We introduce the first unsupervised speech synthesis system based on a simple, yet effective recipe. The framework leverages recent work in unsupervised speech recognition as well...
In this work, we present ActivityPoser, which uses the activity context as a conditional input to estimate the pose of limbs for which we do not have any direct sensor data.
This work thus presents Weighted Pointer interaction, a collection of error-aware pointing techniques that determine whether pointing should be performed by gaze, a fallback...
This paper thus proposes a computational framework that can be used to determine the optimal timing of intelligent suggestions based on user-centric costs and benefits.
Taken together, this study quantifies the degree of jitter that a user can perceive in an AR HMD and demonstrates that it is critical to consider the capabilities and limits of...
The call for this Research Topic was intentionally broad: We sought papers that identify or propose constructs that can be used to describe AR/MR/VR, and papers that evaluate the...
We present the manufacturing process to program the local material properties of the membrane to achieve custom inflation by reinforcing a fabric-elastomer composite using...
In this position paper, we argue that standardized assessment methods for mixed reality are unachievable and undesirable. In fact, we argue for a future in which there is a...
In this paper, we present AvatarPoser, the first learning-based method that predicts full-body poses in world coordinates using only motion input from the user’s head and hands.
In this paper, we report a hierarchical deep learning model for classification of complex human activities using motion sensors.
