Gradient Constraints Can Improve Displacement Expert Performance

The `displacement expert´ has recently proven popular for rapid tracking applications. In this paper, we note that experts are typically constrained only to produce approximately correct parameter updates at training locations. However, we show that incorporating constraints on the gradient of the displacement field within the learning framework results in an expert with better convergence and fewer local minima. We demonstrate this proposal for facial feature localization in static images and object tracking over a sequence.