Exploring Visual Patterns and Judgments Predicated on Role Specificity: Case Studies of Expertise in Gymnastics

Action Quality Assessment Model Using Specialists' Gaze Location and Kinematics Data-Focusing on Evaluating Figure Skating Jumps

Action quality assessment (AQA) tasks in computer vision evaluate action quality in videos, and they can be applied to sports for performance evaluation. A typical example of AQA is predicting the final score from a video that captures an entire figure skating program. However, no previous studies have predicted individual jump scores, which are of great interest to competitors because of the high weight of competition. Despite the presence of unnecessary information in figure skating videos, human specialists can focus and reduce information when they evaluate jumps. In this study, we clarified the eye movements of figure skating judges and skaters while evaluating jumps and proposed a prediction model for jump performance that utilized specialists' gaze location to reduce information. Kinematic features obtained from the tracking system were input into the model in addition to videos to improve accuracy. The results showed that skaters focused more on the face, whereas judges focused on the lower extremities. These gaze locations were applied to the model, which demonstrated the highest accuracy when utilizing both specialists' gaze locations. The model outperformed human predictions and the baseline model (RMSE:0.775), suggesting a combination of human specialist knowledge and machine capabilities could yield higher accuracy.

The Relationship Between the Perceived Movement Quality and the Kinematic Pattern of Complex Skills in Gymnastics

The study aimed to investigate the relationship between the perceived movement quality of a gymnastics skill and its kinematic pattern, as well as the influence of expertise. Thirty participants with different levels of gymnastics expertise (n = 10 visual experts, n = 10 motor experts and n = 10 novices) were recruited for the study. They were instructed to compare the movement quality of eleven video sequences, showing different handstand - back handspring performances. To extract the kinematics, the performances were digitized. By means of an ongoing cluster analysis, the kinematic pattern as well as the pattern of the perceived movement quality of the skills were determined for each experimental group. The results of the cluster analysis of the different experimental groups were analyzed and compared. Expertise differences were found regarding the pattern of the perceived movement quality. There was a significant correlation between the dendrograms of the visual experts and the motor experts (p = .021), as well as between the dendrograms of the visual experts and the novices (p = .011). There was no significant correlation between the dendrograms of the motor experts and the novices (p = .173). The pattern of the perceived movement quality was not correlated with the holistic kinematic pattern of judged skills (p > .143). These results suggest perceptual and cognitive differences of the participants due to their different previous visual and motor experience.

Experiential Knowledge Affects the Visual Search Behaviors of Sprint Coaches and Sport Biomechanists

It is common for applied sport biomechanists and high-performance coaches to work closely together. A feature of this relationship is that both bring unique experiences and knowledge to the common goal of improving an athlete's performance. For sprint running, coaches and biomechanists place importance on different aspects of technique. The purpose of this paper was to determine if these differences in experiential knowledge impact coaches and biomechanists visual perception of sprinting technique. Sport biomechanists (n = 12) and, expert (n = 11) and developing (n = 11) coaches watched video of athletes sprinting at two different speeds while wearing eye tracking glasses and, retrospectively, reported on the technique features observed. Mixed methods ANOVAs were used to determine visual search strategies and efficiency and used to indicate the relationship between visual search and verbal commentary data. The speed of video playback was the main determinant of visual search behavior, significantly impacting the visual search rate and relative fixation duration at a number of areas of interest. The use of a visual pivot indicated all participants' visual search strategies were efficiency driven. Overall, the verbal commentary did not completely align with the eye tracking data and there were varying degrees of agreement with the identified technique related areas of interest for coaches and biomechanists. However, differences in visual search strategy and verbal commentary suggest that experiential knowledge impacts participants' observation and perception of sprinting technique.