Call for Papers

Elsevier Journal on Image and Vision Computing
Special Issue on

Machine Learning in Motion Analysis

With the ubiquitous presence of video data and the increasing importance in a wide range of
real-world applications such as visual surveillance, human-machine interfaces and sport event
interpretation, there is an increasing demand for the automatic analysis and understanding of
object motions from large amounts of video footage.

Vision-based motion analysis aims to detect, track, and identify objects, and more
generally, to understand their behaviors, from video sequences. This exciting research area
has received growing interest in recent years due to a wide spectrum of real world
applications such as biomedical image analysis and modeling, visual surveillance,
human-machine interfaces, and virtual reality.

Although there has been much progress in the past decades, many challenging problems
remain unsolved, such as robust object detection and tracking, unconstrained object activity
recognition, and communicative behavior analysis. Recently, statistical machine learning
algorithms, such as manifold learning, probabilistic graphical models, and kernel machines,
have been successfully applied in this area for object tracking, activity modeling and
recognition. We believe that novel statistical learning technologies have a strong potential to
further contribute to the development of robust yet flexible vision systems. The increasing
performance of vision systems has also brought new challenges to the field of machine
learning, e.g., learning from partial or limited annotations, online and incremental learning,
and learning with very large datasets. Solving the problems involved in object motion analysis
will naturally lead to the development of new machine learning algorithms. In return, new
machine learning algorithms are able to address more realistic problems in object motion
analysis and understanding.

This special issue aims to solicit original research contributions that address vision-based
object motion by using machine learning approaches, or that develop new machine learning
and motion analysis approaches. Submissions that address real-world challenging applications
are especially encouraged. Topics of interest include, but are not limited to:

1) Machine Learning Theories

Supervised/unsupervised/semi-supervised learning

Generative and discriminative approaches

Probabilistic graphical models and exponential families

Large-margin methods with structured output

Manifold learning

Structured Prediction

2) Motion Analysis and Understanding

Motion segmentation and object recognition

Motion feature extraction and representation

Activity analysis and unusual event detection

3) Biological and medical applications, such as:

Fluoroscopic sequence analysis

Live cell/tissue motion analysis

Image guided surgery

Important Dates

Papers should be received by December 1, 2011
First reviews will be returned to authors by March 1, 2012
Revised manuscripts should be submitted by May 1, 2012
Possible second reviews will be returned to authors by July 1, 2012
Revised manuscripts should be submitted by August 1, 2012
Final decisions will be communicated by August 15, 2012
Final manuscripts are due by September 15, 2012
The special issue will be (tentatively) published in December 2012

Guest Editors

Prof. Matti Pietikäinen (mkp@ee.oulu.fi), University of Oulu, Finland
Prof. Matthew Turk (mturk@cs.ucsb.edu), University of California, Santa Barbara, USA
Dr. Liang Wang (wangliangnlpr@gmail.com), Chinese Academy of Sciences
Dr. Guoying Zhao (gyzhao@ee.oulu.fi), University of Oulu, Finland
Dr. Li Cheng (chengli@bii.a-star.edu.sg), Bioinformatics Institute, A*STAR, Singapore

Submission Procedure

Prospective authors should follow the regular guidelines of the Image and Vision
Computing Journal for electronic submission: (http://ees.elsevier.com/imavis). During
submission authors must select the “Special Issue: Machine Learning in Motion Analysis”
when they reach the “Article Type”.