Advancements of Vision-Language Models (VLMs) in Remote Sensing
A special issue of Remote Sensing (ISSN 2072-4292).
Deadline for manuscript submissions: 15 July 2025 | Viewed by 1088
Special Issue Editors
Interests: object information representation and intelligent recognition; hyperspectral image classification
Interests: vision-language models; remote sensing; intelligent transportation; egocentric vision
Interests: vision-language models; remote sensing; graph learning; noise-based models
Interests: image processing; machine learning; remote sensing image interpretation
Interests: geography; urban climate; urban thermal infrared remote sensing; artificial intelligence; change detection; spatiotemporal big data; climate change and complex extreme weather; environmental exposure and health assessment
Special Issue Information
Dear Colleague
The research line of vision–language models (VLMs) promotes remote sensing progress, using natural and significant multimodal (vision and language) data processing abilities. This technology provides a feasible scheme for designing more effective paradigms of traditional remote sensing tasks (e.g., object detection, road extraction, etc.). Furthermore, the remarkable data processing ability of VLMs makes it possible to accomplish complex multimodal tasks (e.g., remote sensing VQA) that previous visual models found hard to achieve in an effective and efficient way. As the complexity of the global geopolitical landscape intensifies, there is a particular need for more efficient remote sensing image processing technologies as they become more critical in information-driven warfare. VLMs offer a powerful tool for gathering intelligence from remote sensing images; the technology’s potential in future multimodal remote sensing applications is highly promising and warrants further exploration, especially in the context of ground surveillance and reconnaissance.
This Special Issue aims to explore the advancements of VLMs in remote sensing, including, but not limited to, the improvements brought by VLMs on traditional remote sensing tasks, the application of VLMs on multimodal tasks in remote sensing, and the discussion of VLMs on the potential future tasks that may emerge due to evolving situational requirements and remote sensing technological developments.
This Special Issue seeks to cover a wide range of topics related to the advancements of VLMs in remote sensing, including, but not limited to, the following aspects:
- VLMs for multimodal remote sensing data fusion;
- Automatic annotation and the description of remote sensing images based on VLMs;
- VLMs for the semantic segmentation and change detection of remote sensing images;
- Object detection and tracking of remote sensing images based on VLMs;
- Super-resolution reconstruction of remote sensing images using VLMs;
- Land cover and scene classification based on VLMs;
- VLMs for multimodal remote sensing image alignment;
- VLMs for open-world remote sensing tasks;
- New multimodal remote sensing benchmark datasets;
- Efficient multimodal retrieval of remote sensing images;
- The large and generalized pretraining of VLMs for remote sensing.
Dr. Zhixi Feng
Dr. Chuang Yang
Dr. Hongyuan Zhang
Dr. Chen Yang
Dr. Yue Chang
Guest Editors
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
Keywords
- vision–language models (VLMs)
- multimodal data fusion
- remote sensing VQA
- automatic annotation
- semantic segmentation
- object detection
- super-resolution reconstruction
- change detection
- pretraining models
- multimodal retrieval
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.
Further information on MDPI's Special Issue policies can be found here.
