No abstract

To evaluate the extent to which infants and mothers are able to coordinate their behavior, the interactions of 54 mother-infant pairs--18 each at 3, 6, and 9 months of age--were videotaped. Coordination was evaluated with 2 measures: (1) matching--the extent to which mother and infant engage in the same behavior at the same time; and (2) synchrony--the extent to which mother and infant change their behavior with respect to one another. Mother-infant pairs increase their degree of coordination with infant age, but the proportion of time they are coordinated is small. Mother-son pairs spend more time in coordinated states than mother-daughter pairs. The results suggest that interactions be characterized in terms of their movement from coordinated to miscoordinated states rather than only in terms of their degree of coordination. The gender differences are discussed in terms of their importance for the developmental differences in females and males.

Automatic facial action unit (AFA) detection from video is a long-standing problem in facial expression analysis. Most approaches emphasize choices of features and classifiers. They neglect individual differences in target persons. People vary markedly in facial morphology (e.g., heavy versus delicate brows, smooth versus deeply etched wrinkles) and behavior. Individual differences can dramatically influence how well generic classifiers generalize to previously unseen persons. While a possible solution would be to train person-specific classifiers, that often is neither feasible nor theoretically compelling. The alternative that we propose is to personalize a generic classifier in an unsupervised manner (no additional labels for the test subjects are required). We introduce a transductive learning method, which we refer to Selective Transfer Machine (STM), to personalize a generic classifier by attenuating person-specific biases. STM achieves this effect by simultaneously learning a classifier and re-weighting the training samples that are most relevant to the test subject. To evaluate the effectiveness of STM, we compared STM to generic classifiers and to cross-domain learning methods in three major databases: CK+ [20], GEMEP-FERA [32] and RU-FACS [2]. STM outperformed generic classifiers in all.

No abstract