Learning Spatiotemporal Models from Training Examples

@inproceedings{Baumberg1995LearningSM,
  title={Learning Spatiotemporal Models from Training Examples},
  author={Adam Baumberg and David C. Hogg},
  year={1995}
}
Physically based vibration modes have been shown to provide a useful mechanism for describing non-rigid motions of articulated and deformable objects. The approach relies on assumptions being made about the elastic properties of an object to generate a compact set of orthogonal shape parameters which can then be used for tracking and data approximation. We present a method for automatically generating an equivalent physically based model using a training set of examples of the object deforming… CONTINUE READING
Highly Cited
This paper has 28 citations. REVIEW CITATIONS

From This Paper

Figures, tables, results, connections, and topics extracted from this paper.
20 Extracted Citations
15 Extracted References
Similar Papers

Citing Papers

Publications influenced by this paper.
Showing 1-10 of 20 extracted citations

Similar Papers

Loading similar papers…