Aug 2026· Multimedia Systems· Vol 32· 0 citations· 60 references
TL;DR
RS-CoT is proposed, a unified framework that enhances multimodal reasoning through CoT-based supervised fine-tuning (SFT) and self-consistency sampling (SCS) and self-consistency sampling (SCS)guided preference optimization for reliable multimodal reasoning in remote sensing.
RS-Florence is proposed, a compact unified model that addresses remote sensing perception systems through a Prompt-Driven Sequence-to-Sequence framework, which maps images and task-specific prompts into a unified sequence of natural language and discrete geometric tokens.
Yang Liu, Wei-Xing Luo, Huai-Zhou Qi et al.· Proceedings of the Thirty-Fi...· 0 citations
Existing class-incremental learning (CIL) methods for remote sensing (RS) scene classification often tend to be training-intensive or rely on static visual features that may inadequately capture the complex interclass similarity and intraclass diversity inherent in RS imagery. Moreover, directly reusing features from m...
Wen-Liang Du, Ji-Cun He, Jia-Qi Zhao et al.· IEEE Transactions on Geoscie...· 0 citations
Extensive experiments on multiple public RSCC benchmark datasets demonstrate that the proposed MGRL-RSCC effectively mitigates exposure bias and conservative generation problems in traditional autoregressive methods.
Fu-Tian Wang, Meng-Qi Wang, Xiao Wang et al.· 0 citations
This work proposes PromptRefine, a white-box SFUDA framework designed to anchor target adaptation through cross-modal intelligence, and leverages the zero-shot semantic priors of large-scale vision–language models to rectify source-biased predictions via a dynamic prompt fine-tuning mechanism.
Unknown authors· Journal of Electronic Imagin...· 0 citations
The Robust and Fine-grained training framework for CLIP-based vision-language models (RoFLIP) is proposed, enhancing both the robustness and granularity of vision-language alignment and underscore RoFLIP’s compositional reasoning and generalization abilities.
Yiwei Sun, Chuan-Bin Liu, Shan-Cheng Fang et al.· International Journal of Com...· 0 citations
AlignJEPA provides a parameter-efficient route for aligning Earth observation foundation models with language by using a pretrained AnySat visual encoder and a RemoteCLIP text encoder while training only a lightweight predictive alignment network.
Md Aminur Hossain, Omkumar Vaghasiya, R. Dwivedi et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.