Timezone: »
Alignment of time series is an important problem to solve in many scientific disciplines. In particular, temporal alignment of two or more subjects performing similar activities is a challenging problem due to the large temporal scale difference between human actions as well as the inter/intra subject variability. In this paper we present canonical time warping (CTW), an extension of canonical correlation analysis (CCA) for spatio-temporal alignment of the behavior between two subjects. CTW extends previous work on CCA in two ways: (i) it combines CCA with dynamic time warping for temporal alignment; and (ii) it extends CCA to allow local spatial deformations. We show CTWs effectiveness in three experiments: alignment of synthetic data, alignment of motion capture data of two subjects performing similar actions, and alignment of two people with similar facial expressions. Our results demonstrate that CTW provides both visually and qualitatively better alignment than state-of-the-art techniques based on dynamic time warping.
Author Information
Feng Zhou (Carnegie Mellon University)
Fernando D De la Torre (Carnegie Mellon University)
More from the Same Authors
-
2022 : Making Text-to-Image Diffusion Models Zero-Shot Image-to-Image Editors by Inferring "Random Seeds" »
Chen Henry Wu · Fernando D De la Torre -
2022 Poster: Generative Visual Prompt: Unifying Distributional Control of Pre-Trained Generative Models »
Chen Henry Wu · Saman Motamed · Shaunak Srivastava · Fernando D De la Torre -
2018 Poster: Compact Generalized Non-local Network »
Kaiyu Yue · Ming Sun · Yuchen Yuan · Feng Zhou · Errui Ding · Fuxin Xu -
2011 Poster: Matrix Completion for Image Classification »
Ricardo S Cabral · Fernando D De la Torre · Joao P Costeira · Alexandre Bernardino -
2008 Poster: Robust Kernel Principal Component Analysis »
Minh Hoai Nguyen · Fernando D De la Torre -
2008 Spotlight: Robust Kernel Principal Component Analysis »
Minh Hoai Nguyen · Fernando D De la Torre