Self-supervised visual learning by variable playback speeds prediction of a video

Hyeon Cho, Taehoon Kim, Hyung Jin Chang, Wonjun Hwang

Research output: Contribution to journalArticlepeer-review

34 Downloads (Pure)


We propose a self-supervised visual learning method by predicting the variable playback speeds of a video. Without semantic labels, we learn the spatio-temporal visual representation of the video by leveraging the variations in the visual appearance according to different playback speeds under the assumption of temporal coherence. To learn the spatio-temporal visual variations in the entire video, we have not only predicted a single playback speed but also generated clips of various playback speeds and directions with randomized starting points. Hence the visual representation can be successfully learned from the meta information (playback speeds and directions) of the video. We also propose a new layer-dependable temporal group normalization method that can be applied to 3D convolutional networks to improve the representation learning performance where we divide the temporal features into several groups and normalize each one using the different corresponding parameters. We validate the effectiveness of our method by fine-tuning it to the action recognition and video retrieval tasks on UCF-101 and HMDB-51. All the source code is released in
Original languageEnglish
Article number9443174
Pages (from-to)79562-79571
Number of pages10
JournalIEEE Access
Publication statusPublished - 28 May 2021


  • Three-dimensional displays
  • Task analysis
  • Visualization
  • Feature extraction
  • Semantics
  • Coherence
  • Sorting


Dive into the research topics of 'Self-supervised visual learning by variable playback speeds prediction of a video'. Together they form a unique fingerprint.

Cite this