Publications

@article{li2025gnlm,
  author    = {Li, Xiang and Chang, Qiong and Li, Yun and Miyazaki, Jun},
  title     = {3D GNLM: Efficient 3D Non-Local Means Kernel with Nested Reuse Strategies for Embedded GPUs},
  journal   = {ACM Transactions on Architecture and Code Optimization},
  year      = {2025},
  month     = {sep},
  volume    = {22},
  number    = {3},
  pages     = {1--22},
  articleno = {90},
  numpages  = {22},
  issn      = {1544-3973},
  doi       = {10.1145/3744909},
  url       = {https://doi.org/10.1145/3744909},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY, USA}
}
    

@article{chang2025fast,
  author    = {Chang, Qiong and Chen, Xinyuan and Li, Xiang and Wang, Weimin and Miyazaki, Jun},
  title     = {Faster than Fast: Accelerating Oriented FAST Feature Detection on Low-end Embedded GPUs},
  journal   = {ACM Transactions on Embedded Computing Systems},
  year      = {2025},
  month     = {apr},
  volume    = {24},
  number    = {3},
  pages     = {1--22},
  issn      = {1539-9087},
  eissn     = {1558-3465},
  doi       = {10.1145/3725217},
  url       = {https://doi.org/10.1145/3725217},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY, USA}
}
    

@inproceedings{li2025nlm,
  author    = {Li, Xiang and Chang, Qiong and Li, Yun and Miyazaki, Jun},
  title     = {Efficient Parallel Implementation of Non-Local Means Algorithm on GPU},
  booktitle = {Proceedings of the 17th Workshop on General Purpose Processing Using GPU},
  series    = {GPGPU '25},
  year      = {2025},
  month     = {mar},
  pages     = {55--61},
  doi       = {10.1145/3725798.3725807},
  url       = {https://doi.org/10.1145/3725798.3725807},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY, USA}
}
    

@article{li2024gist,
  author    = {Li, Xiang and Chang, Qiong and Zha, Aolong and Chang, Shijie and Li, Yun and Miyazaki, Jun},
  title     = {An Optimized GPU Implementation for GIST Descriptor},
  journal   = {ACM Transactions on Architecture and Code Optimization},
  year      = {2024},
  month     = {nov},
  volume    = {21},
  number    = {4},
  pages     = {1--24},
  issn      = {1544-3973},
  doi       = {10.1145/3689339},
  url       = {https://doi.org/10.1145/3689339},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY, USA}
}
    

@article{chang2023sobel,
  author    = {Chang, Qiong and Li, Xiang and Li, Yun and Miyazaki, Jun},
  title     = {Multi-directional Sobel Operator Kernel on GPUs},
  journal   = {Journal of Parallel and Distributed Computing},
  year      = {2023},
  month     = {jul},
  volume    = {177},
  pages     = {160--170},
  issn      = {0743-7315},
  doi       = {10.1016/j.jpdc.2023.03.004},
  url       = {https://doi.org/10.1016/j.jpdc.2023.03.004},
  publisher = {Elsevier BV}
}
    

@inproceedings{chang2023stereovae,
  author    = {Chang, Qiong and Li, Xiang and Xu, Xin and Liu, Xin and Li, Yun and Miyazaki, Jun},
  title     = {StereoVAE: A Lightweight Stereo-Matching System Using Embedded GPUs},
  booktitle = {2023 IEEE International Conference on Robotics and Automation (ICRA)},
  year      = {2023},
  month     = {may},
  pages     = {1982--1988},
  doi       = {10.1109/ICRA48891.2023.10160441},
  url       = {https://doi.org/10.1109/ICRA48891.2023.10160441},
  publisher = {IEEE}
}