Human action recognition is one of the challenging tasks in computer vision. The current action recognition methods use computationally expensive models for learning spatio-temporal dependencies of the action. Models utilizing RGB channels and optical flow separately, models using a two-stream fusion technique, and models consisting of both convolutional neural network (CNN) and long-short term memory (LSTM) network are few examples of such complex models. Moreover, fine-tuning such complex models is computationally expensive as well. This paper proposes a deep neural network architecture for learning such dependencies consisting of a 3D convolutional layer, fully connected (FC) layers, and attention layer, which is simpler to implement and gives a competitive performance on the UCF-101 dataset. The proposed method first learns spatial and temporal features of actions through 3D-CNN, and then the attention mechanism helps the model to locate attention to essential features for recognition.
@article{arxiv.2206.02203,
title = {3D Convolutional with Attention for Action Recognition},
author = {Labina Shrestha and Shikha Dubey and Farrukh Olimov and Muhammad Aasim Rafique and Moongu Jeon},
journal= {arXiv preprint arXiv:2206.02203},
year = {2022}
}