Video‐based action recognition using spurious‐3D residual attention networks
Abstract Recently, 3D Convolutional Neural Networks (3D CNNs) have attracted extensive attention in extracting spatial and temporal features in videos for their efficient feature extraction ability. However, it also brings enormous model parameters by training very deep 3D CNNs. Here, a novel networ...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-09-01
|
| Series: | IET Image Processing |
| Online Access: | https://doi.org/10.1049/ipr2.12541 |