Alcoholism and family interaction

In i6 families, half of which had an alcoholic parent, both parents and an adolescent were videotaped interacting with each other. Mothers, fathers and the adolescent in each family viewed the videotaped interaction and completed ratings of themselves and the other two family members on levels of anxiety, involvement, dominance and friendliness. In families with an alcoholic parent, adolescents and their mothers rated family members as less anxious than did adolescents and mothers in families without a drinking problem. Also mothers in the alcoholic families rated family members as being more involved, and their ratings were higher than mothers in other families. Alcoholic families rated parent-adolescent interactions as more dominant and friendlier. At least in these videotaped interactions where alcohol was not being consumed, mothers in alcoholic families adopted a more positive view of family members than mothers in other families. In addition, possibly due to the efforts of fathers not to drink and memories of interactions when he was drunk, alcoholic families perceived their family interactions as more dominant and friendlier than families without an alcohol-related problem. [Schweitzer R, Wilks j, Callan vJ. Alcoholism and family interaction.

Visual front-end wars : Viola-Jones face detector vs Fourier Lucas-Kanade

The performance of visual speech recognition (VSR) systems are significantly influenced by the accuracy of the visual front-end. The current state-of-the-art VSR systems use off-the-shelf face detectors such as Viola- Jones (VJ) which has limited reliability for changes in illumination and head poses. For a VSR system to perform well under these conditions, an accurate visual front end is required. This is an important problem to be solved in many practical implementations of audio visual speech recognition systems, for example in automotive environments for an efficient human-vehicle computer interface. In this paper, we re-examine the current state-of-the-art VSR by comparing off-the-shelf face detectors with the recently developed Fourier Lucas-Kanade (FLK) image alignment technique. A variety of image alignment and visual speech recognition experiments are performed on a clean dataset as well as with a challenging automotive audio-visual speech dataset. Our results indicate that the FLK image alignment technique can significantly outperform off-the shelf face detectors, but requires frequent fine-tuning.