Darren Cosker's Home Page

Darren Cosker

Royal Academy of Engineering/EPSRC Research Fellow

Department of Computer Science
University of Bath
Bath
United Kingdom
BA2 7AY

D.P.Cosker(at)cs(dot)bath(dot)ac(dot)uk

I joined the Department of Computer Science at Bath University in 2007, where I hold a Royal Academy of Engineering/EPSRC Research Fellowship.

I am a part of the Centre for Digital Entertainment (CDE) and the Media Technology Research Centre (MTRC), both of which have interests spanning Animation, Visual Interpretation and Digital Effects. I received a BSc in Computer Science with Honours from Cardiff University in 2001, and a Ph.D in Computer Science from Cardiff University in 2006. My thesis explored the synthesis and perceptual analysis of visual speech. I am also a visiting fellow at the Centre for Vision, Speech and Signal Processing (CVSSP) at Surrey University, and visiting researcher at Cardiff University.

My research interests lie in the convergence of Computer Vision, Computer Graphics and Psychology - particularly in relation to human motion analysis and synthesis. I am also interested in applying computer vision, graphics and machine learning techniques to movie VFX and video games, and worked as an R&D consultant for Double Negative developing non-rigid motion-tracking tools.

My CV contains more detailed information on current work and interests, as well as a full publication list.

Consultancy: I am happy to perform R&D facial capture (2D and 3D video based) consultancy for video game, VFX and other interested sectors. For example: facial motion capture (marker and markerless video based 2D and 3D AAM driven solutions), performance mapping/solving, pipeline development for dynamic 3D capture and markerless tracking to full 3D mesh correspondence (e.g. for DI3D, 3DMD or MOVA systems), FACS capture, Rockstar 'LA Noire' type capture and replay. Please get in touch to speak more.

Students

Current Students:

Wenbin Li (PhD),
Rui Tang (PhD),
Han Gong (PhD),
Thomas Nugent (EngD - Electronic Arts),
Charalampos Koniaris (EngD - Disney),

Past Students:

Undergraduate: James Cross (BSc, Real-Time 3D Facial Motion Capture), Matthew Howes (BSc, Tracking), Tomas Gerulaitis (BSc, 3D Blend-Shape Models)
Lanthao Benedikt (PhD. Secondary Involvement via University of Cardiff, Dynamic Face Recognition),
Matt Walkerdine (MSc, Skin Detail Enhancement), Rui Tang (MSc, Face Recognition), Chun-Jung Lin (MSc, Gesture Recognition using a 3D Camera)
Kirill Sidorov (BSc, AAM Based Animation), Ross Borkett (BSc, LBPs for Expression Recognition),

EPSRC Network on Vision and Language (V&L) - Annual Meeting 2011

The EPSRC Network on Vision and Language funds and supports research at the convergence of Computer Vision and Language Processing and Understanging.
Visit its homepage for more details on how to get involved, including how to get the network to fund your research.

The first annual meeting for the network will take place on 15th September. The meeting website provides instructions on how to submit your work and attend.

AVA/BMVA Biological and Computer Vision 2011

The study of biological and machine vision share much common history (e.g. Marr), and each discipline has benefited enormously from findings and techniques from the other. In the UK (in contrast to elsewhere) the discussion and collaboration between the sister disciplines seems to have declined. The aim of this meeting, organised jointly by the Applied Vision Association (AVA) (UK biological vision) and British Machine Vision Association (BMVA) (UK computer vision) was to reignite conversations between these two fields.
The meeting was held in Cardiff University School of Psychology on 26th May 2011. For more information, see the meeting website.

ACM/SSPNET Symposium on Facial Analysis and Animation (FAA), 2010

ACM/SSPNET FAA 2010 took place at the Informatics Forum at the University of Edinburgh in October, 2010. You can find out about it at the FAA Webpage and read submited abstracts at the ACM Digital Library. The aim of FAA is to bring together researchers and practitioners from both academia and industry - particularly in VFX and games - interested in all

EngD in Digital Entertainment

There are currently multiple EngD opportunities in our research group in the area of Digital Entertainment, including movie effects post-production and video games. An EngD is a 4 year degree based primarily in Industry on a problem jointly supervised by both Industry and Academia. There are currently EngD opportunities with a number of internationally leading companies, including Electronic Arts, Double Negative, Aardman, Frontier and Naturalmotion. An EngD gives you the perfect opportunity to work on cutting edge problems with both significant Industrial and Academic relevance.

You can find out more details at our current EngD website, or you can send me an email if you are interested in applying or finding out more.

PhD Opportunities

Currently, I am particularly interested in looking for an exceptional candidate to work on facial analysis and animation combined with speech. Funding would be competitive through our Faculty of Science. However, if you are interested in these other broad areas please get in touch: motion capture, human behaviour classification and modelling, 3D capture, stereoscopic display and perception and applied perception to graphics.

Funding: Each year the University awards a certain number of studentships to overseas (non EU/UK) students. These are competitive, and applications for awards have to be submitted (via the potential supervisor) typically by the end of January each year. Students interested in doing a PhD with me through this route should get in touch at the beginning of January at the latest to give time to make the application. Home students (UK/EU) interested in getting funding could do so via Bath Uni. faculty of science funding. Again, an application has to be made with a deadline of around November each year. Interested students should therefore get in touch with me around October for this route. Other funding opportunities do sometimes appear throughout the year, for example via projects with companies or research councils. These would typically be advertised on this site, mailing lists, academic job sites, etc.

Selected Publications

	D. Cosker, E. Krumhuber and A. Hilton, "A FACS Valid 3D Dynamic Action Unit Database with Applications to 3D Dynamic Morphable Facial Modelling", In Proc. of IEEE International Conference on Computer Vision (ICCV), 2011. D3DFACS Dataset Home Page
	M. Wright, C. Lin, E. O'Neil, D. Cosker, P. Johnson, "3D Gesture Recognition: An Evaluation of User and System Performance", Pervasive, 2011.
	Lanthao Benedikt, Paul L. Rosin, David Marshall, Darren Cosker, Hashmat Popat, and Stephen Richmond, "Facial Actions for Biometric Applications" , (Book Chapter) In 'Three-Dimensional Imaging for Orthodontics and Maxillofacial Surgery', Eds. Chung How Kau, Stephen Richmond Part 3: Movement and Facial Dynamics, pp 267-285, Wiley-Blackwell, ISBN: 9781405162401, 2010.
	D. Pickup, C. Li, D. Cosker, P. Hall, P. Willis, "Reconstructing Mass-Conserved Water using Shape from Shading and Optical Flow", In Proc. of Asian Conference on Computer Vision (ACCV), 2010.
	D. Cosker, E. Krumhuber and A. Hilton, "Perception of Linear and Nonlinear Motion Properties using a FACS Validated 3D Facial Model", In Proc. of ACM Symposium on Applied Perception in Graphics and Visualisation (APGV), pp 101-108, 2010
	L. Benedikt, D. Cosker, D. Marshall and P. L. Rosin, "Assessing the Uniqueness and Permanence of Facial Actions for Use in Biometric Applications", IEEE Transactions on Systems, Man and Cybernetics - Part A: Systems and Humans, Vol. 40, No 3, pp 449-460, 2010.
	Y. Zheng, Y. Hicks, D. Marshall, D. Cosker, "Real-Time Generation of Interactive Virtual Human Behaviours", Lecture Notes in Communications in Computer and Information Science Series: Computer Vision and Computer Graphics. Theory and Applications, Springer-Verlag, Vol. 24, Springer, pp 70-82, 2009.
	C. Charron, Y. A. Hicks, P. Hall and D. Cosker, "Incremental Learning of Dynamical Models of Faces", In Proc. BMVC 2009.
	D. Cosker and J. Edge, "Laughing, Crying, Sneezing and Yawning: Automatic Voice Driven Animation of Non-Speech Articulations", In Proc. of Computer Animation and Social Agents (CASA), 2009 Short Version There is various press related to this work, including a report on the New Scientist website.
	E. Krumhuber, A. Manstead, D. Cosker, D. Marshall and P. L. Rosin, "Effects of Dynamic Attributes of Smiles in Human and Synthetic Faces: A Simulated Job Interview Setting", Journal of Non-Verbal Behaviour, vol. 33, no. 1, pp. 1-15, 2009.
	L. Benedikt, D. Cosker, D. Marshall and P. L. Rosin, "3D Facial Gestures in Biometrics: from Feasibility Study to Application", In Proc. of IEEE International Conference on Biometrics Theory, Applications and Systems, pp 1-6, 2008.
	D. Cosker, C. Holt, D. Mason, G. Whatling, D. Marshall and P. L. Rosin, "Automatic Audio Driven Animation of Non-Linguistic Vocalisations", In Proc. of CMBBE 2008. Download: Poster There is various press about this work, including a report on the New Scientist website.
	L. Benedikt, V. Kajic, D. Cosker, D. Marshall and P.L. Rosin, "Facial Dynamics in Biometric Identification", In Proc. of Britsh Machine Vision Conference (BMVC), 2008.
	D. Cosker, R. Borkett, D. Marshall and P. L. Rosin, "Towards Automatic Performance Driven Animation Between Multiple Types of Facial Model", IET Computer Vision, Vol. 2, No. 3, pages 129-141. 2008.
	Y. Zheng, Y. Hicks, D. Marshall and D. Cosker, "Generating Human Interactive Behaviours using the Windowed Viterbi Algorithm", In Proc. of the Third International Conference on Computer Graphics Theory and Applications (GRAPP), 2008 Videos: Push, Pull, Handshake
	L. Benedikt, E. Krumhuber, A. Calvert, D. Cosker, P. Rosin and D. Marshall, "Using Dynamic 3D Facial Data to Create 3D Appearance Models of Facial Action Units", ACM SIGGRAPH 2007 (poster), San Diego, 2007.
	D. Cosker, S. Roy, P. L. Rosin, D. Marshall, "Remapping Animation Parameters between Multiple Types of Facial Model", Lecture Notes in Computer Science (LNCS), Volume 4418, pages 365-378, Springer, 2007. Videos: Overview, Simple_Morph_Target_Mapping_Example
	E. Krumhuber, A. Manstead, D. Cosker, P.L.Rosin and A.D. Marshall, "Facial Dynamics as Indicators of Trustworthiness and Cooperative Behaviour", Emotion, Vol 7, No 4, pp 730-735, 2007. Videos: Overview. Smile_Analysis - this curve is then manipulated to create 'fake' or 'genuine' smiles.
	Z.Zheng, Y. A. Hicks, D. Cosker, D. Marshall and J. A. Chambers, “Virtual Friend: Tracking and Generating Natural Interactive Behaviours in Real Video”, In Proc. of IEEE International Conference on Signal Processing (ICSP), Gullin, China, 2006. Videos: Push_Video_Example
	D. Cosker, D. Marshall, P. Rosin, S. Paddock, S. Rushton, ``Towards Perceptually Realistic Talking Heads: Models, Metrics and McGurk'', ACM Transactions on Applied Perception, vol. 2, no. 3, pp 270-285, 2005. Videos: Synthetic_McGurk_1, (Tuple - Synthetic_Clip="Dead", Audio_Clip="Mat", Perception="Gnat") The full set of videos used in this paper can be obtained by contacting me.
	W. Wang, D. Cosker, Y. Hicks, S. Sanei, and J. A. Chambers, ``Video Assisted Speech Source Separation'', In Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2005 Philadelphia, USA.
	D. Cosker, D. Marshall, P. Rosin, Y.A. Hicks, ``Speech Driven Facial Animation using a Hidden Markov Co-articulation Model'', In Proc. of IEEE International Conference on Pattern Recognition (ICPR), Vol. 1, pp 128-131, 2004. Videos: Example_1, Example_2 (both example videos generated using only speech), Tracking_Example Annotated audio-visual training data used in this paper can be obtained by contacting me.
	D. Cosker, D. Marshall, P. Rosin, Y.A. Hicks,``Speech Driven Facial Animation using a Hierarchical Model'', IEE Vision, Image and Signal Processing, Vol. 151 (4) pp. 314-321, 2004.
	D. Cosker, "Animation of a Hierarchical Appearance Based Facial Model and Perceptual Analysis of Visual Speech", Ph.D Thesis, Cardiff University, 2005