ViT-ReT: Vision and Recurrent Transformer Neural Networks for Human Activity Recognition in Videos
This work addresses the need for faster and more scalable activity recognition systems for applications like sports highlights and surveillance, though it appears to be an incremental improvement over existing transformer adaptations.
The paper tackles human activity recognition in videos by proposing two transformer neural networks (ViT and ReT) to replace traditional CNN-RNN combinations, achieving improved speed and scalability while maintaining competitive accuracy compared to contemporary models.
Human activity recognition is an emerging and important area in computer vision which seeks to determine the activity an individual or group of individuals are performing. The applications of this field ranges from generating highlight videos in sports, to intelligent surveillance and gesture recognition. Most activity recognition systems rely on a combination of convolutional neural networks (CNNs) to perform feature extraction from the data and recurrent neural networks (RNNs) to determine the time dependent nature of the data. This paper proposes and designs two transformer neural networks for human activity recognition: a recurrent transformer (ReT), a specialized neural network used to make predictions on sequences of data, as well as a vision transformer (ViT), a transformer optimized for extracting salient features from images, to improve speed and scalability of activity recognition. We have provided an extensive comparison of the proposed transformer neural networks with the contemporary CNN and RNN-based human activity recognition models in terms of speed and accuracy.