# Making a Case for Learning Motion Representations with Phase

arXiv: https://arxiv.org/abs/1609.01693 · HTML: https://mlsanity.com/paper/1609.01693/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Sep 2016.

## Built on by (most cited first, 3 of 3)

- [Camera Measurement of Physiological Vital Signs](https://mlsanity.com/paper/2111.11547/) (2021)
- [Objects do not disappear: Video object detection by single-frame object location anticipation](https://mlsanity.com/paper/2308.04770/) (2023)
- [Mamba-based Spatio-Frequency Motion Perception for Video Camouflaged Object Detection](https://mlsanity.com/paper/2507.23601/) (2025)

## Abstract (arXiv)

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.