On the Integration of Optical Flow and Action Recognition

Laura Sevilla-Lara, Yiyi Liao, Fatma Güney, Varun Jampani, Andreas Geiger, Michael J. Black

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Most of the top performing action recognition methods use optical flow as a "black box'' input. Here we take a deeper look at the combination of flow and action recognition, and investigate why optical flow is helpful, what makes a flow method good for action recognition, and how we can make it better. In particular, we investigate the impact of different flow algorithms and input transformations to better understand how these affect a state-of-the-art action recognition method. Furthermore, we fine tune two neural-network flow methods end-to-end on the most widely used action recognition dataset (UCF101). Based on these experiments, we make the following five observations: (1) optical flow is useful for action recognition because it is invariant to appearance, (2) optical flow methods are optimized to minimize end-point-error (EPE), but the EPE of current methods is not well correlated with action recognition performance, (3) for the flow methods tested, accuracy at boundaries and at small displacements is most correlated with action recognition performance, (4) training optical flow to minimize classification error instead of minimizing EPE improves recognition performance, and (5) optical flow learned for the task of action recognition differs from traditional optical flow especially inside the human body and at the boundary of the body. These observations may encourage optical flow researchers to look beyond EPE as a goal and guide action recognition researchers to seek better motion cues, leading to a tighter integration of the optical flow and action recognition communities.
Original languageEnglish
Title of host publicationPattern Recognition. GCPR 2018.
EditorsThomas Brox, Andrés Bruhn, Mario Fritz
PublisherSpringer International Publishing
Pages281-297
Number of pages17
ISBN (Electronic)978-3-030-12939-2
ISBN (Print)978-3-030-12939-2
DOIs
Publication statusE-pub ahead of print - 14 Feb 2019
EventGerman Conference on Pattern Recognition 2018 - Stuttgart, Germany
Duration: 10 Oct 201812 Oct 2018
http://gcprvmv2018.vis.uni-stuttgart.de/index.shtml

Publication series

NameLecture Notes in Computer Science
PublisherSpringer, Cham
Volume11269
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349
NameImage Processing, Computer Vision, Pattern Recognition, and Graphics
Volume11269

Conference

ConferenceGerman Conference on Pattern Recognition 2018
Abbreviated titleGCPR 2018
CountryGermany
CityStuttgart
Period10/10/1812/10/18
Internet address

Fingerprint

Dive into the research topics of 'On the Integration of Optical Flow and Action Recognition'. Together they form a unique fingerprint.

Cite this