# Conditional Deep Canonical Time Warping

arXiv: https://arxiv.org/abs/2412.18234 · HTML: https://mlsanity.com/paper/2412.18234/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 28 references that are in the map.
- First posted on arXiv 24 Dec 2024.

## Builds on (most cited first, 9 of 9)

- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Learning Relationships between Text, Audio, and Video via Deep Canonical Correlation for Multimodal Language Analysis](https://mlsanity.com/paper/1911.05544/) (2019)
- [Locally Sparse Neural Networks for Tabular Biomedical Data](https://mlsanity.com/paper/2106.06468/) (2021)
- [Nonparametric Canonical Correlation Analysis](https://mlsanity.com/paper/1511.04839/) (2015)
- [Interpretable Deep Clustering for Tabular Data](https://mlsanity.com/paper/2306.04785/) (2023)
- [Dynamic Temporal Alignment of Speech to Lips](https://mlsanity.com/paper/1808.06250/) (2018)
- [Support Recovery with Stochastic Gates: Theory and Application for Linear Models](https://mlsanity.com/paper/2110.15960/) (2021)
- [Contextual Feature Selection with Conditional Stochastic Gates](https://mlsanity.com/paper/2312.14254/) (2023)
- [A General Optimization Framework for Dynamic Time Warping](https://mlsanity.com/paper/1905.12893/) (2019)

## Abstract (arXiv)

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.