Self-Supervised Visual Learning by Variable Playback Speeds Prediction of a Video
This addresses the problem of learning spatio-temporal representations without semantic labels for video analysis, though it appears incremental as it builds on existing self-supervised methods.
The paper tackles self-supervised visual learning by predicting variable playback speeds in videos, resulting in improved performance on action recognition and video retrieval tasks on UCF-101 and HMDB-51 datasets.
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.