Making a Case for Learning Motion Representations with Phase

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

6 Citations (Scopus)


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.
Original languageEnglish
Title of host publicationComputer Vision ECCV 2016 Workshops
Subtitle of host publicationProceedings
EditorsG. Hua, H. Jegou
Place of PublicationCham
Number of pages10
ISBN (Electronic)978-3-319-49409-8
ISBN (Print)978-3-319-49408-1
Publication statusPublished - 2016
EventECCV 2016: 29th European Conference on Computer Vision - Amsterdam, Netherlands
Duration: 8 Oct 201616 Oct 2016

Publication series

NameLecture Notes in Computer Science
PublisherSpringer International Publishing AG
ISSN (Print)0302-9743


ConferenceECCV 2016

Fingerprint Dive into the research topics of 'Making a Case for Learning Motion Representations with Phase'. Together they form a unique fingerprint.

  • Cite this

    Pintea, S., & van Gemert, J. (2016). Making a Case for Learning Motion Representations with Phase. In G. Hua, & H. Jegou (Eds.), Computer Vision ECCV 2016 Workshops: Proceedings (3 ed., pp. 55-64). (Lecture Notes in Computer Science; Vol. 9915). Springer.