Complex skills with aerial phases, such as somersaults or release-regrasp skills make up about 45 % of all elements in artistic gymnastics. The underlying mechanics of these skills have been studied extensively, and visual information is thought to assist gymnasts in skill performance. However, empirical evidence on the role of gaze behavior and its interplay with movement behavior in complex s...

Despite its recent advances and increasing industrial interest, cloud gaming’s high bandwidth usage is still one of major challenges. In this paper, we demonstrate how incorporating visual attention into gaming helps to reduce bitrate without negatively affecting the player’s quality experience. We show that current models, which work well for normal videos, underperform in context videos. Henc...

High-efficient visual search ability is the key for the athletes to win their games. Visual search is an important way for the athletes to catch effective information on site within complicated environment as well as the manifestation of their regulating and controlling their mental status and skill abilities within complicated environment. Maintaining an appropriate level of anxiety during exe...

Maritime safety and security require a constant surveillance of the traffic at sea, and several human actors are in charge of this control. Potential risks alerts, suspicious vessels and description of the situation are managed by visual surveillance systems. But these systems do not provide real analysis tools for maritime traffic data. Geovisualization and visual analytics have shown to be ve...

Art historians, artists, psychologists, and neuroscientists have long asserted that artists perceive the world differently than nonartists. Although empirical research on the nature and correlates of skilled drawing is limited, the available evidence supports this view: artists outperform nonartists on visual analysis and form recognition tasks and their perceptual advantages are correlated wit...

We introduce skill chaining, a skill discovery method for reinforcement learning agents in continuous domains. Skill chaining produces chains of skills leading to an end-of-task reward. We demonstrate experimentally that skill chaining is able to create appropriate skills in a challenging continuous domain and that doing so results in performance gains.