We propose an action recognition framework using Generative Adversarial Networks. Our model involves training a deep convolutional generative adversarial network (DCGAN) using a large video activity dataset without label information. Then we use the trained discriminator from the GAN model as an unsupervised pre-training step and fine-tune the trained discriminator model on a labeled dataset to...

Generative Adversarial Networks (GANs) have been shown to be able to sample impressively realistic images. GAN training consists of a saddle point optimization problem that can be thought of as an adversarial game between a generator which produces the images, and a discriminator, which judges if the images are real. Both the generator and the discriminator are commonly parametrized as deep con...

In this paper, we introduce a simple but quite effective recognition framework dubbed D-PCN, aiming at enhancing feature extracting ability of CNN. The framework consists of two parallel CNNs, a discriminator and an extra classifier which takes integrated features from parallel networks and gives final prediction. The discriminator is core which drives parallel networks to focus on different re...

A timing discriminator design for space flight delay line image systems is presented. This discriminator processes delay line signal pulses having a few ns width and recovers event timing centroids with an accuracy better than 100 ps full width at half maximum. For space flight use, it is important to minimize parts count and power consumption. Because it is difficult or impossible to adjust eq...

In this paper a new non-coherent architecture for GNSS tracking loops is proposed and analyzed. A non-coherent phase discriminator, able to extend the integration time beyond the bit duration is derived from the Maximum Likelihood principle and integrated into a Costas loop. The discriminator is non-coherent in the sense that the bit information is removed by using a non-linear operation. By jo...

........................................................................................................................ 1 OBJECTIVE ....................................................................................................................... 2 BACKGROUND ................................................................................................................ 2 TASK 1. OPTIMIZA...

Despite of the success of Generative Adversarial Networks (GANs) for image generation tasks, the trade-off between image diversity and visual quality are an well-known issue. Conventional techniques achieve either visual quality or image diversity; the improvement in one side is often the result of sacrificing the degradation in the other side. In this paper, we aim to achieve both simultaneous...

Generative adversarial networks (GANs) are considered a new overarching paradigm in the world of generative models. However, it is well-known that GANs are difficult to train, and several different techniques have been proposed in order to stabilize their training. In this paper, we propose a novel training method called manifold matching, and a new GAN model called Manifold Matching GAN (MMGAN...