Making a Case for Learning Motion Representations with Phase

S. L. Pintea, J. C. van Gemert

Sep 06, 2016 (modified: Sep 06, 2016) ECCV2016 BNMW submission readers: everyone
  • Submit for proceedings: yes
  • Abstract: This work advocates Eulerian motion representation learning over the current standard Lagrangian optical flow model. Eulerian motion is well captured by using phase, as obtained by decomposing the image through a complex-steerable pyramid. We discuss the gain of Eulerian motion in a set of practical use cases: (i) action recognition, (ii) motion prediction in static images, (iii) motion transfer in static images and, (iv) motion transfer in video. For each task we motivate the phase-based direction and provide a possible approach.
  • Conflicts:,
  • Authorids:,