Learning Discriminative Prototypes with Dynamic Time Warping

03/17/2021
by   Xiaobin Chang, et al.
0

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.

READ FULL TEXT

page 2

page 8

research
01/09/2019

D^3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation

We address weakly-supervised action alignment and segmentation in videos...
research
06/13/2019

Temporal Transformer Networks: Joint Learning of Invariant and Discriminative Time Warping

Many time-series classification problems involve developing metrics that...
research
09/13/2023

Deep Attentive Time Warping

Similarity measures for time series are important problems for time seri...
research
05/21/2019

Marginalized Average Attentional Network for Weakly-Supervised Learning

In weakly-supervised temporal action localization, previous works have f...
research
03/28/2021

Attention to Warp: Deep Metric Learning for Multivariate Time Series

Deep time series metric learning is challenging due to the difficult tra...
research
06/18/2012

Discriminative Probabilistic Prototype Learning

In this paper we propose a simple yet powerful method for learning repre...
research
07/22/2018

Deep Discriminative Model for Video Classification

This paper presents a new deep learning approach for video-based scene c...

Please sign up or login with your details

Forgot password? Click here to reset