In general, attention refers to the selection of information in artificial and biological systems. During the last decades, attention has often represented a core topic in the design of AI enabled systems. Today, in the upcoming debate, design, and computational modeling of artificial cognitive systems, selective attention has been reconsidered as focus of research. We find attention relevant for the selection of incoming visual information, for the decision making in top-down, i.e., symbolic to sensory information processing, for the selective functioning within the organization of behaviors, and for the understanding of individual and social cognition through the control of joint attention.
While visual cognition obviously plays a central role in human perception, findings from neuroscience and cognitive psychology have provided strong evidence about the perception-action nature of cognition. In particular, the embodiment of sensory-motor intelligence requires a spatiotemporal interplay between interpretations from various perceptual modalities and the corresponding control on motor activities. In addition, decision making about selecting information from the incoming sensory stream, in tune with contextual processing on a current task and global goals, becomes a challenging control issue within the viewpoint of focused attention. Seemingly attention systems must operate at interfaces between bottom-up driven world interpretation and top-down driven information selection, thus acting at the core of artificial cognitive systems. These insights have already gained paradigmatic changes in several AI related disciplines, such as, in the design of behavior based robotics and the computational modeling of animats.
Within the context of the engineering domain, the development of enabling technologies such as autonomous robotic systems, miniaturized mobile - even wearable - sensors, and ambient intelligence systems involves the real-time analysis of enormous quantities of data. These data have to be processed in an intelligent way to provide "in time delivery" of the required relevant information. Knowledge has to be applied about what needs to be attended to, and when, and what to do in a meaningful sequence, in correspondence with visual feedback.
The workshop aims at providing an interdisciplinary forum to present and communicate about computational models of attention, with the focus on interdependencies with visual cognition. Furthermore, it intends to investigate relevant objectives for performance comparison, to document and to investigate promising application domains, and to discuss visual attention with reference to other aspects of AI enabled systems.
Topics of interest include, but are not limited to, the following:
Techniques, modelling, and concepts:
Application related topics of interest:
Neurobiology of Attention, eds., Itti, L., Tsotsos, J.K., Rees, G.
Attention and Performance in Computational Vision, eds., Paletta, L., Tsotsos, J.K., Rome, E., Humphreys, G.W.