Google, Adobe Share Their Video Accessibility Strategies

The ability for Virtual Reality (VR) to create rich and compelling experiences drives research in a variety of domains beyond entertainment. One such area of interest is the use of VR for learning and training purposes. Indeed, learning and training have been a central topic in VR ever since successful flight simulators decades ago. The allure of VR for training is not only due to the ability to synthesize realistic conditions for situations where on-site training is expensive, dangerous, or difficult to replicate in real life, but also due to the ability to create extreme, unrealistic conditions to over-prepare trainees for the real situation. Full control over the visual and auditory experience of the user, as well as some control over haptic feedback, makes for an engaging training experience and ensures the reproducibility of training sessions. Combined with recent advances in light and untethered headsets, tracking, interaction, and VR authoring tools, various industrial immersive learning applications show promising results. The explosive potential of VR-based collaboration in the post-pandemic era, where remote and non-contact work environments became the new normal, further accelerated the adoption of VR-based training in broader use cases.

As 5G networks find their way into real deployments, there are number of opportunities in the industries to leverage the 5G capabilities. The software-based architecture (SBA), edge computing capabilities and network programmability will enable innovation in products & services and provide opportunities to reimagine experiences which 5G-enabled applications will offer. In this webinar, we will discuss how 5G architecture with edge computing will enable real-time processing of information to enable context-based hyper-personalization and thus transforming the industry applications.

In this webinar, visual effects and digital production company Digital Domain will share their experience developing AI-based toolsets for applying deep learning to their content creation pipeline. AI is no longer just a research project but also a valuable technology that can accelerate labor-intensive tasks, giving time and control back to artists. We’ll start with a brief overview of deep learning and dive into examples of convolutional neural networks (CNNs), generative adversarial networks (GANS), and autoencoders. These examples will include flavors of neural networks useful for everything from face swapping and image denoising to character locomotion, facial animation, and texture creation.

Lack of captions, transcripts, and audio descriptions inhibit a large portion of the population from enjoying and interacting with your video content. Often, accessible content is put on the back burner for different reasons, such as limited budgets or lack of awareness of the legal requirements.