{"id":"https://openalex.org/W7167817233","doi":"https://doi.org/10.1109/tip.2026.3707796","title":"Enhanced Vision-Language Models for Diverse Sensor Understanding: Cost-Efficient Optimization and Benchmarking","display_name":"Enhanced Vision-Language Models for Diverse Sensor Understanding: Cost-Efficient Optimization and Benchmarking","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7167817233","doi":"https://doi.org/10.1109/tip.2026.3707796","pmid":"https://pubmed.ncbi.nlm.nih.gov/42424212"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3707796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3707796","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":"article","indexed_in":["crossref","pubmed"],"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/A5113258484","display_name":"Sangyun Chung","orcid":"https://orcid.org/0009-0004-5397-2687"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sangyun Chung","raw_affiliation_strings":["Integrated Vision Language Laboratory, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0004-5397-2687","affiliations":[{"raw_affiliation_string":"Integrated Vision Language Laboratory, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067319464","display_name":"Youngjoon Yu","orcid":"https://orcid.org/0000-0002-3188-2080"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngjoon Yu","raw_affiliation_strings":["Integrated Vision Language Laboratory, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-3188-2080","affiliations":[{"raw_affiliation_string":"Integrated Vision Language Laboratory, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066488450","display_name":"Seyeon Kim","orcid":"https://orcid.org/0009-0002-4959-8165"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seyeon Kim","raw_affiliation_strings":["Integrated Vision Language Laboratory, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0001-4819-1219","affiliations":[{"raw_affiliation_string":"Integrated Vision Language Laboratory, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140350676","display_name":"Youngchae Chee","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngchae Chee","raw_affiliation_strings":["Integrated Vision Language Laboratory, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0008-7778-2115","affiliations":[{"raw_affiliation_string":"Integrated Vision Language Laboratory, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038798134","display_name":"Yong Man Ro","orcid":"https://orcid.org/0000-0001-5306-6853"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yong Man Ro","raw_affiliation_strings":["Integrated Vision Language Laboratory, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-5306-6853","affiliations":[{"raw_affiliation_string":"Integrated Vision Language Laboratory, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87825593,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"7444","last_page":"7459"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3758000135421753,"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":0.3758000135421753,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.051100000739097595,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0348999984562397,"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/benchmarking","display_name":"Benchmarking","score":0.5702000260353088},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.3253999948501587},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.30880001187324524},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2987000048160553},{"id":"https://openalex.org/keywords/algorithm-design","display_name":"Algorithm design","score":0.2743000090122223}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6262999773025513},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5702000260353088},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3253999948501587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3188999891281128},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2987000048160553},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2696000039577484},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C55660270","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization","level":2,"score":0.24539999663829803}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3707796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3707796","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:42424212","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42424212","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":"Journal Article"}],"best_oa_location":null,"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":{"Large-scale":[0],"Vision-Language":[1],"Models":[2],"(VLMs)":[3],"have":[4],"achieved":[5],"notable":[6],"progress":[7],"in":[8,95,155],"aligning":[9],"visual":[10],"inputs":[11],"with":[12,71],"text.":[13],"However,":[14],"their":[15],"ability":[16],"to":[17,59,83,108],"deeply":[18],"understand":[19],"the":[20,60,72],"unique":[21],"physical":[22],"properties":[23],"of":[24,87,153],"non-RGB":[25,88],"vision":[26],"sensor":[27,49,126],"images":[28],"remains":[29],"limited.":[30],"In":[31,98],"this":[32],"paper,":[33],"we":[34,65,100,128],"revisit":[35],"and":[36,40,90,116,124,137,141],"analyze":[37],"these":[38],"limitations":[39],"introduce":[41],"a":[42,147],"novel,":[43],"cost-efficient":[44],"paradigm":[45],"that":[46,130],"significantly":[47],"advances":[48],"image":[50],"understanding-without":[51],"requiring":[52],"extensive":[53,120],"training":[54],"data":[55,82],"or":[56],"any":[57],"modifications":[58],"existing":[61],"VLM":[62],"architectures.":[63],"Specifically,":[64],"propose":[66],"Sensor-Aware":[67],"Attributes":[68,75],"Fine-Tuning":[69],"(SAFT)":[70],"Diverse":[73],"Negative":[74],"(DNA)":[76],"optimization,":[77],"which":[78],"leverages":[79],"minimal":[80],"sensor-specific":[81,112],"enable":[84],"robust":[85],"learning":[86],"characteristics":[89],"overcome":[91],"RGB-centric":[92],"biases":[93],"inherent":[94],"current":[96],"VLMs.":[97],"addition,":[99],"present":[101],"VS-TDX-the":[102],"first":[103],"comprehensive,":[104],"public":[105],"benchmark":[106],"designed":[107],"rigorously":[109],"evaluate":[110],"VLMs'":[111],"understanding":[113],"across":[114],"diverse":[115],"realistic":[117],"scenarios.":[118],"Through":[119],"experiments":[121],"on":[122],"VLMs":[123,154],"various":[125],"modalities,":[127],"validate":[129],"our":[131],"method":[132],"consistently":[133],"delivers":[134],"superior":[135],"performance":[136],"generalization":[138],"under":[139],"resource-constrained":[140],"architecture-invariant":[142],"settings.":[143],"Our":[144],"approach":[145],"provides":[146],"practical":[148],"advance":[149],"towards":[150],"scalable":[151],"deployment":[152],"increasingly":[156],"sensor-diverse":[157],"real-world":[158],"environments.":[159]},"counts_by_year":[],"updated_date":"2026-07-17T05:52:16.776730","created_date":"2026-07-10T00:00:00"}