Learning Spatiotemporal Features with 3D Convolutional Networks
Du Tran, Lubomir D. Bourdev, Rob Fergus et al. · IEEE International Conference on Computer Vision (ICCV) · 2015
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.
Cited by 9,555 works. doi:10.1109/iccv.2015.510 Open-access PDF
Authors
References
- ImageNet classification with deep convolutional neural networks
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
- Caffe
- Visualizing and Understanding Convolutional Networks
- Visualizing Data using t-SNE
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
- Two-Stream Convolutional Networks for Action Recognition in Videos
- Large-Scale Video Classification with Convolutional Neural Networks
- PANDA: Pose Aligned Networks for Deep Attribute Modeling