# ViCxLSTM

**Repository Path**: LHR_97/ViCxLSTM

## Basic Information

- **Project Name**: ViCxLSTM
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-12-06
- **Last Updated**: 2025-12-06

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# ViCxLSTM: An extended Long Short-term Memory vision transformer for complex remote sensing scene classification

[Swalpa Kumar Roy](https://swalpa.github.io/), [Ali Jamali](https://www.researchgate.net/profile/Ali-Jamali/), [Koushik Biswas], [Danfeng Hong](https://sites.google.com/view/danfeng-hong/), and [Pedram Ghamisi](https://www.lancaster.ac.uk/lec/about-us/people/pedram-ghamisi/)


<img src="Architecture.jpg"/>
___________


Citation
---------------------

**Please kindly cite the paper if this code is useful and helpful for your research.**

       @article{ROY2025101478,
               title = {ViCxLSTM: An extended Long Short-term Memory vision transformer for complex remote sensing scene classification},
               author = {Swalpa Kumar Roy, Ali Jamali, Koushik Biswas, Danfeng Hong, Pedram Ghamisi},
               journal = {International Journal of Applied Earth Observation and Geoinformation},
               pages = {104801},
               year = {2025},
               issn = {1569-8432},
               doi = {https://doi.org/10.1016/j.jag.2025.104801},
               url = {https://www.sciencedirect.com/science/article/pii/S1569843225004480},
              }


<img src="NWPURESISC_45.jpg"/>

Fig. 2. Several examples of the high-resolution aerial imagery for various scene classes in the NWPU RESISC–45
data benchmark.


<img src="Training_Time.jpg"/>

Fig. 3. Training time comparison of the developed deep learning models.


<img src="Parameters_Accuracy.jpg"/>

Fig. 4. Comparison of the number of Parameters of the developed deep learning models.


Acknowledgement
---------------------
xLSTM: Extended Long Short-Term Memory is adapted from (https://github.com/NX-AI/xlstm).

## License

Copyright (c) 2025 Ali Jamali. Released under the MIT License. See [LICENSE](LICENSE) for details.