Abstract | ||
---|---|---|
In this work, we propose a model for video scenes that contains temporal variability in shape and appearance. We propose a conditionally linear model akin to a dynamic extension of active appearance models. We formulate the problem variationally, and propose a framework where a model complexity cost dictates the "modeling responsibility" of each of the factors: appearance, shape and motion. We render the learning problem well-posed by reverting to a physical and a dynamic prior, and use the finite element method to compute a numerical solution. We illustrate our model to learn and simulate the shape, appearance, and motion of scenes that exhibit some form of temporal regularity, intended in a statistical sense. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1109/CVPR.2005.226 | Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference |
Keywords | Field | DocType |
finite element analysis,video coding,active appearance model,dynamic scenes modeling,finite element method,linear model,model complexity cost,modeling responsibility,temporal appearance variability,temporal regularity,temporal shape variability,video scenes | Computer vision,Active shape model,Dynamic Extension,Linear model,Computer science,Finite element method,Active appearance model,Artificial intelligence,Model complexity | Conference |
Volume | ISSN | ISBN |
1 | 1063-6919 | 0-7695-2372-2 |
Citations | PageRank | References |
4 | 0.51 | 15 |
Authors | ||
1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gianfranco Doretto | 1 | 1026 | 78.58 |