A Spatio-Temporal Attention Convolution Block for Action Recognition
Authors:
Open Access
- 1 November 2020
- conference paper
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1651 (1) , 012193
Abstract
We propose a simple and effective 3D neural network module (STAT) embedded in spatiotemporal attention for action recognition. For a given intermediate feature map, our module sequentially infers the distribution of attention along the two dimensions of space and time, and multiplies it with the current feature map in the form of residual to achieve adaptive generation of the next stage feature map. STAT is a 3D convolution general module combined with attention. It is compatible with any 3D convolution network and can easily replace the 3D convolution kernel. The additional overhead it generates is negligible, and it can be trained end-to-end together with ordinary 3DCNN. By comparing the performance of the currently popular 3D networks on the UCF101 and HMDB51 datasets, experiments show that STAT has certain improvements on most 3D networks, which proves that STAT has a certain universality.Keywords
This publication has 13 references indexed in Scilit:
- Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks2017
- Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset2017
- Large-Scale Video Classification with Convolutional Neural Networks2014
- Visualizing and Understanding Convolutional Networks2014
- Action Recognition with Improved Trajectories2013
- 3D Convolutional Neural Networks for Human Action RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- HMDB: A large video database for human motion recognition2011
- A 3-dimensional sift descriptor and its application to action recognition2007
- Behavior Recognition via Sparse Spatio-Temporal Features2006
- The Dynamic Representation of ScenesVisual Cognition, 2000