Conditional Deep Canonical Time Warping

TL;DR

The paper introduces Conditional Deep Canonical Time Warping (CDCTW), a novel method for improving temporal alignment accuracy in high-dimensional, sparse, and dynamically changing sequences, outperforming previous techniques.

Contribution

It proposes a new dynamic feature selection and alignment method, CDCTW, tailored for sparse, high-dimensional, and evolving temporal data, enhancing alignment accuracy.

Findings

CDCTW achieves superior alignment accuracy on various datasets.

The method effectively handles sparsity and high dimensionality.

Experimental results outperform existing temporal alignment techniques.

Abstract

Temporal alignment of sequences is a fundamental challenge in many applications, such as computer vision and bioinformatics, where local time shifting needs to be accounted for. Misalignment can lead to poor model generalization, especially in high-dimensional sequences. Existing methods often struggle with optimization when dealing with high-dimensional sparse data, falling into poor alignments. Feature selection is frequently used to enhance model performance for sparse data. However, a fixed set of selected features would not generally work for dynamically changing sequences and would need to be modified based on the state of the sequence. Therefore, modifying the selected feature based on contextual input would result in better alignment. Our suggested method, Conditional Deep Canonical Temporal Time Warping (CDCTW), is designed for temporal alignment in sparse temporal data to address these challenges. CDCTW enhances alignment accuracy for high dimensional time-dependent views be performing dynamic time warping on data embedded in maximally correlated subspace which handles sparsity with novel feature selection method. We validate the effectiveness of CDCTW through extensive experiments on various datasets, demonstrating superior performance over previous techniques.