Program

Session I: Attention and Embodiment

• (8:30-9:00) Johann Prankl, Michael Zillich, Markus Vincze Motion guided learning of objects on the fly pdf
• (9:00-9:30) Albert Rothenstein, John Tsotsos Time - the resource attention allocates
• (9:30-10:00) Yiannis Aloimonos Segmentation and attention: the "view" from inside the image

Coffee Break (10:00-10:30)

Session II: Categorization and Embodiment

• (10:30-11:00) Changhai Xu, Benjamin Kuipers Construction of the object hierarchy pdf
• (11:00-11:30) Sarah Aboutalib Towards Robust Multi-Cue Object Recognition of "Interactionable" Objects"
• (11:30-12:00) Changhyun Choi Cognitive Vision for Efficient Scene Processing and Object Categorization in Highly Cluttered Environments

Lunch Break (12:00-14:30)

Session III: Embodied Systems

• (14:30-15:00) Mohan Sridharan, Jeremy Wyatt, Richard Dearden POMPD-based planning for visual processing management on a mobile robot pdf
• (15:00-15:30) Giorgio Metta, Andrew Dankers, Giulio Sandini Attention and segmentation in a humanoid robot

Coffee Break (15:30-16:00)

Session IV: Categorization and Learning

• (16:00-16:30) Barbara Caputo From knowledge transfer to one-shot learning of visual categories
• (16:30-17:00) Christian Faubel A neurodynamic architecture for one shot learning of objects - the emergence of a generic object model
• (17:00-17:30) Kira Zsolt Overcoming heterogeneity when transferring concepts between robots with different embodiments

Motivation

Computer vision is gaining importance in the fields of artificial cognitive systems and robotics, due to the progress achieved in the last years in recognition, categorization and scene analysis as well as its low cost and versatility. From robot localization to manipulation, the integration of state of the art vision algorithms into robotic systems is a success story. Still, the two fields are largely separated. While vision has been traditionally studied using a reductionistic approach, issues such as multi-cue integration, embodied categorization and situated attention can only be studied in the context of systems. The goals of this workshop are to document the progress of the relatively young field of cognitive computer vision and systems, to bring together the researchers working and interested in this field and giving them a platform to discuss the most recent advances in the field and what are the research challenges that is timely to attack today.

Topics

The focus of the workshop will be particularly on categorization and attention, and their relation to embodiment:

• Categorization: The capability to categorize objects on the basis of their visual appearance is one of the crucial cognitive abilities that enable humans to understand the outside world and interact with it. Providing an autonomous robot with the same capability is a major scientific challenge. The computer vision community has achieved impressive results in this field recently, but these results are not easily exploited by the robotic community. The current mainstream approach in computer vision performs categorization from collections of static images, typically acquired on the web and usually representing objects on the basis of only one type of visual feature. New methods are needed to enable abstractions and effective categorization, keeping into account the 3D structure of object categories, their associated affordances and how embodiment, context and task affects modeling and learning for an autonomous agent.
• Attention: 30 or so years ago attention was an obvious research topic in computer vision or image processing. One had to go to great lengths to process only the most relevant parts of images because computers had so little power. But now, computer power abounds and is cheap. It is the era of the large database and machine learning and brute force solutions. Today's powerful statistical classifiers may yield impressive single task performance but they do not lead to representations suitable for visual reasoning and cognition. Further, they ignore the fact that the world is 3D and that vision is an active process and cameras must move in the world to find items of interest. Even the databases on which they are tested require re-consideration so ensure they are statistically valid for their tasks and include no biases. Still, results are impressive and only promise to become more so with computer power increases and declining costs. But the goal for vision systems is really still the same as it was 30 years ago. We want systems to be robust to all the variability in the visual world, to the way we view the world and to the knowledge we have of the world, we want them to be flexible and not be single-task systems, we want them to do more than classify an image, and visual reasoning and problem solving remain important unsolved problems. We want them to properly deal with the unexpected or a not-previously-viewed scene. Attention is that capacity that helps optimize the search processes inherent in perception, cognition and action, thus reducing the computational load of an agent. The spectrum of attentive behavior is broad and goes far beyond the simple region-of-interest functions most common in today's systems. When embodied in an agent, attention controls active sensing and action and promises to enable the kind of flexible and robust systems that have been the goal of computer vision since its earliest days.

Submission guidelines

Papers will be double blind reviewed by 3 reviewers. Accepted papers will be published in post-conference proceedings by Springer in LNCS (TBC). The layout of the papers must be prepared according to the Instructions for the Preparation of Camera-Ready Contribution to LNCS Proceedings. Authors are asked to follow these intructions exactly. In addition to the Spinger author instructions, authors should ensure that the submitted paper does not exceed 14 pages in the LNCS format. The first page should contain only the title, abstract and 3-5 keywords characterising the content of the paper. Papers should be sent as a .pdf attachment to icvw-submission@idiap.ch. The subject of the email should be ICVW09, and the body of the email should contain name and affiliation of the authors, title of the submission and name and email address of the contact author.

Important Dates

• Submission deadline July 20, 2009
• Notification to Authors August 20, 2009
• Camera Ready Paper Submission September 5, 2009

Program committee

• Francesco Orabona
• Danica Kragic
• Ross Beveridge
• Horst Bishof
• Antonis Agyros
• Simone Frintrop
• Ales Leonardis
• Sven Wachsmuth
• Michael Felsberg
• Markus Vincze
• Justus Piater
• Jan-Olof Eklhndh
• Bastian Leibe
• Danijel Skocai
• Vasek Hlavac
• David Hogg
• Darius Burschka
• Hedvig Kjellstrom