{"id":"https://openalex.org/W7152399050","doi":"https://doi.org/10.1109/tip.2026.3675431","title":"A Causal Lens on Non-RGB Vision Sensor Understanding in Vision-Language Models","display_name":"A Causal Lens on Non-RGB Vision Sensor Understanding in Vision-Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7152399050","doi":"https://doi.org/10.1109/tip.2026.3675431","pmid":"https://pubmed.ncbi.nlm.nih.gov/41955154"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3675431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3675431","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/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":["Image and Video Systems Laboratory, School of Electrical Engineering, 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":"Image and Video Systems Laboratory, School of Electrical Engineering, 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":["Image and Video Systems Laboratory, School of Electrical Engineering, 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":"Image and Video Systems Laboratory, School of Electrical Engineering, 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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50507407,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"3909","last_page":"3924"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.37049999833106995,"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":0.37049999833106995,"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/T12031","display_name":"Speech and dialogue systems","score":0.10899999737739563,"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"}},{"id":"https://openalex.org/T10656","display_name":"Child and Animal Learning Development","score":0.05999999865889549,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.4641000032424927},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.3569999933242798},{"id":"https://openalex.org/keywords/lens","display_name":"Lens (geology)","score":0.3138999938964844},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.311599999666214},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3070000112056732},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.30649998784065247},{"id":"https://openalex.org/keywords/image-sensor","display_name":"Image sensor","score":0.3041999936103821},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.2838999927043915}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6722999811172485},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6567000150680542},{"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/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.4641000032424927},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3569999933242798},{"id":"https://openalex.org/C15336307","wikidata":"https://www.wikidata.org/wiki/Q1766051","display_name":"Lens (geology)","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C76935873","wikidata":"https://www.wikidata.org/wiki/Q209121","display_name":"Image sensor","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2838999927043915},{"id":"https://openalex.org/C146044194","wikidata":"https://www.wikidata.org/wiki/Q5157334","display_name":"Computational photography","level":4,"score":0.2815999984741211},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2727000117301941},{"id":"https://openalex.org/C200220432","wikidata":"https://www.wikidata.org/wiki/Q7936208","display_name":"Vision science","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3675431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3675431","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:41955154","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41955154","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":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6435501467","display_name":null,"funder_award_id":"RS-2022-II220984","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"Vision-Language":[1],"Models":[2],"(VLMs)":[3],"have":[4],"achieved":[5],"remarkable":[6],"success":[7],"in":[8,138,175],"tasks":[9],"involving":[10],"natural":[11],"RGB":[12],"images,":[13],"their":[14,55],"capability":[15],"to":[16,42,52,75,95,112,160],"understand":[17],"non-RGB":[18,83,142],"sensor":[19,84,144],"data,":[20],"including":[21],"thermal,":[22],"depth,":[23],"hyperspectral,":[24],"and":[25,62,106,183,192],"X-ray":[26],"imagery,":[27],"remains":[28],"severely":[29],"limited.":[30],"This":[31,180],"limitation":[32],"stems":[33],"from":[34,109],"an":[35],"entrenched":[36],"RGB-centric":[37,77],"bias,":[38],"leading":[39],"current":[40],"VLMs":[41,81,140],"treat":[43],"these":[44,168],"distinct":[45],"modalities":[46],"as":[47],"ordinary":[48],"photographs,":[49],"thus":[50],"failing":[51],"account":[53],"for":[54,122,188],"unique":[56],"physical":[57,164],"properties.":[58],"To":[59],"systematically":[60],"evaluate":[61],"address":[63],"this":[64,97],"pervasive":[65],"issue,":[66],"we":[67,87,147],"present":[68],"CausalSense,":[69],"a":[70,89,134,172],"novel":[71],"benchmark":[72,182],"suite":[73],"designed":[74],"expose":[76],"bias":[78],"within":[79],"large-scale":[80],"using":[82,131],"data.":[85],"Concurrently,":[86],"devise":[88],"causal":[90,110,152],"learning":[91],"framework":[92,184],"specifically":[93],"engineered":[94],"alleviate":[96],"RGB-bounded":[98],"bias.":[99],"Our":[100,128],"approach":[101],"effectively":[102],"employs":[103],"confounder":[104],"dictionaries":[105],"backdoor":[107],"adjustments":[108],"inference":[111],"integrate":[113],"essential":[114],"sensor-specific":[115],"knowledge":[116],"into":[117],"VLMs,":[118],"circumventing":[119],"the":[120,163,176,186,204],"need":[121],"extensive":[123],"retraining":[124],"on":[125],"massive":[126],"datasets.":[127],"comprehensive":[129],"evaluations":[130],"CausalSense":[132],"underscore":[133],"significant":[135],"performance":[136,178],"deficiency":[137],"state-of-the-art":[139],"concerning":[141],"vision":[143],"comprehension.":[145],"Crucially,":[146],"demonstrate":[148],"that":[149],"our":[150],"proposed":[151],"deconfounded":[153],"cross-modal":[154],"encoder":[155],"substantially":[156],"improves":[157],"VLMs'":[158],"ability":[159],"reason":[161],"about":[162],"attributes":[165],"captured":[166],"by":[167],"modalities,":[169],"thereby":[170],"achieving":[171],"measurable":[173],"reduction":[174],"observed":[177],"gap.":[179],"combined":[181],"pave":[185],"way":[187],"developing":[189],"more":[190],"resilient":[191],"sensor-aware":[193],"vision-language":[194],"models,":[195],"capable":[196],"of":[197],"robustly":[198],"interpreting":[199],"diverse":[200],"real-world":[201],"phenomena":[202],"beyond":[203],"visible":[205],"spectrum.":[206]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-10T00:00:00"}