We propose HandLer, a novel convolutional architecture that can jointly detect and track hands online in unconstrained videos. HandLer is based on Cascade-RCNN with additional three novel stages. The ...

Solving the forward kinematics problem of robots with high degrees of freedom using neural networks is a really innovative field of study. However, conventional neural network has not been adequate to ...

Novel effective connectivity inference using ultra-group constrained orthogonal forward regression and elastic multilayer perceptron classifier for MCI identification.