# Action Recognition with 3D Residual Attention and Cross Entropy

## TL;DR

This paper introduces a new 3D network with attention mechanisms for better action recognition in videos.

## Contribution

The novel integration of attention mechanisms into 3D ResNet improves spatiotemporal feature learning for action recognition.

## Key findings

- 3DRFNet achieved 91.7% accuracy on the HMDB-51 dataset.
- The model reached 98.7% accuracy on the UCF-101 dataset.
- Attention mechanisms enhance recognition accuracy and robustness in video analysis.

## Abstract

This study proposes a three-dimensional (3D) residual attention network (3DRFNet) for human activity recognition by learning spatiotemporal representations from motion pictures. Core innovation integrates the attention mechanism into the 3D ResNet framework to emphasize key features and suppress irrelevant ones. In each 3D ResNet block, channel and spatial attention mechanisms generate attention maps for tensor segments, which are then multiplied by the input feature mapping to emphasize key features. Additionally, the integration of Fast Fourier Convolution (FFC) enhances the network’s capability to effectively capture temporal and spatial features. Simultaneously, we used the cross-entropy loss function to describe the difference between the predicted value and GT to guide the model’s backpropagation. Subsequent experimental results have demonstrated that 3DRFNet achieved SOTA performance in human action recognition. 3DRFNet achieved accuracies of 91.7% and 98.7% on the HMDB-51 and UCF-101 datasets, respectively, which highlighted 3DRFNet’s advantages in recognition accuracy and robustness, particularly in effectively capturing key behavioral features in videos using both attention mechanisms.