Learning Spatiotemporal Features with 3D Convolutional Networks

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.

PDF Abstract ICCV 2015 PDF ICCV 2015 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Dynamic Facial Expression Recognition MAFW C3D WAR 42.25 # 7
UAR 31.17 # 5
Dynamic Facial Expression Recognition MAFW C3D+LSTM WAR 43.76 # 5
UAR 29.75 # 7
Action Recognition Sports-1M C3D Clip Hit@1 46.1 # 4
Video hit@1 61.1 # 8
Video hit@5 85.5 # 8
Action Recognition UCF101 C3D 3-fold Accuracy 82.3 # 78

Results from Other Papers

Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Action Recognition HMDB-51 C3D Average accuracy of 3 splits 51.6 # 74