[Home] [Schedule] [Speakers & Topics] [Goals and Format] [Abstracts] [NIPS 2004 Conference] [NIPS 2004 Workshops]

NEXT Workshop on this topic behing held at NIPS 2005 on December 10, at Whistler, BC, CANADA. More info here

Organizers:

•  Irfan Essa, Georgia Tech, GVU Center / College of Computing

•  Dieter Fox, U of Washington, Department of Computer Science

Date/Time:

Friday Dec 17, 2004, 7:30am - 10:30am & 4:00pm - 7pm (Day 1 of Workshops)

Goals of the Workshop

Recognition of high-level events from data streams is a much needed resource towards building intelligent machines that provide automatic and autonomous support in our every day lives. Recently, there has been significant progress towards such activity recognition and discovery from data. Research progress is evident in (a) building real systems that extract information from a variety to sensors, to (b) developing and extending statistical machine learning approaches to model data for recognition and matching, to (c) study of specific domains to extract relevant higher-level context which in turn can be leveraged to support recognition. Many well-defined application domains have also been brought to the fore-front recently that only suggests the vast importance of automatic interpretation of data to recognize activities, actions, and behaviors over both short and extended periods. These include surveillance and security, aides for older adults and children with special needs, and support of our every day lives.

However, many significant questions in this area remain and require bringing together experts from various fields to come together to discuss upcoming challenges. In this workshop, we will bring together experts from machine learning, sensing and perception, and ubiquitous computing to discuss issues related to

1. What sensing technologies are available today and how different forms of sensing technologies can be brought to bear on this problem? What is feasible and what are the reliability concerns with various forms of data sensing? (What about privacy?)

2. What data modeling, data interpretation, and machine learning techniques are available today that can be applied to this problem? How can learning be facilitated and how do we deal with unknown and "surprising" events that were unexpected and therefore not modeled?

3. What are some application domains that can leverage from this effort? What specific domain knowledge do these applications provide that can be used to focus the recognition task and perhaps aid in making it tractable?

4. What should be the long-term and short-term goals of the research in activity recognition?

5. Are we mature field to have a challenge domain and a test for such a domain? What is such a domain?

Format

The format of this workshop will be heavily biased towards discussions and brainstorming between experts from differing backgrounds. The main expected outcome is building of better bridges between machine learning, sensing, and ubiquitous computing. It will also generate a list of tools, sensing methodologies, applications, and related challenges within each area that can be used to advance the state of the art in this hotly pursued research challenge.

[Schedule] [Speakers & Topics] [Goals and Format] [Abstracts] [NIPS 2004 Conference] [NIPS 2004 Workshops]

Last Updated: 10/03/2005 10:04:58 AM