Description

Basic visual operations such as categorization and complex tasks such as scene interpretation have long been major challenges for computational vision. At least some of the these issues call for integration of methods into systems. Construction of systems for operation in realistic environments requires integration of methods from signal processing, geometry, statistics and reasoning. Naturally a number of both component methods and system level behaviors can be acquired from studies of biological systems.

Traditionally vision has been studied using a reductionistic approach. Given the complexity of cognitive tasks, however, it is not obvious that such an approach is the most efficient way to address the core problems. Some issues such as multi-cue figure ground segmentation, embodied categorization, and behavior / skill acquisition can only be studied in the context of systems. Recent progress in studies of categorization, statistical learning theory, active perception, software engineering and computational neuroscience is paving the way for improved understanding of cognitive functionalities in biological and artificial systems. This workshop will focus on discussion of components methods such as:

• Memory: The coupling between visual perception, tasks, knowledge and the visual system requires memory. Issues that are of special importance for integrating memory into vision systems include: how to manage representations in presence of limited resources (such as mechanism for generation of abstractions and forgetting); model for attention; integration of information across representations and time.
• Learning and Adaptation: A system whose goal is that of interacting with the real world must be capable of learning from experience and adapt to unexpected changes. Also, there is a need for integration of multiple visual features to enable generation of stable hypotheses, and for methods for combination of cues in the presence of uncertainty.
• Categorization: Research has in particular focused on recall of specific object instances, events and actions. Whereas recently some progress has been achieved on systems that allow limited recognition of object classes, events and scenes across visual appearance, new methods are needed to enable abstractions and effective categorization across variations in color, surface markings, geometry, temporal scenes, context and tasks.
• Integration Vision is often considered in isolation. When considered in the context of an embodied system the concept of an ''active visual observer'' becomes important. The visual system operates here as a task oriented perception module that generates a diverse set of visual descriptions about the environment. The set of descriptors is by no means organized in a hierarchy. Depending on the task at hand the system might generate features to the ''agent'' in terms of events, labels, and/or spatio-temporal models (geometry, trajectories, relations, etc). thus, integration plays an important role from processing of visual cues and multi-modal sensor fusion to systems architecture.

The goal of the workshop is to present and discuss new methods and techniques that enables construction of cognitive vision systems that can perform task oriented categorization and recognition of objects and events. The focus will be on assesment of state of the art and identification of key challenges.

Program

• B. Caputo Categorization using a discriminative approach presentation paper
• A. Zissermann Categorization using a generative approach presentation paper
• M. Ross, L. P. Kaelbling A systematic approach to learning object segmentation presentation paper
• J. Hoey, J. Little Decision theoretic learning of human facial display presentation paper
• A. Graf Image\--based recognition: trading memory for computation presentation paper
• P. Anandan Representation and reasoning in vision presentation paper
• D. Philipona Towards a notion of sensorimotor objects presentation paper
• M. Black Inferring people from images presentation
• V. Vaingankar, V. S. Chaoji, R. S. Gaborski, A. M. Teredesai Cognitively motivated habituation for novelty detection in video presentation paper
• V. Bulitko, G. Lee, I. Levner, L. Li Open challenges in learning vision systems presentation paper
• H. Christensen The CogVis project: why we do use vision (also) presentation paper
• J. Malik improptu talk presentation paper
• Y. Le Cun improptu talk presentation paper

Lucia Award committee winners