English

Making a Case for Learning Motion Representations with Phase

Computer Vision and Pattern Recognition 2016-09-09 v2

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.

Cite

@article{arxiv.1609.01693,
  title  = {Making a Case for Learning Motion Representations with Phase},
  author = {S. L. Pintea and J. C. van Gemert},
  journal= {arXiv preprint arXiv:1609.01693},
  year   = {2016}
}

Comments

ECCV 2016 Workshop on Brave new ideas for motion representations in videos

R2 v1 2026-06-22T15:41:41.511Z