{"id":"https://openalex.org/W7140322039","doi":"https://doi.org/10.3390/jimaging12040145","title":"Refer-ASV: Referring Multi-Object Tracking in Autonomous Surface Vehicle Navigation Scenes","display_name":"Refer-ASV: Referring Multi-Object Tracking in Autonomous Surface Vehicle Navigation Scenes","publication_year":2026,"publication_date":"2026-03-25","ids":{"openalex":"https://openalex.org/W7140322039","doi":"https://doi.org/10.3390/jimaging12040145","pmid":"https://pubmed.ncbi.nlm.nih.gov/42042488"},"language":"en","primary_location":{"id":"doi:10.3390/jimaging12040145","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging12040145","pdf_url":"https://www.mdpi.com/2313-433X/12/4/145/pdf?version=1774428752","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2313-433X/12/4/145/pdf?version=1774428752","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Bin Xue","orcid":"https://orcid.org/0000-0003-3664-9410"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Xue","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 101408, China","State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China"],"raw_orcid":"https://orcid.org/0000-0003-3664-9410","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 101408, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100717177","display_name":"Qiang Yu","orcid":"https://orcid.org/0000-0003-2119-090X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Yu","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China"],"raw_orcid":"https://orcid.org/0000-0003-2119-090X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130548893","display_name":"Kun Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kun Ding","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China"],"raw_orcid":"https://orcid.org/0000-0002-2256-8815","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130625735","display_name":"Ying Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Wang","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China"],"raw_orcid":"https://orcid.org/0000-0003-1385-3224","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130549141","display_name":"Shiming Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiming Xiang","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 101408, China","State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China"],"raw_orcid":"https://orcid.org/0000-0002-2089-9733","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 101408, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100509428","display_name":"Chunhong Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunhong Pan","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China"],"raw_orcid":"https://orcid.org/0000-0001-7433-4474","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5130548893"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28538578,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":"4","first_page":"145","last_page":"145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11622","display_name":"Maritime Navigation and Safety","score":0.5069000124931335,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11622","display_name":"Maritime Navigation and Safety","score":0.5069000124931335,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.15600000321865082,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.14390000700950623,"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/robustness","display_name":"Robustness (evolution)","score":0.7195000052452087},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4966999888420105},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4837000072002411},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4366999864578247},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.40400001406669617},{"id":"https://openalex.org/keywords/vehicle-tracking-system","display_name":"Vehicle tracking system","score":0.39649999141693115},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.37059998512268066},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.36340001225471497}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8163999915122986},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7195000052452087},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.715399980545044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7124999761581421},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4966999888420105},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4837000072002411},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4366999864578247},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.40400001406669617},{"id":"https://openalex.org/C84119951","wikidata":"https://www.wikidata.org/wiki/Q3498530","display_name":"Vehicle tracking system","level":3,"score":0.39649999141693115},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.37059998512268066},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.36340001225471497},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C154586513","wikidata":"https://www.wikidata.org/wiki/Q4420972","display_name":"Tracking system","level":3,"score":0.304500013589859},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C2987395694","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Feature tracking","level":3,"score":0.2639000117778778},{"id":"https://openalex.org/C95020103","wikidata":"https://www.wikidata.org/wiki/Q1813492","display_name":"Match moving","level":3,"score":0.2603999972343445}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/jimaging12040145","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging12040145","pdf_url":"https://www.mdpi.com/2313-433X/12/4/145/pdf?version=1774428752","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},{"id":"pmid:42042488","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42042488","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":"Journal of imaging","raw_type":null},{"id":"pmh:oai:doaj.org/article:8f0cb45c4cd04cf69cf224750bf74637","is_oa":true,"landing_page_url":"https://doaj.org/article/8f0cb45c4cd04cf69cf224750bf74637","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Imaging, Vol 12, Iss 4, p 145 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13117675","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13117675/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Imaging","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/jimaging12040145","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging12040145","pdf_url":"https://www.mdpi.com/2313-433X/12/4/145/pdf?version=1774428752","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Life below water","score":0.6608282923698425,"id":"https://metadata.un.org/sdg/14"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140322039.pdf","grobid_xml":"https://content.openalex.org/works/W7140322039.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W2124781496","https://openalex.org/W2150066425","https://openalex.org/W2194775991","https://openalex.org/W2296073425","https://openalex.org/W2511791013","https://openalex.org/W2552331162","https://openalex.org/W2565639579","https://openalex.org/W2603203130","https://openalex.org/W2962766617","https://openalex.org/W2963351448","https://openalex.org/W2997242810","https://openalex.org/W3084173793","https://openalex.org/W3086436251","https://openalex.org/W3094000868","https://openalex.org/W3096609285","https://openalex.org/W3116469262","https://openalex.org/W3118212025","https://openalex.org/W3130257562","https://openalex.org/W3204885083","https://openalex.org/W4229375907","https://openalex.org/W4283265075","https://openalex.org/W4310467366","https://openalex.org/W4312473433","https://openalex.org/W4313072323","https://openalex.org/W4322576511","https://openalex.org/W4362501010","https://openalex.org/W4385575022","https://openalex.org/W4385739414","https://openalex.org/W4386076180","https://openalex.org/W4392452358","https://openalex.org/W4392904092","https://openalex.org/W4398186003","https://openalex.org/W4400035744","https://openalex.org/W4401732049","https://openalex.org/W4402726924","https://openalex.org/W4405974723","https://openalex.org/W4406610663","https://openalex.org/W4410920648","https://openalex.org/W4412939518","https://openalex.org/W4413944783","https://openalex.org/W4415539897","https://openalex.org/W4416748109","https://openalex.org/W7118945935","https://openalex.org/W7123362041"],"related_works":[],"abstract_inverted_index":{"Water-surface":[0],"perception":[1],"is":[2,15,103],"critical":[3],"for":[4,17,49,95],"autonomous":[5],"surface":[6],"vehicle":[7],"navigation,":[8],"where":[9],"reliable":[10],"tracking":[11,24,29,138],"of":[12,37,64,80,159],"task-relevant":[13],"objects":[14,36],"essential":[16],"safe":[18],"and":[19,54,61,76,109,114,144],"robust":[20],"operation.":[21],"Referring":[22],"multi-object":[23],"(RMOT)":[25],"provides":[26],"a":[27,77,156],"flexible":[28],"paradigm":[30],"by":[31,140],"allowing":[32],"users":[33],"to":[34,56],"specify":[35],"interest":[38],"through":[39],"natural":[40],"language.":[41],"However,":[42],"existing":[43,164],"RMOT":[44,92],"benchmarks":[45],"are":[46],"mainly":[47],"designed":[48],"ground":[50],"or":[51],"satellite":[52],"scenes":[53,113],"fail":[55],"capture":[57],"the":[58,90,137],"distinctive":[59],"visual":[60],"semantic":[62],"characteristics":[63],"water-surface":[65,100],"environments,":[66],"including":[67],"strong":[68],"reflections,":[69],"severe":[70],"illumination":[71],"variations,":[72],"weak":[73],"motion":[74],"constraints,":[75],"high":[78],"proportion":[79],"small":[81],"objects.":[82],"To":[83,118],"address":[84],"this":[85],"gap,":[86],"we":[87,124],"introduce":[88],"Refer-ASV,":[89,123,162],"first":[91],"dataset":[93],"tailored":[94],"ASV":[96,107],"navigation":[97,112],"in":[98,146],"complex":[99],"scenes.":[101,176],"Refer-ASV":[102],"constructed":[104],"from":[105],"real-world":[106],"videos":[108],"features":[110],"diverse":[111],"fine-grained":[115],"vessel":[116],"categories.":[117],"facilitate":[119],"systematic":[120],"evaluation":[121],"on":[122,161,168],"further":[125],"propose":[126],"RAMOT,":[127],"an":[128],"end-to-end":[129],"baseline":[130],"framework":[131],"that":[132,153],"enhances":[133],"visual-language":[134,142],"alignment":[135,143],"throughout":[136],"pipeline":[139],"improving":[141],"robustness":[145],"challenging":[147],"maritime":[148],"environments.":[149],"Experimental":[150],"results":[151],"show":[152],"RAMOT":[154],"achieves":[155],"HOTA":[157],"score":[158],"39.97":[160],"outperforming":[163],"methods.":[165],"Additional":[166],"experiments":[167],"Refer-KITTI":[169],"demonstrate":[170],"its":[171],"generalization":[172],"ability":[173],"across":[174],"different":[175]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-03-26T00:00:00"}
