Temporal Convolutional Networks: A Unified Approach to Action Segmentation

Colin Lea, Rene Vidal, Austin Reiter, Gregory D. Hager

Sep 01, 2016 (modified: Sep 01, 2016) ECCV2016 BNMW submission readers: everyone
  • Submit for proceedings: yes
  • Abstract: 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.
  • Conflicts: jhu.edu, cs.jhu.edu, cis.jhu.edu
  • Authorids: clea1@jhu.edu, rvidal@cis.jhu.edu, areiter@cs.jhu.edu, hager@cs.jhu.edu

Loading