Using a neural net to instantiate a deformable model

By Christopher K. I. Williams, Michael Revow, Geoffrey E. Hinton. 1994

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Geoffrey E. Hinton
2. Ruslan Salakhutdinov
3. Yoshua Bengio
4. Christopher K. I. Williams
5. Trevor Darrell
6. Sergey Levine
7. Dacheng Tao
8. Andrea Vedaldi

Citations in the corpus

• How to Represent Part-Whole Hierarchies in a Neural Network (2021, positive): “Once the lowest-level embedding has been initialized, it can be refined in a closed loop by backpropagating the reconstruction error through the neural field [Williams et al., 1995].”
• Using Generative Models for Handwritten Digit Recognition (1996, methodology): “Using the rich set of instantiation parameters supplied by the correct elastic model after it has been (cid:12)tted, we can train a conventional supervised multi-layer neural network to predict model instantiation parameters from the image [51].”