is the largest annual computer vision event that brings together students, academics, and industry researchers in computer vision and machine learning. This year’s conference was held virtually from June 14 to June 19. Many RIT researchers attended this year, participating in several workshops and following the multi-track main conference. This included pre-recorded fireside chats with Satya Nadella of Microsoft and Charlie Bell of Amazon Web Services. Over the course of the week, there were 45 sessions with approximately 1,500 leading authors and experts, and over 6,500 registered attendees.
RIT Tokyo’s Lead Scientist, Yeongnam Chae, presented his paper, , at the , in conjunction with CVPR. His paper, written co-jointly with members of RIT Tokyo and RIT Bengaluru, introduces a multi-modal authentication approach for payments using a face image and low energy Bluetooth (BLE) signal of a user’s device. Based on extensive empirical findings, he proposes BLE signal as a second authentication factor, which is more secure than using a phone number as authentication.
Chae’s collaborative research is very timely. Consumers are looking to purchase goods with just the turn of their heads and businesses are interested in streamlining their operations but there remain concerns over privacy and data breaches. While latest models show 99% accuracy on public datasets, there is still work to be done to ensure authentication safety. Chae’s research may help usher in a new approach that improves overall accuracy and security of face-based, seamless payment systems.
RIT has been actively exploring seamless authentication for many years. This includes a recently introduced which allows users to use their face and PIN number to pay for items. Additionally, RIT set up in Tokyo’s baseball stadium last year as a way to deliver seamless experiences for fans and improve ballpark accessibility.
CVPR was originally scheduled to be held in Seattle, Washington but was modified to accommodate researchers around the world in a virtual format. We would like to thank the organizers, the IEEE Computer Society and the Computer Vision Foundation, without whom this event would otherwise not have been possible.
Narrowing the theory-practice gap in Reinforcement Learning at this year’s NeurIPS
Rakuten Mobile and Rakuten Vissel Kobe are working to change future of Sports
RIT wins one of shared tasks at WAT 2020
RIT presents paper on Automatic Post-Editing at EMNLP 2020