Final Program

Opening

Invited Talk 1

Embodied Emotion and Attention

Tom Ziemke

School of Humanities & Informatics
University of Skövde, Sweden

Emotions can be considered as embodied appraisals, i.e.
perceptions of bodily changes that reflect selected concernrelevant
aspects of the dynamics of agent-environment
interaction. Emotional attunement to changing situations, ranging
from relatively long-lasting background emotions (e.g. moods) to
'short-term' emotions (e.g. fear), provides agents with attention
in the sense of a dynamic modulation of action tendencies and
affordance perception. While robotic and living bodies certainly
differ in their (quasi-) physiological reactions, the concepts of
embodied appraisal and emotional attunement can also usefully
be modeled in robots. The talk provides a theoretical discussion
of the relation between embodiment, emotion and attention, and
provides examples from a European bio-inspired cognitive
robotics project called ICEA (Integrating Cognition, Emotion and
Autonomy).

Session I - Cognitive Processing

Abstraction Level Regulation of Cognitive Processing Through
Emotion-Based Attention Mechanisms
Graça Gaspar, Luis Morgado
ISEL, Portugal

Differences and Interactions between Cerebral Hemispheres
When Processing Ambiguous Homographs
Zohar Eviatar, Hananel Hazan, Larry Manevitz, Orna Peleg
University of Haifa, Israel

Session II – Biologically Inspired Attention

Selective Tuning: Modeling the Dynamics of Feature Binding
during Object-Selective Attention
Albert Rothenstein, John Tsotsos
York University, Toronto, Canada

The Spiking Search over Time and Space Model (sSoTS):
Simulating Dual Task Experiments and the Temporal Dynamics of
Preview Search
Dietmar Heinke, Eirini Mavritsaki, Glyn Humphreys, Gustavo Deco
University of Birmingham, UK

Biologically Inspired Framework for Learning and Abstract
Representation of Attention Control
Hadi Fatemi Shariatpanahi, Majid Nili Ahmadabadi
University of Tehran, Iran

Lunch

Invited Talk 2

Learning to Attend: From Bottom-Up to Top-Down

Jochen Triesch

Frankfurt Institute for Advanced Studies, Frankfurt am Main,
Germany and Department of Cognitive Science, Univ. of
California, San Diego, USA

The control of overt visual attention relies on an interplay of
"bottom-up" and "top-down" mechanisms. Purely "bottom-up"
models cannot provide a satisfactory account of human attention
orienting in many natural behaviors. But how do humans learn to
incorporate "top-down" mechanisms into their control of
attention? The phenomenon of "gaze following", i.e. the ability to
infer where someone else is looking, offers an interesting window
into this question. I review findings on the emergence of gaze
following in human infants and present a computational model of
the underlying learning processes. The model proposes an
explanation for the gradual shift of emphasis from bottom-up to
top-down cues in attention control. It explains this process in
terms of generic reinforcement learning mechanisms and predicts
a new class of "mirror neurons" specific for looking behaviors.
Finally, it offers an explanation for deficits in gaze following in
developmental disorders such as autism.

Session III – Attentive Symbol Grounding

Session IV – Visual and Auditory Attention

Color Saliency and Inhibition in Region Based Visual Attention
Muhammad Zaheer Aziz, Baerbel Mertsching
Paderborn University, Germany

Autonomous Attentive Exploration in Search and Rescue
Scenarios
Andrea Carbone, Daniele Ciacelli, Alberto Finzi, Fiora Pirri
University of Rome, La Sapienza, Italy

Auditory Gist Perception: An Alternative to Attentional Selection
of Auditory Streams
Martin Cooke, Sue Harding, Peter König
University of Sheffield, UK

Poster Session

A Cognitive Model for Visual Attention and its Application
Tibor Bosse, Peter-Paul van Maanen, Jan Treur
Vrije Universiteit Amsterdam, Netherlands

The Selective Attention for Identification model (SAIM):
Simulating Visual Search in Natural Colour Images
Andreas Backhaus, Dietmar Heinke, Glyn Humphreys, Yarou Sun
University of Birmingham, UK

Region-oriented Visual Attention-based Activity Detection
Thomas Geerinck, Hichem Sahli
Vrije Universiteit Brussel, Belgium

A Possible Interplay of Bottom-up and Top-down Approach:
Evidences from Early Vision
Kuntal Ghosh, Sandip Sarkar, Kamales Bhaumik
Saha Institute of Nuclear Physics, India

Automatic Landmark Detection and Recognition in Autonomous
Robotics
Antonio Chella, Irene Macaluso, Lorenzo Riano
Univeristà degli studi di Palermo, Italy

Learning to Attend to Concepts: An Incremental Hidden Variable
Networks Approach
Saied Haidarian Shahri, Majid Nili Ahmadabadi
University of Tehran, Iran