Active vision systems, and especially foveated vision systems, depend on efficient attentional mechanisms. We propose that machine visual attention should consist of both high level, context dependent components, and low level, context free components. As a basis for the context free component, we present an attention operator based on the intuitive notion of symmetry, which generalizes many of the existing methods for detecting regions of interest. It is a low level operator that can be applied successfully without a priori knowledge of the world. The resulting symmetry edge map can be applied in various low, intermediate and high level tasks, such as extraction of interest points, grouping and object recognition. In particular, we have implemented an algorithm which locates interest points in real time, and can be incorporated in active and purposive vision systems. The results agree with some psychophysical findings concerning symmetry as well as evidence concerning selection of fixation points...

Four studies investigated whether and when infants connect information about an actor's affect and perception to their action. Arguably, this may be a crucial way in which infants come to recognize the intentional behaviors of others. In Study 1 an actor grasped one of two objects in a situation where cues from the actor's gaze and expression could serve to determine which object would be grasped, specifically the actor first looked at and emoted positively about one object but not the other. Twelve-month-olds, but not 8-month-olds, recognized that the actor was likely to grasp the object which she had visually regarded with positive affect. Studies 2, 3, and 4 replicated the main finding from Study 1 with 12- and 14-month-olds and included several contrasting conditions and controls. These studies provide evidence that the ability to use information about an adult's direction of gaze and emotional expression to predict action is both present, and developing at the end of the first year of life. q 2002 Elsevier Science B.V. All rights reserved.

Abstract. This paper presents a novel approach for extracting characteristic parts of a face. Rather than finding a priori specified features such as nose, eyes, mouth or others, the proposed approach is aimed at extracting from a face the most distinguishing or dissimilar parts with respect to another given face, i.e. at “finding differences ” between faces. This is accomplished by feeding a binary classifier by a set of image patches, randomly sampled from the two face images, and scoring the patches (or features) by their mutual distances. In order to deal with the multi-scale nature of natural facial features, a local space-variant sampling has been adopted. 1

Introduction Biological vision is foveated, highly goal oriented and task dependent. This observation, which is rather clear if we trace the behavior of practically every vertebrate, is now being taken seriously into consideration by the computer vision community. This is evident from recent work on active vision systems and heads (Clark and Ferrier, 1988; Brunnstrome et al., 1992; Crowley, 1991; Rimey and Brown, 1992) and general active vision concepts and algorithms (Aloimonos et al., 1987; Bajcsy, 1988; Aboot and Ahuja, 1988; Ballard, 1990; Culhane and Tsotsos, 1992). One of the fundamental features of active vision is the use of space-variant vision and sensors (Yeshurun and Schwartz, 1989; Tistarelli and Sandini, 1990; Rojer and Schwartz, 1990), that allow, in the case of the log-polar representation data reduction as well as a certain degree of size and rotation invariance. The use of such sensors require efficient mechanisms for gaze control, that are, in turn, directed

This paper develops and demonstrates an original approach to face-image analysis based on identifying distinctive areas of each individual’s face by its comparison to others in the population. The method differs from most others—that we refer as unary — where salient regions are defined by analyzing only images of the same individual. We extract a set of multi-scale patches from each face image before projecting them into a common feature space. The degree of “distinctiveness” of any patch depends on its distance in feature space from patches mapped from other individuals. First a pair-wise analysis is developed and then a simple generalization to the multiple-face case is proposed. A perceptual experiment, involving 45 observers, indicates the method to be fairly compatible with how humans mark faces as distinct. A quantitative example of face authentication is also performed in order to show the essential role played by the distinctive information. A comparative analysis shows that performance of our n-ary approach is as good as several contemporary unary, or binary, methods- whilst tapping a complementary source of information. Furthermore we show it can also provide a useful degree of illumination invariance.

Since Autism was first outlined (Kanner, 1943), an agreed-upon definition of Autism has been reached and standardized diagnostic methods produced. To date, however, no clear etiology has been established, and proposed treatments vary widely. Research has uncovered enough about Autism’s underlying neuroand cognitive psychology to allow us to outline treatment implications to benefit those families seeking help now who are unwilling to wait for the elusive ultimate answer. The Autism Treatment Center of America ™ has been using The Son-Rise Program ® (SRP) with families since 1983 in order to fulfill this need. The SRP was developed by parents experimenting with ways to reach their severely autistic child (Kaufman, 1976). Science at this time offered no guidance on facilitating the social development of children with Autism. Since their son emerged from Autism after 3 _ years of intensive work, the Kaufmans have offered SRP to families internationally. To date, no rigorous longitudinal testing of the efficacy of SRP has been performed yet it can be seen that the key principles of this approach draw

This article reviews the advantages and limitations of current methods for the refinement and quantification of this highly heterogeneous social phenotype

This paper offers an approach to social cognitive development intended to address the above discrepancy, which is considered a key element for any understanding of the pathophysiology of autism

This article is dedicated to the memory of our mentor, collaborator, and colleague, Donald Cohen, MD, whose legacy embodies the best in clinical services, public advocacy, clinical science, bioethics, and mentoring

Abstract. Face recognition is among the most challenging techniques for personal identity verification. Even though it is so natural for humans, there are still many hidden mechanisms which are still to be discovered. According to the most recent neurophysiological studies, the use of dynamic information is extremely important for humans in visual perception of biological forms and motion. Moreover, motion processing is also involved in the selection of the most informative areas of the face and consequently directing the attention. This paper provides an overview and some new insights on the use of dynamic visual information for face recognition, both for exploiting the temporal information and to define the most relevant areas to be analyzed on the face. In this context, both physical and behavioral features emerge in the face representation. 1