Self-Supervised Visual Learning by Variable Playback Speeds Prediction of a Video

Abstract

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.

Accepted by IEEE Access on May 19, 2021

References in corpus (5)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
• Self-supervised Co-training for Video Representation Learning
• Unsupervised Domain Adaptation through Self-Supervision
• Self-supervised Video Representation Learning by Pace Prediction

Cited by in corpus (5)

• TCLR: Temporal Contrastive Learning for Video Representation
• Labelling unlabelled videos from scratch with multi-modal self-supervision
• Cross-Modal Attention Consistency for Video-Audio Unsupervised Learning
• ASCNet: Self-supervised Video Representation Learning with Appearance-Speed Consistency
• Unsupervised Visual Representation Learning by Tracking Patches in Video