Learning Spatiotemporal Features with 3D Convolutional Networks
Top Cited Papers
- 1 December 2015
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4489-4497
- https://doi.org/10.1109/iccv.2015.510
Abstract
We propose a simple, yet effective approach for spatiotemporal feature learning using deep 3-dimensional convolutional networks (3D ConvNets) trained on a large scale supervised video dataset. Our findings are three-fold: 1) 3D ConvNets are more suitable for spatiotemporal feature learning compared to 2D ConvNets, 2) A homogeneous architecture with small 3x3x3 convolution kernels in all layers is among the best performing architectures for 3D ConvNets, and 3) Our learned features, namely C3D (Convolutional 3D), with a simple linear classifier outperform state-of-the-art methods on 4 different benchmarks and are comparable with current best methods on the other 2 benchmarks. In addition, the features are compact: achieving 52.8% accuracy on UCF101 dataset with only 10 dimensions and also very efficient to compute due to the fast inference of ConvNets. Finally, they are conceptually very simple and easy to train and use.Keywords
Other Versions
This publication has 26 references indexed in Scilit:
- CaffePublished by Association for Computing Machinery (ACM) ,2014
- Large-Scale Video Classification with Convolutional Neural NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Evaluating New Variants of Motion Interchange PatternsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Action bank: A high-level representation of activity in videoPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- 3D Convolutional Neural Networks for Human Action RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Moving vistas: Exploiting motion for describing scenesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Boundary Learning by Optimization with Topological ConstraintsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Convolutional Learning of Spatio-temporal FeaturesLecture Notes in Computer Science, 2010
- A Spatio-Temporal Descriptor Based on 3D-GradientsPublished by British Machine Vision Association and Society for Pattern Recognition ,2008
- A 3-dimensional sift descriptor and its application to action recognitionPublished by Association for Computing Machinery (ACM) ,2007