End-to-end convolution representation learning has been proved to be ver...
Deep neural network with dual-path bi-directional long short-term memory...
In this paper, we propose a method called Hodge and Podge for sound even...
Deep neural network with dual-path bi-directional long short-term memory...
In this paper, we present a method called HODGEPODGE[1] for
large-scale ...
Training convolutional neural networks for image classification tasks us...
Deep dilated temporal convolutional networks (TCN) have been proved to b...
Deep gated convolutional networks have been proved to be very effective ...
Short-time Fourier transform (STFT) is used as the front end of many pop...
Conventionally, convolutional neural networks (CNNs) process different i...
Softmax activation is commonly used to output the probability distributi...
Recent advances in fine-grained recognition utilize attention maps to
lo...
J-vector has been proved to be very effective in text-dependent speaker
...
Face attributes are interesting due to their detailed description of hum...
Online and stochastic learning has emerged as powerful tool in large sca...