Ryugaku Jinja · Professor Archive
Public Professor Archive
Nobutaka Kuroki黒木 修隆
Kobe University · Graduate School of Engineering / Faculty of Engineering · 准教授
- Publications
- 4
- Projects
- 4
- Keywords
- 7
留学
神社Kobe University · Graduate School of Engineering / Faculty of Engineering · 准教授
Research keywordsEnergy harvesting・CNN・voltage boost converter・Convolutional neural・ultra-low power・Detecting tampered・diode using a hysteresis
This is a public-data preview. Personalized fit, contact angles, and saved workflows require sign-in.
- An error diagnosis technique based on location variable simulation employing dedicated multiplicity-limiter function and ordering for input patterns2024 · 2024年03月, The 25th Workshop on Synthesis And System Integration of Mixed Information Technologies, 125 - 130, 英語
- SRFLOW-Attention: Super Resolution with Multi-Head Attention for Effective Use of Low-Resolution Information2024 · This paper proposes normalizing flow‐based image super‐resolution techniques using attention modules. In the proposed method, the features of the low‐resolution images are extracted using a Swin Transformer. Furthermore, multi‐head attention in the flow layers makes effective use of the feature maps. This architecture enables the efficient injection of low‐resolution image features extracted by the transformer into the flow layer. Experimental results at x4 magnifications showed that the proposed method achieved state‐of‐the‐art performance for quantitative metrics and visual quality among single‐loss architectures. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.
- Lightweight monocular depth estimation network using separable convolution2024 · 2024年03月, The 25th Workshop on Synthesis And System Integration of Mixed Information Technologies, 187 - 192, 英語
- A CNN network suitable for fpga implementation in surveillance camera systems2024 · 2024年03月, The 25th Workshop on Synthesis And System Integration of Mixed Information Technologies, 95 - 100, 英語
Next stepSign in for fit and contact guidance
Personalized fit, contact angles, and saved workflows require sign-in.