Facial expression recognition is a challenging task due to two major problems: the presence of inter-subject variations in facial expression recognition dataset and impure expressions posed by human subjects. In this paper we present a novel Human-to-Animation conditional Generative Adversarial Network (HA-GAN) to overcome these two problems by using many (human faces) to one (animated face) mapping. Specifically, for any given input human expression image, our HA-GAN transfers the expression information from the input image to a fixed animated identity. Stylized animated characters from the Facial Expression Research Group-Database (FERGDB) are used for the generation of fixed identity. By learning this many-to-one identity mapping function using our proposed HA-GAN, the effect of inter-subject variations can be reduced in Facial Expression Recognition(FER). We also argue that the expressions in the generated animated images are pure expressions and since FER is performed on these generated images, the performance of facial expression recognition is improved. Our initial experimental results on the state-of-the-art datasets show that facial expression recognition carried out on the generated animated images using our HA-GAN framework outperforms the baseline deep neural network and produces comparable or even better results than the state-of-the-art methods for facial expression recognition.

No abstract

Motivation is one of the important factors that increase the success of athletes, especially who lift weights. It increases not only the success of the athletes but also influences other notions such as increasing self-confidence, decreasing anxiety, and improving endurance. Although motivation has a key role in the performance of athletes, most of the athletes may be fully motivated only in competition environments. However, being motivated only in competition environments is not enough for athletes since they spend most of their time in training. If they are motivated in training environments as motivated as in competition environments, they can increase their performance, however, being motivated during training sessions is not easy since there are not enough motivational factors, such as spectators, in training environments. In order to solve this problem, this study aims to increase the motivation levels of powerlifters during training sessions by developing a virtual competition environment. In this environment, the athletes experience a virtual competition environment by using HTC Vive. To understand the efficiency of the virtual environment, it was tested with 32 professional athletes. The findings illustrated that using VR technology was beneficial to increase the level of motivation of powerlifters during training sessions.

Organ at risk (OAR) segmentation is a crucial step for treatment planning and outcome determination in radiotherapy treatments of cancer patients. Several deep learning based segmentation algorithms have been developed in recent years, however, U-Net remains the de facto algorithm designed specifically for biomedical image segmentation and has spawned many variants with known weaknesses. In this study, our goal is to present simple architectural changes in U-Net to improve its accuracy and generalization properties. Unlike many other available studies evaluating their algorithms on single center data, we thoroughly evaluate several variations of U-Net as well as our proposed enhanced architecture on multiple data sets for an extensive and reliable study of the OAR segmentation problem. Our enhanced segmentation model includes (a)architectural changes in the loss function, (b)optimization framework, and (c)convolution type. Testing on three publicly available multi-object segmentation data sets, we achieved an average of 80% dice score compared to the baseline U-Net performance of 63%.