| MARCOnI - ConvNet-based MARker-less Motion Capture in Outdoor and Indoor Scenes. | 4 | 0.42 | 2017 |
| Dancing with Turks | 1 | 0.40 | 2015 |
| Efficient object localization using Convolutional Networks | 113 | 3.57 | 2015 |
| Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation. | 243 | 8.87 | 2014 |
| Modeep: A Deep Learning Framework Using Motion Features For Human Pose Estimation | 45 | 1.62 | 2014 |
| Learning Human Pose Estimation Features with Convolutional Networks. | 47 | 2.04 | 2013 |
| Cryptagram: photo privacy for online social media | 14 | 0.77 | 2013 |
| Markerless Motion Capture in the Crowd | 1 | 0.35 | 2012 |
| 3D skeletal reconstruction from low-resolution multi-view images | 0 | 0.34 | 2012 |
| Learning invariance through imitation | 13 | 1.09 | 2011 |
| Pose-Sensitive Embedding by Nonlinear NCA Regression. | 14 | 6.61 | 2010 |
| Convolutional learning of spatio-temporal features | 228 | 13.45 | 2010 |
| Large Displacement Optical Flow | 63 | 4.23 | 2009 |
| Improving acoustic speaker verification with visual Body-Language features | 2 | 0.45 | 2009 |
| ILM's multitrack: a new visual tracking framework for high-end VFX production | 4 | 0.86 | 2009 |
| Mood swings: expressive speech animation | 68 | 2.11 | 2005 |
| Squidball: an experiment in large-scale motion capture and game design | 8 | 1.09 | 2005 |
| Speaking with hands: creating animated conversational characters from recordings of human performance. | 1 | 0.35 | 2004 |
| Twist Based Acquisition and Tracking of Animal and Human Kinematics | 106 | 3.85 | 2004 |
| Speaking with hands: creating animated conversational characters from recordings of human performance | 87 | 4.08 | 2004 |
| Learning Non-Rigid 3D Shape from 2D Motion | 79 | 3.68 | 2003 |
| Motion capture assisted animation: texturing and synthesis | 173 | 13.36 | 2002 |
| Space-Time Tracking | 56 | 4.36 | 2002 |
| Turning to the masters: motion capturing cartoons | 106 | 6.18 | 2002 |
| Tracking And Modeling Non-Rigid Objects With Rank Constraints | 142 | 8.67 | 2001 |
| Recovering Non-Rigid 3D Shape from Image Streams | 373 | 22.57 | 2000 |
| Using Vision for Animation: From Kangaroos to Talking Heads | 0 | 0.34 | 2000 |
| Animating by Multi-Level Sampling | 25 | 4.71 | 2000 |
| Tracking People with Twists and Exponential Maps | 425 | 66.22 | 1998 |
| Learning and Recognizing Human Dynamics in Video Sequences | 318 | 80.71 | 1997 |
| Video Rewrite: driving visual speech with audio | 320 | 26.24 | 1997 |
| Video rewrite: visual speech synthesis from video. | 0 | 0.34 | 1997 |
| Eigen-points [image matching] | 10 | 1.67 | 1996 |
| Nonlinear manifold learning for visual speech recognition | 70 | 34.79 | 1995 |
| Nonlinear image interpolation using manifold learning | 39 | 26.18 | 1994 |
| Surface Learning with Applications to Lipreading | 51 | 100.70 | 1993 |
| Bimodal sensor integration on the example of `speechreading' | 19 | 6.66 | 1993 |
| Improving connected letter recognition by lipreading | 53 | 33.99 | 1993 |
