3 papers
cs.SD2021
MS-SincResNet: Joint learning of 1D and 2D kernels using multi-scale SincNet and ResNet for music genre classification
Pei-Chun Chang, Yong-Sheng Chen, Chang-Hsing Lee
In this study, we proposed a new end-to-end convolutional neural network, called MS-SincResNet, for music genre classification. MS-SincResNet appends 1D multi-scale SincNet (MS-Sin…
cs.CV2021
Learning Facial Representations from the Cycle-consistency of Face
Jia-Ren Chang, Yong-Sheng Chen, Wei-Chen Chiu
Faces manifest large variations in many aspects, such as identity, expression, pose, and face styling. Therefore, it is a great challenge to disentangle and extract these character…
cs.CV2017
Deep Competitive Pathway Networks
Jia-Ren Chang, Yong-Sheng Chen
In the design of deep neural architectures, recent studies have demonstrated the benefits of grouping subnetworks into a larger network. For examples, the Inception architecture in…