Action Recognition Using High Temporal Resolution 3D Neural Network Based on Dilated Convolution

Yongyang Xu, Yaxing Feng, Zhong Xie, Mingyu Xie, Wei LuoIEEE Access 2020 · DOI

Abstract

3D Convolution Neural Networks (CNNs), an important deep learning model, has good performance in recognizing actions in videos. When recognizing actions from videos, 3D CNNs usually down-sample in temporal dimension, leading to loss of the temporal information. To obtain more temporal information from the videos, this work proposed a new model based on the Inflated 3D ConvNet (I3D), named as I3D-T. Instead of using down-sample in temporal dimension, the proposed model applied the dilated convolution in temporal dimension to enlarge the receptive field. At the same time, a non-local feature gating block was designed in the model to learn the correlations between different feature maps. The experimental results showed that the proposed I3D-T has the state-of-art performance. Using RGB frames as input, the action recognition accuracies are respectively 95% and 74.8% in public dataset of UCF101 and HMDB-51.
BibTeX
@inproceedings{xu2020action,
  author = {Yongyang Xu and Yaxing Feng and Zhong Xie and Mingyu Xie and Wei Luo},
  title = {{Action Recognition Using High Temporal Resolution 3D Neural Network Based on Dilated Convolution}},
  booktitle = {IEEE Access},
  year = {2020},
  doi = {10.1109/access.2020.3022407},
}

Loading related content...

Figure