About Me ...
I am a Research Scientist at Disney Research Pittsburgh, in conjunction with Carnegie Mellon University. My current research focuses on articulated motion capture, manifold learning, character animation and a number of other directions on the fringe of computer vision, machine learning, and computer graphics. I work in colaboration with Prof. Jessica Hodgins and a number of other excellent researchers. Before coming to Disney Research and CMU, I spent 2 years working as a Postdoctoral Fellow in the Department of Computer Science at University of Toronto (UofT). At UofT I worked with Prof. David Fleet and collaborated with a number of his, as well as Prof. Geoff Hinton's students. During my time at UofT I also twice taught an undergraduate Computer Graphics course at University of Toronto, Scarborough.
My doctorate dissertation, Continuous-state Graphical Models for Object Localization, Pose Estimation and Tracking, was written under the supervision of my advisor Prof. Michael J. Black at Brown University. I received my Master's Degree in Computer Science and dual undergraduate degrees in Computer Science and Applied Mathematics from Boston University, where I worked with Prof. Stan Sclaroff.
I also try to maintain an active professional service within the community. As part of that service I regularly review papers for major computer vision and machine learning conferences, and have orginized a number of workshops and, more recently, a tutorial. My full bio and CV can be found here.
My research interests mainly lie in the areas of computer vision, machine learning, and computer graphics. I am particularly interested in statistical models for problems of visual inference. I am probably most known for my work on articulated pose estimation and tracking. More recently I have also conducted research on the articulated shape estimation. My most recent work focuses on the physics-based dynamical simulation priors for articulated human motion modeling and tracking.
News and recent activity
- Siggraph 2011: Motion Capture from Body-Mounted Cameras
- Co-edited book Visual Analysis of Humans: Looking at People (T. Moeslund, A. Hilton, V. Krüger, L. Sigal, Eds.), ISBN 978-0-85729-996-3, Springer, 2011.
- The tutorial Looking at People: The past, the present and the future held in conjunction with ICCV 2011 (co-organized with Thomas Moeslund, Adrian Hilton and Volker Krüger)
Recently accepted papers and book chapters
- Facial Expression Transfer with Input-Output Temporal Restricted Boltzmann Machines
M. Zeiler, G. Taylor, L. Sigal, I. Matthews and R. Fergus. NIPS, 2011.
Videos: [web page] - Motion Capture from Body-Mounted Cameras,
T. Shiratori, H. S. Park, L. Sigal, Y. Sheikh and J. K. Hodgins. ACM SIGGRAPH, 2011.
Project: web page
Videos: [Supplementary Video (QuickTime, 85mb)]
- Human Attributes from 3D Pose Tracking, L. Sigal, D. Fleet, N. Troje, M. Livne. ECCV, 2010.
Videos: [Supplementary Video (12mb)] - Stable Spaces for Real-time Clothing, E. de Aguiar, L. Sigal, A. Treuille and J. K. Hodgins. ACM SIGGRAPH, 2010.
Project: Web Page
Videos: [Supplementary Video (64mb)] - Dynamical Binary Latent Variable Models for 3D Human Pose Tracking, G. Taylor, L. Sigal, D. Fleet and G. Hinton.
CVPR, 2010.
Suplimental Materials: Learning
Videos: [Supplementary Video - Multiview (13mb)], [Supplementary Video - Monocular (16mb)].
Selected publications
- Estimating Contact Dynamics, M. Brubaker, L. Sigal and D. Fleet. ICCV, 2009.
- Shared Kernel Information Embedding for Discriminative Inference, L. Sigal, R. Memisevic, D. Fleet. CVPR, 2009.
- Physical Simulation for Probabilistic Motion Tracking, M. Vondrak, L. Sigal and O. C. Jenkins. CVPR, 2008.
- Combined discriminative and generative articulated pose and non-rigid shape estimation. L. Sigal, A. Balan and M.J. Black. NIPS, 2007.
- Predicting 3D People from 2D Pictures. L. Sigal and M. J. Black. AMDO, 2006. (best paper award)
- Measure Locally, Reason Globally: Occlusion-sensitive Articulated Pose Estimation. L. Sigal and M. J. Black. CVPR, 2006.
- Tracking Loose-limbed People. L. Sigal, S. Bhatia, S. Roth, M. J. Black and M. Isard. CVPR, 2004.
Organized tutorials
- Physics-Based Human Motion Modelling for People Tracking (in conjunction with ICCV 2009). Organizers: M. Brubaker, L. Sigal, D. Fleet.
Organized workshops
- HM2010: 3rd Workshop on Human Motion Understanding, Modeling, Capture and Animation (held in conjunction with ECCV 2010)
- EHuM2: 2nd Workshop on Evaluation of Articulated Human Motion and Pose Estimation (held in conjunction with CVPR 2007)
- EHuM: Workshop on Evaluation of Articulated Human Motion and Pose Estimation (held in conjunction with NIPS 2006)