Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction
This addresses the need for scalable video understanding without costly annotations, though it is incremental as it builds on existing self-supervised pretext tasks.
The paper tackles the problem of expensive video labeling by proposing 3DRotNet, a self-supervised method that learns spatiotemporal features from unlabeled videos via rotation prediction, resulting in accuracy boosts of 20.4% on UCF101 and 16.7% on HMDB51 for action recognition compared to training from scratch.
The success of deep neural networks generally requires a vast amount of training data to be labeled, which is expensive and unfeasible in scale, especially for video collections. To alleviate this problem, in this paper, we propose 3DRotNet: a fully self-supervised approach to learn spatiotemporal features from unlabeled videos. A set of rotations are applied to all videos, and a pretext task is defined as prediction of these rotations. When accomplishing this task, 3DRotNet is actually trained to understand the semantic concepts and motions in videos. In other words, it learns a spatiotemporal video representation, which can be transferred to improve video understanding tasks in small datasets. Our extensive experiments successfully demonstrate the effectiveness of the proposed framework on action recognition, leading to significant improvements over the state-of-the-art self-supervised methods. With the self-supervised pre-trained 3DRotNet from large datasets, the recognition accuracy is boosted up by 20.4% on UCF101 and 16.7% on HMDB51 respectively, compared to the models trained from scratch.