ACM SIGMM Interest List


Options: Use Forum View

Use Monospaced Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Thomas Ploetz <[log in to unmask]>
Reply To:
Thomas Ploetz <[log in to unmask]>
Tue, 25 Jan 2011 17:09:02 +0000
text/plain (82 lines)
Final Call for Papers

1st International Workshop on 
Frontiers in Activity Recognition using Pervasive Sensing 
--- IWFAR 2011 ---

in conjunction with

9th International Conference on Pervasive Computing (Pervasive) 
San Francisco, USA, June 12, 2011

** Co-Chairs:
Thomas Ploetz, Newcastle University, UK -- [log in to unmask]
Daniel Roggen, ETH Zurich, Switzerland -- [log in to unmask]
Andreas Bulling, University of Cambridge, Lancaster University, UK -- [log in to unmask]

** Program committee
G. Abowd, Georgia Inst. of Techn., USA
M. Beigl, KIT, Germany
I. Essa, Georgia Inst. of Techn., USA
A. Godfrey, Newcastle University, UK
S. Intille, Northeastern University, USA
T. van Kasteren, Bogazici University, Turkey
K. van Laerhoven, TU Darmstadt, Germany
C. Lombriser, IBM Zurich, Switzerland
P. Lukowicz, University of Passau, Germany
P. Olivier, Newcastle University, UK
M. Philipose, Intel Research, USA
J. Rehg, Georgia Inst. of Techn., USA
L. Rochester, Newcastle University, UK
B. Schiele, MPI Saarbruecken, Germany

Activity recognition (AR) emerged as a key area of research in pervasive computing and plays a central role in the field’s vision of developing context-aware systems and interaction. The general objective for current activity recognition systems is to analyze continuous sensor data streams and to detect and discriminate certain activities of interest, and to reject portions of sensor data that cover unknown or idle activities. Reviewing the current literature in the field may give the impression that the general problem of activity recognition has almost been solved. This opens up the question which other – more challenging – activity recognition problems should be addressed in the future. More generally speaking, this also relates to the question how a future AR system should look like. What will be the challenges of AR that go beyond the aforementioned classification approach and could, for example, comprise a quantitative measure of the quality of performing an activity rather than only detecting an activity?
IWFAR 2011 will focus on new “Frontiers in activity recognition using pervasive sensing” in this sense. We want to stimulate and explore the creativity of the community regarding new applications and approaches to AR. The latter could comprise radically new procedures like, for example, biologically inspired AR methods or rigorously exploiting general time-series analysis approaches. We provide a forum for researchers and practitioners to gather and present new ideas, and discuss aspects related to applications and techniques that go beyond classic activity recognition. Covering a more or less emerging field, expected contributions could also cover more speculative ideas.

** Topics
Topics of interest cover both technical approaches as well as definitions of new application cases. Submissions should cover ideas and approaches around next generation activity recognition. This includes but is not limited to:

Meta-analysis of AR methodologies
Engineering of AR-specific machine learning tools
Feature extraction specific to human activities
Bio-inspired approaches for human action perception
Lifelong learning; hybrid approaches; sporadic ground truth
Unsupervised analysis techniques
Quantitative assessments of activity data
Multi-modal activity recognition
Unifying high-level reasoning to low-level pattern matching

Long-term trend and behavioral studies
Anomaly / novelty detection
Robust activity recognition in real-world environments
Human-computer interaction
Support for users with disabilities
Skill assessment

New sensor hardware
New sensing modalities
Sensor networks
Creative use of existing sensors

** Submission Guideline
Prospective authors should prepare full papers with a maximum length of six pages or notes of maximally two pages (double column, ACM style, PDF). Manuscripts will be reviewed by at least two members of the PC. Printed proceedings will be distributed to the participants together with electronic copies on CDROM. An edited book or a special issue of a journal is planned for the aftermath of the workshop for which accepted papers could be the basis.

** Important Dates
Manuscript submission:	
February 4, 2011	Authors notification:	
March 3, 2011	
June 12, 2011

** Contact, further information
[log in to unmask]