-
Chapter and Conference Paper
Teacher and Student Joint Learning for Compact Facial Landmark Detection Network
Compact neural networks with limited memory and computation are demanding in recently popularized mobile applications. The reduction of network parameters is an important priority. In this paper, we address a ...
-
Chapter and Conference Paper
Convolution with Logarithmic Filter Groups for Efficient Shallow CNN
In convolutional neural networks (CNNs), the filter grou** in convolution layers is known to be useful to reduce the network parameter size. In this paper, we propose a new logarithmic filter grou** which ...
-
Chapter and Conference Paper
Learning Features Robust to Image Variations with Siamese Networks for Facial Expression Recognition
This paper proposes a computationally efficient method for learning features robust to image variations for facial expression recognition (FER). The proposed method minimizes the feature difference between an ...
-
Chapter and Conference Paper
High-Speed Periodic Motion Reconstruction Using an Off-the-shelf Camera with Compensation for Rolling Shutter Effect
In recent years, high-speed signal reconstruction with sub-Nyquist sampling have attracted the attention of researchers in the signal processing field. Nonetheless, such methods have been limited either by the...
