"object":[149],"features.":[150],"Experiments":[151],"confirm":[152],"when":[154],"is":[157],"applied":[158],"different":[160],"baselines,":[162],"significantly":[163],"boosts":[164],"their":[165,175],"performance":[166,176],"perceptual":[168],"quality":[169],"metrics":[170],"as":[171,173],"well":[172],"enhances":[174],"detection":[178],"segmentation":[180],"validating":[182],"effectiveness":[184],"adaptability.":[186]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}