About this Research Topic
Vision Transformer (ViT) is a transformer-like model that handles vision processing tasks. In contrast to the previous recurrent network (RNN) or CNN, ViT can better mine the global information from the sequence by self-attention mechanism. Thus, it has demonstrated superiority in a wide range of applications in remote sensing data analysis as it is able to capture complex spatial and temporal relationships in RS, such as change detection, hyperspectral imagery, and aircraft detection.
However, there are still many challenges and opportunities for applying Transformer to large-scale and real-time RS applications. This special issue aims to provide a platform for researchers and practitioners to share their latest advances and insights on the theory and application of Transformers in RS.
The scope of this Research Topic is as follows:
1. Transformer-based approaches for remote sensing image/SAR classification and land-use segmentation.
2. Transformer-based rotated object detection and tracking in remote sensing imagery.
3. Transformer-based super-resolution/Pan-sharpening techniques for remote sensing imagery.
4. Transformer-based time series analysis for satellite video.
5. Fusion of remote sensing data from different modalities using transformer models
6. Deep learning approaches for Transformer-based remote sensing applications.
However, there are still many challenges and opportunities for applying Transformer to large-scale and real-time RS applications. This special issue aims to provide a platform for researchers and practitioners to share their latest advances and insights on the theory and application of Transformers in RS.
The scope of this Research Topic is as follows:
1. Transformer-based approaches for remote sensing image/SAR classification and land-use segmentation.
2. Transformer-based rotated object detection and tracking in remote sensing imagery.
3. Transformer-based super-resolution/Pan-sharpening techniques for remote sensing imagery.
4. Transformer-based time series analysis for satellite video.
5. Fusion of remote sensing data from different modalities using transformer models
6. Deep learning approaches for Transformer-based remote sensing applications.
Keywords: remote sensing, land-use, transformer, computer vision, image processing
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
