Self-Supervised Human Activity Recognition by Augmenting Generative Adversarial Networks
This work addresses the challenge of enhancing video-based activity recognition, particularly for applications like measuring executive functions in children, though it is incremental as it builds on existing GAN and self-supervised learning methods.
The paper tackles the problem of improving video representations for human activity recognition by augmenting GANs with a self-supervised task, resulting in a more than 4% increase in top-1 classification accuracy on datasets like KTH, UCF101, and Ball-Drop.
This article proposes a novel approach for augmenting generative adversarial network (GAN) with a self-supervised task in order to improve its ability for encoding video representations that are useful in downstream tasks such as human activity recognition. In the proposed method, input video frames are randomly transformed by different spatial transformations, such as rotation, translation and shearing or temporal transformations such as shuffling temporal order of frames. Then discriminator is encouraged to predict the applied transformation by introducing an auxiliary loss. Subsequently, results prove superiority of the proposed method over baseline methods for providing a useful representation of videos used in human activity recognition performed on datasets such as KTH, UCF101 and Ball-Drop. Ball-Drop dataset is a specifically designed dataset for measuring executive functions in children through physically and cognitively demanding tasks. Using features from proposed method instead of baseline methods caused the top-1 classification accuracy to increase by more then 4%. Moreover, ablation study was performed to investigate the contribution of different transformations on downstream task.