CVPR Daily - Wednesday

In the computer vision researcher panel, experts highlighted some of the key technical challenges, including how to deal with the growing size of models on resource-constrained devices like mobile phones, and how to ensure that these models are always safe to use, for example by abstaining from answering a question rather than answering incorrectly. The panel of access tech advocates discussed scenarios in which they prefer systems that employ AI versus remote sighted assistants and their hopes for future computer vision technologies. The experts in the industry professionals panel also provided their perspective on solutions that solely rely on humans versus AI, and discussed the challenges of deploying accessibility products and services in practice. They also offered valuable advice to students and individuals who are interested in joining accessibility teams in industries. From the three interdisciplinary panels, we heard an overall excitement about the past decade of progress in accessibility. This included improved development frameworks to build accessible products as well as better products themselves from companies such as Apple, Microsoft, and Be My Eyes. Panelists also described what they envisioned for the future of technology with a nearly unanimous agreement that we will have wearable technology companions with information personalized to the interest of each user. We also heard about the challenges in developing such future technologies, including designing datasets that are representative of people with disabilities. Through the Challenges and insights from the panel discussions, the workshop focused on highlighting some of the key progress that has been made in the field of computer vision in technologies for people who are blind and low-vision. We hope to inspire the research community to look ahead and imagine what the next decade of tech might look like, and to take on solving the challenges which lie along the path to realizing it. 26 DAILY CVPR Workshop Wednesday

RkJQdWJsaXNoZXIy NTc3NzU=