{"id":"https://openalex.org/W7124160957","doi":"https://doi.org/10.1109/icpads67057.2025.11323096","title":"AquaVLM: A Domain-Specific Vision\u2013Language Model for Structured Understanding of Oceanarium Scenes","display_name":"AquaVLM: A Domain-Specific Vision\u2013Language Model for Structured Understanding of Oceanarium Scenes","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W7124160957","doi":"https://doi.org/10.1109/icpads67057.2025.11323096"},"language":null,"primary_location":{"id":"doi:10.1109/icpads67057.2025.11323096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","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/A5084619979","display_name":"Baihao You","orcid":"https://orcid.org/0000-0003-1779-7389"},"institutions":[{"id":"https://openalex.org/I101479585","display_name":"South China Agricultural University","ror":"https://ror.org/05v9jqt67","country_code":"CN","type":"education","lineage":["https://openalex.org/I101479585"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baihao You","raw_affiliation_strings":["College of Mathematics and Informatics, South China Agricultural University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mathematics and Informatics, South China Agricultural University,Guangzhou,China","institution_ids":["https://openalex.org/I101479585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123021360","display_name":"Jingheng Long","orcid":null},"institutions":[{"id":"https://openalex.org/I101479585","display_name":"South China Agricultural University","ror":"https://ror.org/05v9jqt67","country_code":"CN","type":"education","lineage":["https://openalex.org/I101479585"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingheng Long","raw_affiliation_strings":["College of Mathematics and Informatics, South China Agricultural University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mathematics and Informatics, South China Agricultural University,Guangzhou,China","institution_ids":["https://openalex.org/I101479585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123010492","display_name":"Longrui Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I101479585","display_name":"South China Agricultural University","ror":"https://ror.org/05v9jqt67","country_code":"CN","type":"education","lineage":["https://openalex.org/I101479585"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longrui Zhang","raw_affiliation_strings":["College of Mathematics and Informatics, South China Agricultural University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mathematics and Informatics, South China Agricultural University,Guangzhou,China","institution_ids":["https://openalex.org/I101479585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122996789","display_name":"Zelin He","orcid":null},"institutions":[{"id":"https://openalex.org/I101479585","display_name":"South China Agricultural University","ror":"https://ror.org/05v9jqt67","country_code":"CN","type":"education","lineage":["https://openalex.org/I101479585"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zelin He","raw_affiliation_strings":["College of Mathematics and Informatics, South China Agricultural University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mathematics and Informatics, South China Agricultural University,Guangzhou,China","institution_ids":["https://openalex.org/I101479585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123001168","display_name":"Wenxi Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I101479585","display_name":"South China Agricultural University","ror":"https://ror.org/05v9jqt67","country_code":"CN","type":"education","lineage":["https://openalex.org/I101479585"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxi Wu","raw_affiliation_strings":["College of Mathematics and Informatics, South China Agricultural University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mathematics and Informatics, South China Agricultural University,Guangzhou,China","institution_ids":["https://openalex.org/I101479585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088015912","display_name":"Ximing Li","orcid":"https://orcid.org/0000-0002-2740-3470"},"institutions":[{"id":"https://openalex.org/I101479585","display_name":"South China Agricultural University","ror":"https://ror.org/05v9jqt67","country_code":"CN","type":"education","lineage":["https://openalex.org/I101479585"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ximing Li","raw_affiliation_strings":["College of Mathematics and Informatics, South China Agricultural University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mathematics and Informatics, South China Agricultural University,Guangzhou,China","institution_ids":["https://openalex.org/I101479585"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I101479585"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57066506,"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":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9315000176429749,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9315000176429749,"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":0.014000000432133675,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.013700000010430813,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.7483000159263611},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5968999862670898},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5716999769210815},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.5519999861717224},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5203999876976013},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5078999996185303},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4307999908924103},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4074000120162964},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.40119999647140503}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7774999737739563},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.7483000159263611},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.621999979019165},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5968999862670898},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5716999769210815},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5519999861717224},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5203999876976013},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5078999996185303},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4307999908924103},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4074000120162964},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.40119999647140503},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3456999957561493},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3416000008583069},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2987000048160553},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28839999437332153},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2745000123977661},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2703999876976013},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.2660999894142151},{"id":"https://openalex.org/C2986522900","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relationship","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpads67057.2025.11323096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8317869305610657,"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":3,"referenced_works":["https://openalex.org/W4391601861","https://openalex.org/W4402660140","https://openalex.org/W4402727764"],"related_works":[],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLMs)":[2],"have":[3],"advanced":[4],"cross-modal":[5],"understanding":[6],"and":[7,25,41,50,100,111],"generation,":[8],"yet":[9],"their":[10],"domain":[11,63],"adaptability":[12],"remains":[13],"limited.":[14],"To":[15,65],"address":[16],"the":[17,106,109],"lack":[18],"of":[19,48,75,95,108],"high-quality":[20],"captions":[21],"for":[22,45,126],"fish":[23],"recognition":[24],"description":[26],"in":[27],"oceanarium":[28,77],"scenes,":[29],"we":[30,69],"introduce":[31],"AquaVLM,":[32],"a":[33,37,93,120],"domain-specific":[34],"VLM":[35],"incorporating":[36],"Categorical-Spatial":[38],"Descriptor":[39],"(CSD)":[40],"multi-type":[42],"prompt":[43],"templates":[44],"joint":[46],"modeling":[47],"category":[49],"spatial":[51],"information.":[52],"A":[53],"Low-Rank":[54],"Adaptation":[55],"(LoRA)":[56],"scheme":[57],"enables":[58],"parameter-efficient":[59],"fine-tuning":[60],"to":[61],"enhance":[62],"transfer.":[64],"support":[66],"this":[67],"task,":[68],"build":[70],"AquaCap,":[71,91],"an":[72],"image-text":[73],"dataset":[74],"2,722":[76],"images":[78],"with":[79],"aligned":[80],"descriptions.":[81],"Experiments":[82],"show":[83],"that":[84],"AquaVLM":[85],"substantially":[86],"outperforms":[87],"representative":[88],"VLMs":[89],"on":[90,119],"achieving":[92],"BERTScore":[94],"0.9217,":[96],"indicating":[97],"superior":[98],"semantic":[99],"descriptive":[101],"quality.":[102],"Ablation":[103],"studies":[104],"confirm":[105],"effectiveness":[107],"CSD":[110],"multi-template":[112],"design,":[113],"while":[114],"successful":[115],"4-bit":[116],"quantized":[117],"deployment":[118],"mobile-cloud":[121],"architecture":[122],"highlights":[123],"its":[124],"potential":[125],"resource-limited":[127],"applications.":[128],"The":[129],"artifacts":[130],"are":[131],"available":[132],"upon":[133],"request.":[134]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-01-15T00:00:00"}
