The dominant paradigm for video-based action segmentation is composed of two steps: first, compute low-level features for each frame using Dense Trajectories or a Convolutional Neural Network to encode local spatiotemporal information, and second, input these features into a classifier such as a Recurrent Neural Network (RNN) that captures high-level temporal relationships. 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.
展开▼
