[Back]

W. Kropatsch, A. Ion, N. Artner:
"Describing When and Where in Vision";
Talk: 16th Iberoamerican Congress on Pattern Recognition (CIARP 2011), Pucon, Chile; 2011-11-15 - 2011-11-18; in: "The 16th International Congress on Pattern Recognition, CIARP 2011, volume 7042 of Lecture Notes in Computer Science", Lecture Notes on Computer Science, 7042 (2011), ISSN: 0302-9743; 25 - 26.

Different from the what and where pathways in the organization
of the visual system, we address representations that describe
dynamic visual events in a unified way.
Representations are an essential tool for any kind of process that operates
on data, as they provide a language to describe, store and retrieve
that data. They define the possible properties and aspects that
are stored, and govern the levels of abstraction at which the respective
properties are described. In the case of visual computing (computer vision,
image processing), a representation is used to describe information
obtained from visual input (e.g. an image or image sequence and the
objects it may contain) as well as related prior knowledge (experience).
The ultimate goal, to make applications of visual computing be part
of our daily life, requires that vision systems operate reliably, nearly
anytime and anywhere. Therefore, the research community aims to solve
increasingly more complex scenarios. Vision both in humans and computers
is a dynamic process, thus variations (change) always appear in
the spatial and the temporal dimensions. Nowadays significant research
efforts are undertaken to represent variable shape and appearance, however,
joint representation and processing of spatial and temporal domains
is not a well-investigated topic yet. Visual computing tasks are
mostly solved by a two-stage approach of frame-based processing and
subsequent temporal processing. Unfortunately, this approach reaches
its limits in scenes with high complexity or difficult tasks e.g. action
recognition. Therefore, we focus our research on representations which
jointly describe information in space and time and allow to process data
of space-time volumes (several consecutive frames).
In this keynote we relate our own experience and motivations, to the
current state of the art of representations of shape, of appearance, of
structure, and of motion. Challenges for such representations are in applications
like multiple object tracking, tracking non-rigid objects and
human action recognition.