A Neural Net Training Interface on TensorFlow, with focus on speed
Tensorpack is a neuralnetwork training interface based on TensorFlow v1. Uses TensorFlow in the efficient way with no extra overhead. On common CNNs, it runs training 1.2~5x faster than the equivalent Keras code. Your training can probably gets faster if written with Tensorpack. Scalable data-parallel multi-GPU / distributed training strategy is off-the-shelf to use.
Cross Audio-Visual Recognition using 3D Architectures
...The essential problem is to find the correspondence between the audio and visual streams, which is the goal of this work. We proposed the utilization of a coupled 3D Convolutional NeuralNetwork (CNN) architecture that can map both modalities into a representation space to evaluate the correspondence of audio-visual streams using the learned multimodal features.