Parental mediation, YouTube’s networked public, and the baby-iPad encounter: mobilizing digital dexterity.

This study collected a sample of YouTube videos in which parents recorded their young children utilizing mobile touchscreen devices. Focusing on the more frequently viewed and highly-discussed videos, the paper analyzes the ways in which babies’ ‘digital dexterity’ is coded and understood in terms of contested notions of ‘naturalness’, and how the display of these capabilities is produced for a networked public. This reading of the ‘baby-iPad encounter’ helps expand existing scholarly concepts such as parental mediation and technology domestication. Recruiting several theoretical frameworks, the paper seeks to go beyond concerns of mobile devices and immobile children by analyzing children’s digital dexterity not just as a kind of mobility, but also as a set of reciprocal mobilizations that work across domestic, virtual and publically networked spaces.

Efficient and precise interactive hand tracking through joint, continuous optimization of pose and correspondences

Fully articulated hand tracking promises to enable fundamentally new interactions with virtual and augmented worlds, but the limited accuracy and efficiency of current systems has prevented widespread adoption. Today's dominant paradigm uses machine learning for initialization and recovery followed by iterative model-fitting optimization to achieve a detailed pose fit. We follow this paradigm, but make several changes to the model-fitting, namely using: (1) a more discriminative objective function; (2) a smooth-surface model that provides gradients for non-linear optimization; and (3) joint optimization over both the model pose and the correspondences between observed data points and the model surface. While each of these changes may actually increase the cost per fitting iteration, we find a compensating decrease in the number of iterations. Further, the wide basin of convergence means that fewer starting points are needed for successful model fitting. Our system runs in real-time on CPU only, which frees up the commonly over-burdened GPU for experience designers. The hand tracker is efficient enough to run on low-power devices such as tablets. We can track up to several meters from the camera to provide a large working volume for interaction, even using the noisy data from current-generation depth cameras. Quantitative assessments on standard datasets show that the new approach exceeds the state of the art in accuracy. Qualitative results take the form of live recordings of a range of interactive experiences enabled by this new approach.