Learning new sport actions: Pilot study to investigate the imitative and the verbal instructive teaching methods in motor education

Design and Development of an Imitation Detection System for Human Action Recognition Using Deep Learning

Human action recognition (HAR) is a rapidly growing field with numerous applications in various domains. HAR involves the development of algorithms and techniques to automatically identify and classify human actions from video data. Accurate recognition of human actions has significant implications in fields such as surveillance and sports analysis and in the health care domain. This paper presents a study on the design and development of an imitation detection system using an HAR algorithm based on deep learning. This study explores the use of deep learning models, such as a single-frame convolutional neural network (CNN) and pretrained VGG-16, for the accurate classification of human actions. The proposed models were evaluated using a benchmark dataset, KTH. The performance of these models was compared with that of classical classifiers, including K-Nearest Neighbors, Support Vector Machine, and Random Forest. The results showed that the VGG-16 model achieved higher accuracy than the single-frame CNN, with a 98% accuracy rate.

Visual estimation of the force applied by another person

As observers, we believe that we can visually estimate the force that another person is applying to a material. However, it is unclear what kind of cues we use to do this. We focused on two types of visual change that occur when actors push an elastic material from above with their fingers: visual shaking and visual indentation depth. The first one relates to a finger/hand shaking, known as an "induced tremor", and the second one relates to material deformation due to the application of force. We found that human observers mainly used visual shaking to estimate the force being applied by another person in a video clip. Overall, the apparent applied force was perceived to be stronger when the level of visual shaking was greater. We also found that observers mainly used visual indentation depth and visual shaking to estimate the softness rating of materials. Overall, the apparent softness was perceived to be greater when the visual indentation depth was larger and the level of visual shaking was lower, which indicates that observers use visual shaking to estimate the force being applied, and that estimated force is then used for an estimation of softness.

The Best of Two Different Visual Instructions in Improving Precision Ball-Throwing and Standing Long Jump Performances in Primary School Children

Two observational learning approaches have been shown to be successful in improving children's motor performances: one is "technique-focused", another is "goal-focused". In this study, we sought to compare the effectiveness of these two strategies, thus testing for the more efficient method of observational learning to enhance motor skills in primary school children. To this end, two experiments were designed. Experiment 1 involved a precision ball throwing task. Experiment 2 involved a standing long jump task. A total of 792 subjects (aged 6-11) participated in this study and were divided into technique-focus (Experiment 1 n = 200; Experiment 2 n = 66), goal-focus (Experiment 1 n = 195; Experiment 2 n = 68), and control groups (Experiment 1 n = 199; Experiment 2 n = 64). The experiments were divided into pretest, practice, and retention phases. During the practice phase, the technique-focus and goal-focus groups were given different visual instructions on how to perform the task. The results showed that children aged 10-11 belonging to the technique-focus group performed significantly better in the practice phase than both the goal-focus and the control group (p < 0.001), but only for the precision ball throwing task. These findings could be useful for training adaptation in the context of motor learning and skills acquisition.