Today, the development of enabling technologies such as video surveillance systems, miniaturised mobile 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.
Selective attention has been a classical computer vision topic such as in feature selection, salient region extraction, or biologically motivated system architectures. Recently, the fundamental need for cognitive vision methodologies has been broadly recognized (ECVision). Methods on attention and control are mandatory to render computer vision systems more robust. Concurrently, cognitive psychology has discovered attention mechanisms to play a key role in object recognition and scene interpretation, resulting in innovative computational attention architectures modelling human perception.
The workshop aims at highlighting the central role of attention on various kinds of performance in machine vision processes. It provides an interdisciplinary forum to present and communicate on computational models of visual attention, to outline relevant objectives for performance comparison, to document and to investigate promising application domains, and to discuss it with reference to other aspects of cognitive vision.
Topics of interest include, but are not limited to, the following: