Unilateral Spatial Neglect (USN) commonly results from a stroke or acquired brain injury. USN affects multiple modalities and results in failure to respond to stimuli on the contralesional side of space. Although USN is a heterogeneous syndrome, present-day therapy methods often fail to consider multiple modalities. Musical Neglect Therapy (MNT) is a therapy method that succeeds in incorporating multiple modalities by asking patients to make music. This research aimed to exploit the immersive and modifiable aspect of VR to translate MNT to a VR therapy tool. The tool was evaluated in a 2-week pilot study with four clinical users. These results are compared to a control group of four non-clinical users. Results indicated that patients responded to triggers in their entire environment and performance results could be clearly differentiated between clinical and non-clinical users. Moreover, patients increasingly corrected their head direction towards their neglected side. Patients stated that the use of VR increased their enjoyment of the therapy. This study contributes to the current research on rehabilitation for USN by proposing the first system to apply MNT in a VR environment. The tool shows promise as an addition to currently used rehabilitation methods. However, results are limited to a small sample size and performance metrics. Future work will focus on validating these results with a larger sample over a longer period. Moreover, future efforts should explore personalisation and gamification to tailor to the heterogeneity of the condition.

Accurately predicting where the user of a Virtual Reality (VR) application will be looking at in the near future improves the perceive quality of services, such as adaptive tile-based streaming or personalized online training. However, because of the unpredictability and dissimilarity of user behavior it is still a big challenge. In this work, we propose to use reinforcement learning, in particular contextual bandits, to solve this problem. The proposed solution tackles the prediction in two stages: (1) detection of movement; (2) prediction of direction. In order to prove its potential for VR services, the method was deployed on an adaptive tile-based VR streaming testbed, for benchmarking against a 3D trajectory extrapolation approach. Our results showed a significant improvement in terms of prediction error compared to the benchmark. This reduced prediction error also resulted in an enhancement on the perceived video quality.

One of the most frequent health problems is stress. It has been linked to negative effects on employee well-being in many occupations, and it is considered responsible for many physical and psychological problems. Traditional in-person relaxation therapy has proven to be effective in reducing stress. However, it has some drawbacks such as high cost, required infrastructure and the need for qualified trainers. Relaxation therapy in Virtual Reality (VR) tries to solve these problems. However, one aspect has received little attention, that is personalised therapy. Indeed, while many studies show the need for patient-tailored relaxation exercises, little existing work focuses on personalised VR content. One reason for this is the complexity of recognising emotions, which is required for emotion-based adaptive VR. In this work, a method for adapting VR content to the emotional state of the user is presented. This model has been applied in a VR relaxation therapy application, which adapts to the user’s emotional state utilising a heuristic optimiser. Simulations have proven the performance and usability of the emotion model. Additionally, this paper explores the impact of the order in which adaptations are performed on the effectiveness of the relaxation experience.

Virtual Reality (VR) is finding its way into many domains, including healthcare. Therapists greatly benefit from having any scenario in VR at their disposal for exposure therapy. However, adapting the VR environment to the needs of the patient is time-consuming. Therefore, an intelligent decision support system that takes context information into account would be a big improvement for personalised VR therapy. In this paper, a semantic ontology is presented for modelling relevant concepts and relations in the context of anxiety therapy in VR. The necessary knowledge was collected through workshops with therapists, this resulted in a layered ontology. Furthermore, semantic reasoning through logical rules enables deduction of interesting high-level knowledge from low-level data. The presented ontology is a starting point for further research on intelligent adaptation algorithms for personalised VR exposure therapy. CCS CONCEPTS • Theory of computation → Semantics and reasoning; • Information systems → Expert systems; • General and reference → Design.

The increasing popularity of video gaming competitions, the so called eSports, has contributed to the rise of a new type of end-user: the passive game video streaming (GVS) user. This user acts as a passive spectator of the gameplay rather than actively interacting with the content. This content, which is streamed over the Internet, can suffer from disturbing network and encoding impairments. Therefore, assessing the user's perceived quality, i.e. the Quality of Experience (QoE), in real-time becomes fundamental. For the case of natural video content, several approaches already exist that tackle the client-side real-time QoE evaluation. The intrinsically different expectations of the passive GVS user, however, call for new real-time quality models for these streaming services. Therefore, this paper presents a real-time Reduced-Reference (RR) quality assessment framework based on a low-complexity psychometric curve-fitting approach. The proposed solution selects the most relevant, low-complexity objective feature. Afterwards, the relationship between this feature and the ground-truth quality is modelled based on the psychometric perception of the human visual system (HVS). This approach is validated on a publicly available dataset of streamed game videos and is benchmarked against both subjective scores and objective models. As a side contribution, a thorough accuracy analysis of existing Objective Video Quality Metrics (OVQMs) applied to passive GVS is provided. Furthermore, this analysis has led to interesting insights on the accuracy of low-complexity client-based metrics as well as to the creation of a new Full-Reference (FR) objective metric for GVS, i.e. the Game Video Streaming Quality Metric (GVSQM).

As the demand of Virtual Reality (VR) video streaming to mobile devices increases, novel optimization transport techniques need to be designed to cope with these ultra-highbandwidth video services. One approach currently attracting attention is the application of adaptive tile-based streaming solutions to the VR video arena. The VR videos are encoded at different quality levels, temporally divided into segments and spatially split into tiles. During the streaming, each of these tiles can be transmitted independently according to its location within the frame (i.e., within or outside of the user's field of view). These methods open a new venue for bandwidth and latency optimization for the streaming of VR videos. However, the effect of the different adaptive streaming optimizations on the end-user perception is still an open research topic. In this demo, we present a VR video platform to experience the working principles of adaptive tile-based VR video streaming services. Through different tiling approaches, bandwidth conditions and viewport algorithms, it allows the users to explore the effects that each optimization has on the perception of the service. In addition, the platform provides real-time bandwidth savings and objective Quality of Experience (QoE) measurements to provide a quantitative analysis of the optimizations effects. This demo aims to provide a common playground for researchers to benchmark and evaluate the performance of their optimization solutions.

Virtual Reality (VR) has the potential to change not only to the way we consume and perceive entertainment but also to improve other important areas of society. One sector that is starting to benefit from the advantages of VR is the treatment of stress related mental illnesses. VR is able to bring relaxation therapy to the next level in which solutions can be scalable (without the need for real-time dedicated professionals) and personalized. This paper presents VRelax, a personalized VR relaxation therapy approach. By means of semantic methodologies and online learning techniques, VRelax provides a personalized, relaxing virtual environment to the user.

No abstract