Home/Shuffle and Learn: Unsupervised Learning using Temporal Order Verification

Shuffle and Learn: Unsupervised Learning using Temporal Order Verification

Ishan Misra, C. Lawrence Zitnick and Martial Hebert
European Conference on Computer Vision (ECCV), October, 2016

Download Publication (PDF)

Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author’s copyright. These works may not be reposted without the explicit permission of the copyright holder.


In this paper, we present an approach for learning a visual representation from the raw spatiotemporal signals in videos. Our representation is learned without supervision from semantic labels. We formulate our method as an unsupervised sequential verification task, i.e., we determine whether a sequence of frames from a video is in the correct temporal order. With this simple task and no semantic labels, we learn a powerful visual representation using a Convolutional Neural Network (CNN). The representation contains complementary information to that learned from supervised image datasets like ImageNet. Qualitative results show that our method captures information that is temporally varying, such as human pose. When used as pre-training for action recognition, our method gives significant gains over learning without external data on benchmark datasets like UCF101 and HMDB51. To demonstrate its sensitivity to human pose, we show results for pose estimation on the FLIC and MPII datasets that are competitive, or better than approaches using significantly more supervision. Our method can be combined with supervised representations to provide an additional boost in accuracy.

BibTeX Reference
title = {Shuffle and Learn: Unsupervised Learning using Temporal Order Verification},
author = {Ishan Misra and C. Lawrence Zitnick and Martial Hebert},
booktitle = {European Conference on Computer Vision (ECCV)},
sponsor = {Office of Naval Research, US Army Research Laboratory},
publisher = {Springer},
month = {October},
year = {2016},