Dependence Maximizing Temporal Alignment via Squared-Loss Mutual Information
This method addresses temporal alignment challenges in fields like speech processing and computer vision, offering a novel information-theoretic approach that is incremental in improving alignment flexibility and computational efficiency.
The paper tackles the problem of temporal alignment between sequences with different lengths, dimensionality, and statistical properties by proposing LSDTW, a method that maximizes statistical dependency using squared-loss mutual information, achieving efficient alignment as demonstrated on synthetic and Kinect action recognition datasets.
The goal of temporal alignment is to establish time correspondence between two sequences, which has many applications in a variety of areas such as speech processing, bioinformatics, computer vision, and computer graphics. In this paper, we propose a novel temporal alignment method called least-squares dynamic time warping (LSDTW). LSDTW finds an alignment that maximizes statistical dependency between sequences, measured by a squared-loss variant of mutual information. The benefit of this novel information-theoretic formulation is that LSDTW can align sequences with different lengths, different dimensionality, high non-linearity, and non-Gaussianity in a computationally efficient manner. In addition, model parameters such as an initial alignment matrix can be systematically optimized by cross-validation. We demonstrate the usefulness of LSDTW through experiments on synthetic and real-world Kinect action recognition datasets.