Search

Neural rendering is an exciting topic injecting machine learning methodologies into the classical computer graphics rendering pipeline. Although recent works have achieved remarkable fidelity, discussion on how to enable it for interactive scenarios like video games seems to be lacking. Aside from an editable 3D model and UV-mapping, an interactive application will demand the neural rendering to handle animatable 3D content with interactive speed. This is currently a gap in neural rendering and our solution to this problem is a novel neural rendering pipeline involving a primitive named NeRFahedron. It localizes a NeRF field and as such effectively reduces the number of expensive network sampling operations to improve speed. Our pipeline involves tetrahedron rasterization, localized ray marching and near-surface particle sampling. The result is a method that can enable animatable content for neural rendering with interactive speed, which has been shown to be competitive in rendering animation. We will also showcase its ability to enable interactive applications via a real-time demo.

Have you ever picked up a stuffed toy and pretended to play with it in your childhood? We are motivated by the novel use of stuffed toys in enhancing extended reality interaction. A key goal of extended reality is to induce the feeling of presence in its users. Naturally mapped control interface has been shown to enhance presence. The literature also indicates that a high degree of freedom tracking is important to extended reality. Based on these observations, we show that a free-form naturally mapped control interface is well-motivated via a theoretical contextualization. We explore the possibility of building such a controller in the form of stuffed toys. To realize stuffed toys as controllers, a novel soft-pose estimator empowered by cage-based deformation is proposed. It is shown to be effective in tracking the poses and deformations of real soft objects even by training with synthetic data only. Three gameplay prototypes are developed to demonstrate that interactive play can be enabled by the soft-pose estimator. They also form the basis for two user studies that validate the success of tracking stuffed toys with the soft-pose estimator for interactive play.

As occupational rehabilitation services are part of the public medical and health services in Hong Kong, work-injured workers are treated along with other patients and are not considered a high priority for occupational rehabilitation services. The idea of a work trial arrangement in the private market occurred to meet the need for a more coordinated occupational rehabilitation practice. However, there is no clear service standard in private occupational rehabilitation services nor concrete suggestions on how to offer rehabilitation plans to injured workers. Electronic Health Records (EHRs) data can provide a foundation for developing a model to improve this situation. This project aims at using a machine-learning-based approach to enhance the traditional prediction of disability duration and rehabilitation plans for work-related injury and illness. To help patients and therapists to understand the machine learning result, we also developed an interactive dashboard to visualize machine learning results. The outcome is promising. Using the variational autoencoder, our system performed better in predicting disability duration. We have around 30% improvement compared with the human prediction error. We also proposed further development to construct a better system to manage the work injury case.

This paper aims to illustrate an example of how to set up a work injury database: the Smart Work Injury Management (SWIM) system. It is a secure and centralized cloud platform containing a set of management tools for data storage, data analytics, and machine learning. It employs artificial intelligence to perform in-depth analysis via text-mining techniques in order to extract both dynamic and static data from work injury case files. When it is fully developed, this system can provide a more accurate prediction model for cost of work injuries. It can also predict return-to-work (RTW) trajectory and provide advice on medical care and RTW interventions to all RTW stakeholders. The project will comprise three stages. Stage one: to identify human factors in terms of both facilitators and barriers RTW through face-to-face interviews and focus group discussions with different RTW stakeholders in order to collect opinions related to facilitators, barriers, and essential interventions for RTW of injured workers; Stage two: to develop a machine learning model which employs artificial intelligence to perform in-depth analysis. The technologies used will include: 1. Text-mining techniques including English and Chinese work segmentation as well as N-Gram to extract both dynamic and static data from free-style text as well as sociodemographic information from work injury case files; 2. Principle component/independent component analysis to identify features of significant relationships with RTW outcomes or combine raw features into new features; 3. A machine learning model that combines Variational Autoencoder, Long and Short Term Memory, and Neural Turning Machines. Stage two will also include the development of an interactive dashboard and website to query the trained machine learning model. Stage three: to field test the SWIM system. SWIM ia secure and centralized cloud platform containing a set of management tools for data storage, data analytics, and machine learning. When it is fully developed, SWIM can provide a more accurate prediction model for the cost of work injuries and advice on medical care and RTW interventions to all RTW stakeholders. The project has been approved by the Ethics Committee for Human Subjects at the Hong Kong Polytechnic University and is funded by the Innovation and Technology Commission (Grant # ITS/249/18FX).

Candida albicans is an important opportunistic fungal pathogen capable of causing fatal systemic infections in humans. Presently in Malaysia, there is little information available on the genetic diversity of this organism and trends in behavioural characteristics. In this project, three genotyping methods: 25S rDNA genotyping, Alternative Lengthening of Telomerase (ALT) sequence typing and Multi-Locus Sequence Typing (MLST) were applied to study the genetic diversity of strains from infected hospital in-patients and asymptomatic individuals in the community. The results showed that, with the 25S rDNA genotyping, as in other parts of the world, the most common genotype was type A which accounted for approximately 70% of the 111 isolates tested. Further typing with the ALT sequence showed type 3 to be the most common in the isolates tested. MLST analysis revealed many possibly novel sequence types, as well as a statistically significant association between pathogenicity and a group of closely related isolates, most of which were from hospital samples. Further work on genotypes associated with enhanced virulence will help to clarify the value of genotyping for clinical and epidemiological investigations.

IntroductionThe eHealth technologies that are being designed for chronic disease constitute a global trend towards health assessment and self-management. However, most of these approaches tend to focus on a single symptom or problem rather than on the multiple problems that are characteristic of many of these chronic illnesses. The aim of this study is to examine the effectiveness of and adherence to a self-management application (app) that identifies multiple problem areas related to surviving breast cancer as the targeted chronic illness.Methods and analysisThis is a randomised controlled study. Eligible participants will be allocated randomly into either an intervention group or a control group at a 1:1 ratio. The intervention group will be assigned to the self-management app (‘Be-with-You’), while the control group will use a general health app (‘Sham’ app). The primary outcomes will include the differences between the two groups in their health literacy, problem-solving skills and self-management skills. The secondary outcomes will include group differences in self-efficacy, readiness for change and health-related quality of life. All of these outcomes will be measured at baseline and at 4 weeks and 12 weeks after intervention. In addition, usability of these two mobile apps will be measured at 4 weeks and 12 weeks after intervention. The planned sample size is 476.Ethics and disseminationThe Human Subjects Ethics Sub-committee of The Hong Kong Polytechnic University approved the study (HSEARS20190922001, 24 September 2019). Dissemination of findings will occur at the local, national and international levels.Trial registration numberChiCTR1900026244.

Dyslexia cause neurological limitations upon its patients such that they have poor phonological awareness and orthographical skills. This in turn limit the patients’ abilities to derive meaning from words which are keys to effective reading. To aid dyslexics in their comprehensions, a top-down approach to reading is proposed. In the meanwhile, a graphical model is also proposed as a tool to help researchers pinpoint neurological processes. It cleanly shows that the top-down approach could bypass dyslexic patients’ neurological limitations. It is also hypothesized that by aiding their understanding of articles and words, it is also possible for patients to improve their phonological awareness and orthographical skills. Our implementation to the research goals is VR reading, which uses multimedia feedback to give cues to dyslexic students on the meaning of words and articles. VR reading consists of aiding images, voice-overs, videos and a background theme dome that gives encapsulated cues on the meanings of the article and its words that are detached from the article itself. This is an important design decision as we want dyslexic students to rely more on multimedia feedback in deriving the meaning. We also show a preliminary evaluation which is a step towards testifying the aforementioned hypotheses with VR reading. It involves primary school children to read a Chinese article and be evaluated afterwards. The result seems to indicate that VR reading is useful in aiding students in their reading comprehension and additionally, has potential to improve their phonological awareness and orthographical skills.

IntroductionBreast cancer is the leading cause of global cancer incidence and represents 11.7% of all new cancer cases. However, breast cancer survivors (BCS) suffer from many intense physical and psychological symptoms, functional deficits and adverse effects during and after treatment, significantly affecting their quality of life. Virtual reality (VR) technology uses computer technology to create an interactive three-dimensional world by visual, audio and touch simulation and is being used in breast cancer rehabilitation management. This paper reports on the protocol for a systematic review and meta-analysis exploring the efficacy of VR-based interventions in the rehabilitation management of BCS.Methods and analysisThis protocol for conducting a systematic review and meta-analysis was prepared according to the recommendations of the Preferred Reporting Items for Systematic Review and Meta-Analysis Protocols 2015 statement. Web of Science, PubMed, Embase, CINAHL, Cochrane Central Register of Controlled Trials, CNKI, Wanfang, VIP and SinoMed will be used in the search. The search will include randomised controlled trials, quasi-experimental studies and case-controlled trials published in English and Chinese. Further, the risk of bias of the studies included in the systematic review and meta-analysis will be assessed using the Cochrane risk-of-bias tool. The statistical program Review Manager V.5.3 will be used in the meta-analysis. The I² test will be used to determine statistical heterogeneity among the included studies.Ethics and disseminationEthics approval will not be needed because the data to be used in this systematic review and meta-analysis will be extracted from published studies. The systematic review and meta-analysis will focus on whether VR-based interventions are effective in the rehabilitation management of BCS. It will be disseminated by publication in a peer-reviewed journal.PROSPERO registration numberCRD42021250727.

Animating a character given an image is an interesting research problem that posed to have applicational values. Namely, it could help animators to automatically animate new characters with motions similar to previous characters. The problem also has value in digital entertainment for animating characters created by players such as drawn characters. There are a few deep learning video synthesis models that could generate a video given an image. However, it is unlikely there exists a dataset that could train them for animating characters since characters for digital entertainment tend to be more novel and diverse. Nor is it practical for animators to create a large dataset for training. To this end, a 2D-CharAnimNet is proposed. Empowered by a novel motion transfer scheme for video generation, the proposed variational-autoencoder-based model could use a relatively small dataset. In addition, to improve the fidelity of video frames, dynamic skip-connections along with a polishing generative adversarial networks are also proposed. Results seem to indicate that the model has encouraging potential in adapting for applicational uses.

Observing that a motion signal is decomposable into multiple levels, a video generation model which realizes this hypothesis is proposed. The model decomposes motion into a two-level signal involving a global path and local pattern. They are modeled via a latent path in the form of a composite Bezier spline along with a latent sine function respectively. In the application context, the model fills the research gap in its ability to connect an arbitrary number of input key frames smoothly. Experimental results indicate that the model improves in terms of the smoothness of the generated video. In addition, the ability of the model in separating global and local signal has been validated.