Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification
Authors:
Top Cited Papers
- 7 October 2018
- book chapter
- Published by Springer Nature
- p. 318-335
Abstract
No abstract availableKeywords
All Related Versions
This publication has 37 references indexed in Scilit:
- Multi-region Two-Stream R-CNN for Action Detection2016
- Temporal Segment Networks: Towards Good Practices for Deep Action Recognition2016
- Learning to Track for Spatio-Temporal Action Localization2015
- Human Action Recognition Using Factorized Spatio-Temporal Convolutional Networks2015
- Finding action tubes2015
- ActivityNet: A large-scale video benchmark for human activity understanding2015
- Going deeper with convolutions2015
- Large-Scale Video Classification with Convolutional Neural Networks2014
- Seeing the Arrow of Time2014
- Towards Understanding Action Recognition2013