{"id":"https://openalex.org/W7161830522","doi":"https://doi.org/10.1109/access.2026.3695395","title":"Improving Rock Detection Accuracy by Using Vision-Language Models With Textual\u2013Visual Prompt Alignment","display_name":"Improving Rock Detection Accuracy by Using Vision-Language Models With Textual\u2013Visual Prompt Alignment","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7161830522","doi":"https://doi.org/10.1109/access.2026.3695395"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3695395","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3695395","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3695395","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043110356","display_name":"Vincenzo Carletti","orcid":"https://orcid.org/0000-0002-9130-5533"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Vincenzo Carletti","raw_affiliation_strings":["Department of Information and Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, Salerno, Italy"],"raw_orcid":"https://orcid.org/0000-0002-9130-5533","affiliations":[{"raw_affiliation_string":"Department of Information and Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, Salerno, Italy","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136573648","display_name":"Antonio Greco","orcid":"https://orcid.org/0000-0002-5495-2432"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Antonio Greco","raw_affiliation_strings":["Department of Information and Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, Salerno, Italy"],"raw_orcid":"https://orcid.org/0000-0002-5495-2432","affiliations":[{"raw_affiliation_string":"Department of Information and Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, Salerno, Italy","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083939361","display_name":"Alessia Saggese","orcid":"https://orcid.org/0000-0003-4687-7994"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessia Saggese","raw_affiliation_strings":["Department of Information and Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, Salerno, Italy"],"raw_orcid":"https://orcid.org/0000-0003-4687-7994","affiliations":[{"raw_affiliation_string":"Department of Information and Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, Salerno, Italy","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114815441","display_name":"Camilla Spingola","orcid":null},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Camilla Spingola","raw_affiliation_strings":["Department of Information and Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, Salerno, Italy"],"raw_orcid":"https://orcid.org/0009-0009-1828-4367","affiliations":[{"raw_affiliation_string":"Department of Information and Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, Salerno, Italy","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092302658","display_name":"Bruno Vento","orcid":"https://orcid.org/0009-0006-7687-4929"},"institutions":[{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Bruno Vento","raw_affiliation_strings":["Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Naples, Italy"],"raw_orcid":"https://orcid.org/0009-0006-7687-4929","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Naples, Italy","institution_ids":["https://openalex.org/I71267560"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62986796,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"77944","last_page":"77957"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.11079999804496765,"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":0.11079999804496765,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.08079999685287476,"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":0.07779999822378159,"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/object-detection","display_name":"Object detection","score":0.41600000858306885},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3580999970436096},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2971999943256378},{"id":"https://openalex.org/keywords/radar-tracker","display_name":"Radar tracker","score":0.2904999852180481},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.28369998931884766}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6207000017166138},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49619999527931213},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.46779999136924744},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46540001034736633},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.41600000858306885},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3580999970436096},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.3131999969482422},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C32283439","wikidata":"https://www.wikidata.org/wiki/Q1407014","display_name":"Radar tracker","level":3,"score":0.2904999852180481},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.28369998931884766},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2612000107765198},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.258899986743927}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3695395","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3695395","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:8880bdd9a86d4ca1814a27eb50f8fe2c","is_oa":true,"landing_page_url":"https://doaj.org/article/8880bdd9a86d4ca1814a27eb50f8fe2c","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":"IEEE Access, Vol 14, Pp 77944-77957 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3695395","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3695395","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"reliable":[1],"detection":[2,79,210],"of":[3,28,33,74,181,198,211],"unconventional":[4],"obstacles,":[5],"such":[6],"as":[7,202],"rocks,":[8],"is":[9,21,48],"essential":[10],"for":[11,60,77,208],"ensuring":[12],"safe":[13],"and":[14,30,87,109,136,170,186,205],"continuous":[15],"railway":[16,35,214],"operations.":[17],"However,":[18],"this":[19,51,54],"task":[20],"challenging":[22],"due":[23],"to":[24,105,112],"the":[25,31,71,142,178,196,199,209],"visual":[26,114,119,184],"heterogeneity":[27],"rocks":[29,212],"scarcity":[32],"annotated":[34],"data.":[36],"Existing":[37],"vision-based":[38],"systems":[39],"often":[40],"rely":[41],"on":[42,149,213],"conventional":[43],"classifiers,":[44],"whose":[45],"generalization":[46,188],"ability":[47],"limited":[49],"in":[50,98,133,167],"setting.":[52],"In":[53],"work,":[55],"we":[56],"introduce":[57],"Textual-Visual":[58],"Alignment":[59],"Rock":[61],"Detection":[62],"(TVA-Rock),":[63],"a":[64,81,92,203],"parameter-efficient":[65],"textual-visual":[66,94],"alignment":[67,96],"framework":[68],"that":[69,154,159],"leverages":[70],"representational":[72],"strength":[73],"vision-language":[75],"models":[76],"rock":[78],"within":[80],"two-stage":[82],"pipeline":[83],"comprising":[84],"track":[85],"segmentation":[86],"patch-wise":[88],"classification.":[89],"TVA-Rock":[90,155],"employs":[91],"sequential":[93,126],"prompt":[95,115],"strategy,":[97],"which":[99],"textual":[100,143,182],"prompts":[101],"are":[102,160],"first":[103],"optimized":[104],"encode":[106],"task-relevant":[107],"semantics,":[108],"subsequently":[110],"used":[111],"guide":[113],"tuning,":[116],"yielding":[117],"rock-aware":[118],"representations":[120],"without":[121],"modifying":[122],"backbone":[123],"weights.":[124],"This":[125],"design":[127],"stabilizes":[128],"multimodal":[129],"optimization,":[130],"mitigates":[131],"overfitting":[132],"data-scarce":[134],"regimes,":[135],"enables":[137],"efficient":[138,206],"inference":[139],"by":[140],"discarding":[141],"branch":[144],"after":[145],"training.":[146],"Extensive":[147],"experiments":[148],"realistic":[150],"onboard-camera":[151],"samples":[152],"show":[153],"outperforms":[156],"existing":[157],"approaches,":[158],"also":[161],"more":[162],"complex,":[163],"achieving":[164],"state-of-the-art":[165],"performance":[166],"identifying":[168],"small":[169],"visually":[171],"irregular":[172],"rocks.":[173],"Ablation":[174],"studies":[175],"further":[176],"validate":[177],"incremental":[179],"contribution":[180],"prompting,":[183,185],"architectural":[187],"across":[189],"different":[190],"VLM":[191],"backbones.":[192],"These":[193],"results":[194],"demonstrate":[195],"potential":[197],"proposed":[200],"method":[201],"robust":[204],"strategy":[207],"tracks.":[215]},"counts_by_year":[],"updated_date":"2026-05-29T06:17:43.578629","created_date":"2026-05-21T00:00:00"}