The dominant paradigm for video-based action segmentation is composed of two steps: first, for each frame, compute low-level features using Dense Trajectories or a Convolutional Neural Network that encode spatiotemporal information locally, and second, input these features into a classifier that captures high-level temporal relationships, such as a Recurrent Neural Network (RNN). While often effective, this decoupling requires specifying two separate models, each with their own complexities, and prevents capturing more nuanced long-range spatiotemporal relationships. We propose a unified approach, as demonstrated by our Temporal Convolutional Network (TCN), that hierarchically captures relationships at low-, intermediate-, and high-level time-scales. Our model achieves superior or competitive performance using video or sensor data on three public action segmentation datasets and can be trained in a fraction of the time it takes to train an RNN.
@article{arxiv.1608.08242,
title = {Temporal Convolutional Networks: A Unified Approach to Action Segmentation},
author = {Colin Lea and Rene Vidal and Austin Reiter and Gregory D. Hager},
journal= {arXiv preprint arXiv:1608.08242},
year = {2016}
}
Comments
Submitted to the ECCV workshop on "Brave new ideas for motion representations in videos" (http://bravenewmotion.github.io/)