· 2015
Learning Spatiotemporal Features with 3D Convolutional Networks
- 9,739citations
- 2015year
Short summary
3D Convolutional Networks (3D ConvNets) outperform 2D ConvNets for spatiotemporal feature learning, with a homogeneous architecture using small 3x3x3 kernels achieving top performance.
AI-generated from the title and abstract; the full text is not read.
Key points
- 3D ConvNets are more effective than 2D ConvNets for spatiotemporal feature learning.
- A homogeneous architecture with small 3x3x3 kernels is optimal for 3D ConvNets.
- C3D features achieve state-of-the-art performance on multiple video benchmarks.
- C3D features are compact and efficient, achieving high accuracy with low dimensionality.
AI-generated from the title and abstract; the full text is not read.
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.
The authors' abstract, as published at the source., 2015 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionComputer Science