Abstract
Virtual Reality (VR) telepresence platforms are being challenged to support live performances, sporting events, and conferences with thousands of users across seamless virtual worlds. Current systems have struggled to meet these demands which has led to high-profile performance events with groups of users isolated in parallel sessions. The core difference in scaling VR environments compared to classic 2D video content delivery comes from the dynamic peer-to-peer spatial dependence on communication. Users have many pair-wise interactions that grow and shrink as they explore spaces. In this paper, we discuss the challenges of VR scaling and present an architecture that supports hundreds of users with spatial audio and video in a single virtual environment. We leverage the property of spatial locality with two key optimizations: (1) a Quality of Service (QoS) scheme to prioritize audio and video traffic based on users' locality, and (2) a resource manager that allocates client connections across multiple servers based on user proximity within the virtual world. Through real-world deployments and extensive evaluations under real and simulated environments, we demonstrate the scalability of our platform while showing improved QoS compared with existing approaches.

Abstract
Deep learning has recently gained popularity in the field of video anomaly detection, with the development of various methods for identifying abnormal events in visual data. The growing need for automated systems to monitor video streams for anomalies, such as security breaches and violent behaviours in public areas, requires the development of robust and reliable methods. As a result, there is a need to provide tools to objectively evaluate and compare the real-world performance of different deep learning methods to identify the most effective approach for video anomaly detection. Current state-of-the-art metrics favour weakly-supervised strategies stating these as the best-performing approaches for the task. However, the area under the ROC curve, used to justify this statement, has been shown to be an unreliable metric for highly unbalanced data distributions, as is the case with anomaly detection datasets. This paper provides a new perspective and insights on the performance of video anomaly detection methods. It reports the results of a benchmark study with state-of-the-art methods using a novel proposed framework for evaluating and comparing the different models. The results of this benchmark demonstrate that using the currently employed set of reference metrics led to the misconception that weakly-supervised methods consistently outperform semi-supervised ones. © 2023 The Authors

Abstract
Visual representations have the potential to improve information understanding. We explore this idea in the development of NewsLine, an open-source web-based prototype that focuses on narrative visualizations of news content. Having structured data as input, the prototype produces a storyline which showcases the narrative's events and participants, allowing the user to interact with the visualization in a number of ways. We built an information hub around the storyline to allow for multiple levels of exploration, specifically the main visualization, the event information module, and the sidebar. The visualization depicts the sequence of events that make up a news story, as well as the interactions between the involved parties in each event. The event information module presents additional information on a particular event. The sidebar is the “control center” of the visualization, unlocking a number of interactions and configurations. The prototype was evaluated with a user study with journalists and also with an online survey which gathered feedback from 178 potential end users. From these, 106 participants (60.6%) provided a rating of four or above (one to five scale) when asked to quantify their interest in using the application. Moreover, participants were asked to rank the importance of the visualization elements used. The results highlight that two elements stand out as the most important, the events and the entities. Overall, the participants generally found the application to be useful, but in need of some work in order for it to be made available to a broader public. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

Abstract
Deep learning-based models are widely used for disease classification in chest radiographs. This exam can be performed in one of two projections (posteroanterior or anteroposterior), depending on the direction that the X-ray beam travels through the body. Since projection visibly affects the way anatomical structures appear in the scans, it may introduce bias in classifiers, especially when spurious correlations between a given disease and a projection occur. This paper examines the influence of chest radiograph projection on the performance of deep learning-based classification models and proposes an approach to mitigate projection-induced bias. Results show that a DenseNet-121 model is better at classifying images from the most representative projection in the data set, suggesting that projection is taken into account by the classifier. Moreover, this model can classify chest X-ray projection better than any of the fourteen radiological findings considered, without being explicitly trained for that task, putting it at high risk for projection bias. We propose a label-conditional gradient reversal framework to make the model insensitive to projection, by forcing the extracted features to be simultaneously good for disease classification and bad for projection classification, resulting in a framework with reduced projection-induced bias.

Abstract
Deep Learning models are tremendously valuable in several prediction tasks, and their use in the medical field is spreading abruptly, especially in computer vision tasks, evaluating the content in X-rays, CTs or MRIs. These methods can save a significant amount of time for doctors in patient diagnostics and help in treatment planning. However, these models are significantly sensitive to confounders in the training data and generally suffer a performance hit when dealing with out-of-distribution data, affecting their reliability and scalability in different medical institutions. Deep Learning research on Medical datasets may overlook essential details regarding the image acquisition procedure and the preprocessing steps. This work proposes a data-centric approach, exploring the potential of attention maps as a regularisation technique to improve robustness and generalisation. We use image metadata and explore self-attention maps and contrastive learning to promote feature space invariance to image disturbance. Experiments were conducted using Chest X-ray datasets that are publicly available. Some datasets contained information about the windowing settings applied by the radiologist, acting as a source of variability. The proposed model was tested and outperformed the baseline in out-of-distribution data, serving as a proof of concept. © 2023 IEEE.

Abstract
[No abstract available]