Skip to main content.

Introduction

I am currently a research fellow at the Centre of Vision, Speech and Signal Processing (CVSSP) at  The University of Surrey. I joined CVSSP in January 2009. Prior to this I was a research scientist with the Machine Vision Group (MVG) at The University of Oulu in Northern Finland from February 2006 until December 2008. I received my PhD from École Polytechnique Fédérale de Lausanne (EPFL) in October 2005, whilst working as a research assistant at the IDIAP Research Institute in the town of Martigny Switzerland. In November 2000 I completed a Bachelor of Computing and Mathematical sciences (Hons) at The School of Computer Science and Software Engineering at The University of Western Australia in Perth, Australia.

Research Interests

My current research is primarily in the area of audio-visual tracking in videos. Currently this is focused on using sparse representations for appearance modelling combined with particle filters for dynamic modelling. I have also been researching the use of audio and video information for robust face detection. My previous research at CVSSP was primarily in the area of human action recognition in videos. Currently this is focused on using 3-D SIFT like features to generate frame and sequence representations for recognition. I have also been working on more general image representations for object recognition. I have participated in submissions to the PASCAL VOC 2009 and also the ImageCLEF retrieval contest at ICPR 2010. I also help to organise and run the evaluations for the IEEE Workshop on Feature Detectors and Descriptors: The State Of The Art and Beyond at CVPR 2009, along with Dr Krystian Mikolajczyk.

My previous research at The University of Oulu focused on human activity recognition and body part segmentation in surveillance videos. I also collaborated with colleagues on visual motion estimation in mobile phones and visual speech recognition. The research for my PhD was primarily in the field of human action recognition in videos specifically, sports broadcast and smart meeting room data. This research was conducted under the supervision of Dr Samy Bengio and Dr Jean-Marc Odobez. During my PhD I also contributed to two European Union IST projects: Automatic Segmentation and Semantic Annotation of Sports Videos (ASSAVID) and Learning for Adaptable Visual Assistants (LAVA).

^ TOP

Recent Publications

M. Barnard and W. Wang Audio Head Pose Estimation using the Direct to Reverberant Speech Ratio Speech Communication (to appear)

V. Kilic, M. Barnard, W. Wang, and J. Kittler Audio assisted robust visual tracking with adaptive particle filtering IEEE Transactions on Multimedia, vol. 17, no. 2, pp. 186-200, 2015.

M. Barnard, P.K. Koniusz, W. Wang, J. Kittler, S.M. Naqvi and J.A. Chambers Robust Multi-Speaker Tracking via Dictionary Learning and Identity Modelling
IEEE Transactions of Multimedia, vol. 16, no. 3, pp. 864-880, 2014.

M. Barnard, W. Wang and J. Kittler Audio Head Pose Estimation using the Direct to Reverberant Speech Ratio
Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013), Vancouver, Canada, 2013.

V. Kilic, M. Barnard, W. Wang and J. Kittler Audio Constrained Particle Filter Based Visual Tracking
Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013), Vancouver, Canada, 2013.

M. Barnard, W. Wang, J. Kittler, S.M.R. Naqvi, and J.A. Chambers A Dictionary Learning Approach to Tracking
Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2012), Kyoto, Japan, March 25-30, 2012.

M. A. Tahir, F. Yan, P. Koniusz, M. Awais, M. Barnard, K. Mikolajczyk, and J. Kittler A Robust and Scalable Visual Category and Action Recognition System using Kernel Discriminant Analysis with Spectral Regression
IEEE Transactions of Multimedia vol. 15 no. 7 2013

For a full list of publications see here ^ TOP