Papers › Shuffle and Learn: Unsupervised Learning using Temporal Order Verification

Shuffle and Learn: Unsupervised Learning using Temporal Order Verification

28 Mar 2016arXiv:1603.08561archive 2025-07-28

Ishan Misra, C. Lawrence Zitnick, Martial Hebert

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.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action RecognitionPose EstimationSelf-Supervised Action RecognitionTemporal Action LocalizationVideo Alignment

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Self-Supervised Action Recognition HMDB51 Shuffle and Learn (AlexNet) Frozen false #48 of 48 Archive leaderboard report
Self-Supervised Action Recognition HMDB51 Shuffle and Learn (AlexNet) Pre-Training Dataset UCF101 #48 of 48 Archive leaderboard report
Self-Supervised Action Recognition HMDB51 Shuffle and Learn (AlexNet) Top-1 Accuracy 19.8 #48 of 48 Archive leaderboard report
Self-Supervised Action Recognition UCF101 Shuffle and Learn (AlexNet) 3-fold Accuracy 50.9 #52 of 53 Archive leaderboard report
Self-Supervised Action Recognition UCF101 Shuffle and Learn (AlexNet) Frozen false #52 of 53 Archive leaderboard report
Self-Supervised Action Recognition UCF101 Shuffle and Learn (AlexNet) Pre-Training Dataset UCF101 #52 of 53 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections