3D Reasoning from Blocks to Stability.

Objects occupy physical space and obey physical laws. To truly understand a scene, we must reason about the space that objects in it occupy, and how each objects is supported stably by each other. In other words, we seek to understand which objects would, if moved, cause other objects to fall. This 3D volumetric reasoning is important for many scene understanding tasks, ranging from segmentation of objects to perception of a rich 3D, physically well-founded, interpretations of the scene. In this paper, we propose a new algorithm to parse a single RGB-D image with 3D block units while jointly reasoning about the segments, volumes, supporting relationships, and object stability. Our algorithm is based on the intuition that a good 3D representation of the scene is one that fits the depth data well, and is a stable, self-supporting arrangement of objects (i.e., one that does not topple). We design an energy function for representing the quality of the block representation based on these properties. Our algorithm fits 3D blocks to the depth values corresponding to image segments, and iteratively optimizes the energy function. Our proposed algorithm is the first to consider stability of objects in complex arrangements for reasoning about the underlying structure of the scene. Experimental results show that our stability-reasoning framework improves RGB-D segmentation and scene volumetric representation.

The Hidden Sides of Names--Face Modeling with First Name Attributes.

This paper introduces the new idea of describing people using first names. We show that describing people in terms of similarity to a vector of possible first names is a powerful representation of facial appearance that can be used for a number of important applications, such as naming never-seen faces and building facial attribute classifiers. We build models for 100 common first names used in the US and for each pair, construct a pairwise first-name classifier. These classifiers are built using training images downloaded from the internet, with no additional user interaction. This gives our approach important advantages in building practical systems that do not require additional human intervention for data labeling. The classification scores from each pairwise name classifier can be used as a set of facial attributes to describe facial appearance. We show several surprising results. Our name attributes predict the correct first names of test faces at rates far greater than chance. The name attributes are applied to gender recognition and to age classification, outperforming state-of-the-art methods with all training images automatically gathered from the internet. We also demonstrate the powerful use of our name attributes for associating faces in images with names from caption, and the important application of unconstrained face verification.

Stain reduction of an integrated oral hygiene system.

This article discusses research to determine the efficacy of a prototype integrated power toothbrush and toothpaste dispensing system, the IntelliClean System from Sonicare and Crest, in the removal of extrinsic stain. The prototype integrated system and a positive control, the Sonicare Elite with conventional toothpaste, were evaluated in 2 randomized, single-blinded, parallel 4-week controlled clinical trials. There was a low dropout rate, with 28 subjects of the 31 randomized in study 1 completing the study (10% loss to follow-up) and 26 subjects of the 28 randomized in study 2 completing the study (7% loss to follow-up). Lobene stain scores were used to assess the extent and intensity of stain for all teeth meeting the criteria for inclusion in the studies. Lobene stain scores were assessed at baseline and after 4 weeks in both studies. A survey also was conducted at the conclusion of each study to determine user attitude toward the integrated system. The prototype integrated system was found to significantly reduce overall extrinsic stain over time, performing not significantly differently from the positive control. Overall, the prototype integrated system reduced the composite measure of stain that encompasses both the extent and intensity of stain by 60%. This research demonstrates that the IntelliClean System from Sonicare and Crest is highly effective in reducing extrinsic stain.

Fracture prevalence in Duchenne muscular dystrophy.

The objective of this study was to determine the prevalence, circumstances, and outcome of fractures in males with Duchenne muscular dystrophy (DMD) attending neuromuscular clinics. Three hundred and seventy-eight males (median age 12 years, range 1 to 25 years) attending four neuromuscular centres were studied by case-note review supplemented by GP letter or by interview at the time of clinic attendance. Seventy-nine (20.9%) of these patients had experienced fractures. Forty-one percent of fractures were in patients aged 8 to 11 years and 48% in independently ambulant patients. Falling was the most common mechanism of fracture. Upper-limb fractures were most common in males using knee-ankle-foot orthoses (65%) while lower-limb fractures predominated in independently mobile and wheelchair dependent males (54% and 68% respectively). Twenty percent of ambulant males and 27% of those using orthoses lost mobility permanently as a result of the fracture. In a substantial proportion of males, the occurrence of a fracture had a significant impact on subsequent mobility.