No abstract

In this paper we describe a method to learn parameters which govern pedestrian motion by observing video data. Our learning framework is based on variational mode learning and allows us to efficiently optimize a continuous pedestrian cost model. We show that this model can be trained on automatic tracking results, and provides realistic and accurate pedestrian motions.

The primal face of pain (PFP) is postulated to be a common and universal facial expression to pain, hardwired and present at birth. We evaluated its presence by applying a computer-based methodology consisting of "point-pair" comparisons captured from video to measure facial movement in the pain expression by way of change across two images: one image before and one image after a painful stimulus (heel-stick). Similarity of facial expression was analyzed in a sample of 57 neonates representing both sexes and 3 ethnic backgrounds (African American, Caucasian and Hispanic/Latino) while controlling for these extraneous and potentially modulating factors: feeding type (bottle, breast, or both), behavioral state (awake or asleep), and use of epidural and/or other perinatal anesthesia. The PFP is consistent with previous reports of expression of pain in neonates and is characterized by opening of the mouth, drawing in of the brows, and closing of the eyes. Although facial expression was not identical across or among groups, our analyses showed no particular clustering or unique display by sex, or ethnicity. The clinical significance of this commonality of pain display, and of the origin of its potential individual variation begs further evaluation.

Little difference was noted in eye and eyebrow movement between pain intensities. The mouth opened wider (vertically) in neonates experiencing the higher pain stimulus. Qualitative differences in neonatal facial expression to pain intensity may exist, and the mouth may be an area in which to detect them. Further study of the generalizability of these findings is needed.

Pain assessment is of high priority in the clinical setting. Facial Pain Scales (FPSs) are pain assessment tools generally used with school-aged children. The implicit theoretical bases for the success of FPSs have seldom been explored. Explanations why and how FPSs work (or do not work) have not been addressed. We support the existence of a universal pain expression--the Primal Face of Pain (PFP), which is present at birth, evolved in nature, and modulated through sociocultural factors. We propose it to be key in understanding the applicability of FPSs. We present here the design of a computer-assisted descriptive study that will observe, quantify and model the PFP as present in newborns. Measurement of the PFP will lead to exploration of the theoretical consequences of its existence, particularly as related to pediatric pain assessment and the valid use of FPSs. Further, this work can lay a foundation for the development of a new generation of FPSs.