{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:05:03Z","timestamp":1784268303476,"version":"3.55.0"},"reference-count":69,"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":[{"name":"Institute of Information and Communications Technology Planning and Evaluation"},{"name":"Korean Government [Ministry of Science and ICT (MSIT)]","award":["RS-2022-II220124"],"award-info":[{"award-number":["RS-2022-II220124"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3707796","type":"journal-article","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T19:46:19Z","timestamp":1783626379000},"page":"7444-7459","source":"Crossref","is-referenced-by-count":0,"title":["Enhanced Vision-Language Models for Diverse Sensor Understanding: Cost-Efficient Optimization and Benchmarking"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-5397-2687","authenticated-orcid":false,"given":"Sangyun","family":"Chung","sequence":"first","affiliation":[{"name":"Integrated Vision Language Laboratory, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3188-2080","authenticated-orcid":false,"given":"Youngjoon","family":"Yu","sequence":"additional","affiliation":[{"name":"Integrated Vision Language Laboratory, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4819-1219","authenticated-orcid":false,"given":"Seyeon","family":"Kim","sequence":"additional","affiliation":[{"name":"Integrated Vision Language Laboratory, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7778-2115","authenticated-orcid":false,"given":"Youngchae","family":"Chee","sequence":"additional","affiliation":[{"name":"Integrated Vision Language Laboratory, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5306-6853","authenticated-orcid":false,"given":"Yong Man","family":"Ro","sequence":"additional","affiliation":[{"name":"Integrated Vision Language Laboratory, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"17283","article-title":"Grounding language models to images for multimodal inputs and outputs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koh"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3522802"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3523801"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3542272"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3187288"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3076556"},{"key":"ref8","article-title":"MPLUG-DocOwl: Modularized multimodal large language model for document understanding","author":"Ye","year":"2023","journal-title":"arXiv:2307.02499"},{"key":"ref9","volume-title":"Hello GPT-4O","year":"2024"},{"key":"ref10","article-title":"GPT-driver: Learning to drive with GPT","author":"Mao","year":"2023","journal-title":"arXiv:2310.01415"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/FLLM63129.2024.10852498"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3546853"},{"key":"ref14","article-title":"MobileVLM: A fast, strong and open vision language assistant for mobile devices","author":"Chu","year":"2023","journal-title":"arXiv:2312.16886"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00708"},{"key":"ref16","article-title":"Pretraining vision-language model for difference visual question answering in longitudinal chest X-rays","author":"Cho","year":"2024","journal-title":"arXiv:2402.08966"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610090"},{"key":"ref18","article-title":"ReKep: Spatio-temporal reasoning of relational keypoint constraints for robotic manipulation","author":"Huang","year":"2024","journal-title":"arXiv:2409.01652"},{"key":"ref19","article-title":"A3 VLM: Actionable articulation-aware vision language model","author":"Huang","year":"2024","journal-title":"arXiv:2406.07549"},{"key":"ref20","volume-title":"InternVL2: Better Than the Best\u2014Expanding Performance Boundaries of Open-Source Multimodal Models With the Progressive Scaling Strategy","year":"2024"},{"key":"ref21","article-title":"SpatialBot: Precise spatial understanding with vision language models","author":"Cai","year":"2024","journal-title":"arXiv:2406.13642"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-025-00095-w"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02510"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.bionlp-1.35"},{"key":"ref25","article-title":"LLMs can evolve continually on modality for X-modal reasoning","author":"Yu","year":"2024","journal-title":"arXiv:2410.20178"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref27","volume-title":"LLAVA-next: Improved Reasoning, OCR, and World Knowledge","author":"Liu","year":"2024"},{"key":"ref28","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":"ref29","article-title":"VideoLLaMA 2: Advancing spatial\u2013temporal modeling and audio understanding in video-LLMs","author":"Cheng","year":"2024","journal-title":"arXiv:2406.07476"},{"key":"ref30","article-title":"MiniCPM-V: A GPT-4 V level MLLM on your phone","author":"Yao","year":"2024","journal-title":"arXiv:2408.01800"},{"key":"ref31","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":"ref32","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref33","article-title":"InternVL3.5: Advancing open-source multimodal models in versatility, reasoning, and efficiency","author":"Wang","year":"2025","journal-title":"arXiv:2508.18265"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref35","article-title":"PandaGPT: One model to instruction-follow them all","author":"Su","year":"2023","journal-title":"arXiv:2305.16355"},{"key":"ref36","article-title":"MME: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023","journal-title":"arXiv:2306.13394"},{"key":"ref37","article-title":"SEED-bench: Benchmarking multimodal LLMs with generative comprehension","author":"Li","year":"2023","journal-title":"arXiv:2307.16125"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref39","article-title":"Q-bench: A benchmark for general-purpose foundation models on low-level vision","author":"Wu","year":"2023","journal-title":"arXiv:2309.14181"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3445770"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0285(92)90007-O"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1037\/10037-000"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref45","article-title":"Phantom of latent for large language and vision models","author":"Lee","year":"2024","journal-title":"arXiv:2409.14713"},{"key":"ref46","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv:2403.05530"},{"key":"ref47","volume-title":"Claude 3.5 Sonnet","year":"2024"},{"key":"ref48","volume-title":"Prolific","year":"2025"},{"issue":"3","key":"ref49","first-page":"324","article-title":"Rank analysis of incomplete block designs","volume":"39","author":"Bradley","year":"1952","journal-title":"Biometrika"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2338"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298682"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00571"},{"key":"ref53","volume-title":"Thermal Dogs and People X6EJW Dataset","year":"2022"},{"key":"ref54","volume-title":"Pet Dataset","year":"2024"},{"key":"ref55","volume-title":"Thermal Dataset","year":"2023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02066-6"},{"key":"ref57","volume-title":"Animal-Detection-Flir-Extra Dataset","year":"2023"},{"key":"ref58","volume-title":"Chips-Thermal-Face-Dataset","year":"2020"},{"key":"ref59","year":"2023","journal-title":"IFSOD Dataset"},{"key":"ref60","article-title":"DIODE: A dense indoor and outdoor DEpth dataset","author":"Vasiljevic","year":"2019","journal-title":"arXiv:1908.00463"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref62","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":"ref63","volume-title":"Unifesp X-Ray Body Part Classifier Competition","author":"Farina","year":"2022"},{"key":"ref64","volume-title":"X-ray Baggage Detection Dataset","year":"2022"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0441"},{"key":"ref66","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref67","article-title":"A general theoretical paradigm to understand learning from human preferences","author":"Azar","year":"2023","journal-title":"arXiv:2310.12036"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3946"},{"key":"ref69","article-title":"DeepSeekMath: Pushing the limits of mathematical reasoning in open language models","author":"Shao","year":"2024","journal-title":"arXiv:2402.03300"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11602763.pdf?arnumber=11602763","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T05:19:00Z","timestamp":1784265540000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11602763\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3707796","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}