Learning Discriminative Prototypes with Dynamic Time Warping

2021-03-17 · CVPR 2021 1 · Xiaobin Chang, Frederick Tung, Greg Mori

Dynamic Time Warping (DTW) is widely used for temporal data processing. However, existing methods can neither learn the discriminative prototypes of different classes nor exploit such prototypes for further analysis. We propose Discriminative Prototype DTW (DP-DTW), a novel method to learn class-specific discriminative prototypes for temporal recognition tasks. DP-DTW shows superior performance compared to conventional DTWs on time series classification benchmarks. Combined with end-to-end deep learning, DP-DTW can handle challenging weakly supervised action segmentation problems and achieves state of the art results on standard benchmarks. Moreover, detailed reasoning on the input video is enabled by the learned action prototypes. Specifically, an action-based video summarization can be obtained by aligning the input sequence with action prototypes.

📄 PDF Abstract BibTeX arXiv:2103.09458

Code (1)

BorealisAI/TSC-Disc-Proto 공식 구현 pytorch

Tasks

Action SegmentationDynamic Time WarpingTime SeriesTime Series Analysis Time Series Classification Video Summarization

Methods 이 논문이 사용한 방법론

DTW Dynamic Time Warping (DTW) [1] is one of well-known distance measures between a pairwise of time series. The main idea of DTW is to compute the distance from the matching of…

Deep Attentive Time Warping

2023-09-13 · Shinnosuke Matsuo, Xiaomeng Wu, Gantugs Atarsaikhan, Akisato Kimura 외

Similarity measures for time series are important problems for time series classification. To handle the nonlinear time distortions, Dynamic Time Warping (DTW) has been widely used. However, DTW is not learnable and suff…

Dynamic Time Warping Metric Learning Time Series Time Series Classification

Time Series Data Augmentation for Neural Networks by Time Warping with a Discriminative Teacher

2020-04-19 · Brian Kenji Iwana, Seiichi Uchida

Neural networks have become a powerful tool in pattern recognition and part of their success is due to generalization from using large datasets. However, unlike other domains, time series classification datasets are ofte…

Data Augmentation Dynamic Time Warping Time Series Time Series Analysis+1

D3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation

2019-01-09 · CVPR 2019 6 · Chien-Yi Chang, De-An Huang, Yanan Sui, Li Fei-Fei 외

We address weakly supervised action alignment and segmentation in videos, where only the order of occurring actions is available during training. We propose Discriminative Differentiable Dynamic Time Warping (D3TW), the …

Dynamic Time Warping Segmentation Weakly Supervised Action Segmentation (Transcript)

Attention to Warp: Deep Metric Learning for Multivariate Time Series

2021-03-28 · Shinnosuke Matsuo, Xiaomeng Wu, Gantugs Atarsaikhan, Akisato Kimura 외

Deep time series metric learning is challenging due to the difficult trade-off between temporal invariance to nonlinear distortion and discriminative power in identifying non-matching sequences. This paper proposes a nov…

Dynamic Time Warping Metric Learning Time Series Time Series Analysis+1

ShapeDBA: Generating Effective Time Series Prototypes using ShapeDTW Barycenter Averaging

2023-09-28 · Ali Ismail-Fawaz, Hassan Ismail Fawaz, François Petitjean, Maxime Devanne 외

Time series data can be found in almost every domain, ranging from the medical field to manufacturing and wireless communication. Generating realistic and useful exemplars and prototypes is a fundamental data analysis ta…

Clustering Dynamic Time Warping Time Series Time Series Analysis+1