{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T05:01:36Z","timestamp":1776488496478,"version":"3.51.2"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100010418","name":"Institute of Information and Communications Technology Planning and Evaluation grant funded by Korean Government","doi-asserted-by":"publisher","award":["RS-2022-II220984"],"award-info":[{"award-number":["RS-2022-II220984"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Center for Applied Research in Artificial Intelligence grant funded by Defense Acquisition Program Administration (DAPA) and Agency for Defense Development","award":["UD230017TD"],"award-info":[{"award-number":["UD230017TD"]}]},{"name":"BK21 FOUR [Connected AI Education and Research Program for Industry and Society Innovation, Korea Advanced Institute of Science and Technology (KAIST) Electrical Engineering (EE)]"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3675431","type":"journal-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T19:49:06Z","timestamp":1775764146000},"page":"3909-3924","source":"Crossref","is-referenced-by-count":0,"title":["A Causal Lens on Non-RGB Vision Sensor Understanding in Vision-Language Models"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3188-2080","authenticated-orcid":false,"given":"Youngjoon","family":"Yu","sequence":"first","affiliation":[{"name":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5306-6853","authenticated-orcid":false,"given":"Yong Man","family":"Ro","sequence":"additional","affiliation":[{"name":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3286710"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339661"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3437288"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3558446"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP55913.2025.11084572"},{"key":"ref6","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"arXiv:2306.14824"},{"key":"ref7","article-title":"Qwen2.5-VL technical report","author":"Bai","year":"2025","journal-title":"arXiv:2502.13923"},{"key":"ref8","first-page":"1","article-title":"Trajectory-LLM: A language-based data generator for trajectory prediction in autonomous driving","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Yang"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5220\/0012395700003636"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3522130"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3576490"},{"key":"ref12","article-title":"PaLM-E: An embodied multimodal language model","author":"Driess","year":"2023","journal-title":"arXiv:2303.03378"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3393298"},{"key":"ref14","volume-title":"InternVL2: Better Than the Best-Expanding Performance Boundaries of Open-Source Multimodal Models With the Progressive Scaling Strategy","year":"2024"},{"key":"ref15","article-title":"MiniCPM-V: A GPT-4V level MLLM on your phone","author":"Yao","year":"2024","journal-title":"arXiv:2408.01800"},{"key":"ref16","volume-title":"The Book of Why: The New Science of Cause and Effect","author":"Pearl","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01077"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS55030.2025.11242427"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref20","first-page":"53366","article-title":"Next-GPT: Any-to-any multimodal LLM","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref22","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref23","article-title":"VideoLLaMA 2: Advancing spatial\u2013temporal modeling and audio understanding in video-llms","author":"Cheng","year":"2024","journal-title":"arXiv:2406.07476"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0850"},{"key":"ref27","article-title":"MM-Vet: Evaluating large multimodal models for integrated capabilities","author":"Yu","year":"2023","journal-title":"arXiv:2308.02490"},{"key":"ref28","article-title":"RGB-th-bench: A dense benchmark for visual-thermal understanding of vision language models","author":"Moshtaghi","year":"2025","journal-title":"arXiv:2503.19654"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128671"},{"key":"ref30","volume-title":"Causal Inference in Statistics: A Primer","author":"Pearl","year":"2016"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01751"},{"key":"ref32","article-title":"Improved baselines with visual instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv:2310.03744"},{"key":"ref33","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv:2409.12191"},{"key":"ref34","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Georgiev","year":"2024","journal-title":"arXiv:2403.05530"},{"key":"ref35","volume-title":"Hello GPT-4O","year":"2024"},{"key":"ref36","volume-title":"Claude 3.5 Sonnet","year":"2024"},{"key":"ref37","article-title":"Enhanced vision-language models for diverse sensor understanding: Cost-efficient optimization and benchmarking","author":"Chung","year":"2024","journal-title":"arXiv:2412.20750"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0285(92)90007-O"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1214\/09-SS057"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref41","volume-title":"Natural Language Processing With Python: Analyzing Text With the Natural Language Toolkit","author":"Bird","year":"2009"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.02.004"},{"issue":"2","key":"ref44","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","volume":"1","author":"Hu"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00571"},{"key":"ref46","volume-title":"Thermal Dogs and People X6ejw Dataset","year":"2022"},{"key":"ref47","volume-title":"Pet Dataset","year":"2024"},{"key":"ref48","volume-title":"Thermal Dataset","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02066-6"},{"key":"ref50","volume-title":"Animal-Detection-Flir-Extra Dataset","year":"2023"},{"key":"ref51","volume-title":"Chips-Thermal-Face-Dataset","year":"2020"},{"key":"ref52","volume-title":"IFSOD Dataset","year":"2023"},{"key":"ref53","first-page":"1","article-title":"DIODE: A dense indoor and outdoor DEpth dataset","author":"Vasiljevic","year":"2019","journal-title":"arXiv:1908.00463"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref55","article-title":"DIML\/CVL RGB-D dataset: 2M RGB-D images of natural indoor and outdoor scenes","author":"Cho","year":"2021","journal-title":"arXiv:2110.11590"},{"key":"ref56","volume-title":"UNIFESP X-ray Body Part Classifier Competition","year":"2022"},{"key":"ref57","volume-title":"X-ray Baggage Detection Dataset","year":"2022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00103"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00429"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2046811"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00267"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50045-1"},{"key":"ref63","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/BF02295996"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_41"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.866"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.5244\/c.35.74"},{"key":"ref68","article-title":"Learning to focus: Causal attention distillation via gradient-guided token pruning","author":"Guo","year":"2025","journal-title":"arXiv:2506.07851"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11478662.pdf?arnumber=11478662","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T04:32:23Z","timestamp":1776486743000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11478662\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3675431","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}