Action Recognition with Non-Uniform Key Frame Selector
Open Access
- 13 January 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 24-28
Abstract
Current approaches for spatiotemporal action recognition have achieved impressive progress, especially in temporal information processing. Meanwhile, the power of spatial information may be underestimated. Thus, a non-uniform key frame selector is proposed to pick the most representative frames according to the relationship between frames along the temporal dimension. Specifically, the reweight high-level frame features are used to generate an importance score sequence, while the key frames, in each temporal section, are selected based on the above scores. Such selected frames have richer semantic information, which has positive impact on the network training. The proposed model is evaluated on two action recognition, namely datasets HMDB51 and UCF101, and promising accuracy improvement is achieved.Keywords
This publication has 22 references indexed in Scilit:
- Temporal Segment Networks: Towards Good Practices for Deep Action Recognition2016
- Learning Spatiotemporal Features with 3D Convolutional Networks2015
- Going deeper with convolutions2015
- Action Recognition with Improved Trajectories2013
- Dense Trajectories and Motion Boundary Descriptors for Action RecognitionInternational Journal of Computer Vision, 2013
- Intelligent multi-camera video surveillance: A reviewPattern Recognition Letters, 2013
- 3D Convolutional Neural Networks for Human Action RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- A Spatio-Temporal Descriptor Based on 3D-Gradients2008
- Behavior Recognition via Sparse Spatio-Temporal Features2006
- Motion illusions as optimal perceptsNature Neuroscience, 2002