As the opportunity to interact with humanoid robots and virtual avatars increases, the emotional impact of the interaction with these artificial agents becomes an important consideration. The uncanny valley effect is a psychological phenomenon relevant to such a consideration. Although the uncanny valley remained untested for several decades, recent empirical studies confirmed the uncanny valley effect when human observers rated their liking of robots’ faces. To uncover the uncanny valley in behavioral measures of affective response, the present study used two implicit affective tasks, affective priming and single-category implicit association test (IAT). Positivity scores for each of the images of robot faces were derived and were plotted against the humanness rating of the robot faces. The results demonstrated the uncanny valley effect in these implicit behavioral measures. The finding indicates the effectiveness of using these implicit measures to assess affective responses to individual items rather than to groups of items, and it suggests the potential of these behavioral paradigms for wider application outside laboratory research.

Abstract The computer vision community has extensively researched the area of human motion analysis, which primarily focuses on pose estimation, activity recognition, pose or gesture recognition and so on. However for many applications, like monitoring of functional rehabilitation of patients with musculo skeletal or physical impairments, the requirement is to comparatively evaluate human motion. In this survey, we capture important literature on vision-based monitoring and physical rehabilitation that focuses on comparative evaluation of human motion during the past two decades and discuss the state of current research in this area. Unlike other reviews in this area, which are written from a clinical objective, this article presents research in this area from a computer vision application perspective. We propose our own taxonomy of computer vision-based rehabilitation and assessment research which are further divided into sub-categories to capture novelties of each research. The review discusses the challenges of this domain due to the wide ranging human motion abnormalities and difficulty in automatically assessing those abnormalities. Finally, suggestions on the future direction of research are offered.

Human pose estimation through deep learning has achieved very high accuracy over various difficult poses. However, these are computationally expensive and are often not suitable for mobile based systems. In this paper, we investigate the use of MobileNets, which is well-known to be a light-weight and efficient CNN architecture for mobile and embedded vision applications. We adapt MobileNets for pose estimation inspired by the hourglass network. We introduce a novel split stream architecture at the final two layers of the MobileNets. This approach reduces over-fitting, resulting in improvement in accuracy and reduction in parameter size. We also show that by maintaining part of the original network we are able to improve accuracy by transferring the learned features from ImageNet pre-trained MobileNets. The adapted model is evaluated on the FLIC dataset. Our network out-performed the default MobileNets for pose estimation, as well as achieved performance comparable to the state of the art results while reducing inference time significantly.