Learning Spatiotemporal Features With 3D Convolutional ...

Learning Spatiotemporal Features with 3D Convolutional NetworksDu Tran1,2, Lubomir Bourdev1, Rob Fergus1, Lorenzo Torresani2, Manohar Paluri11 Facebook AI Research,2 Dartmouth propose a simple, yet effective approach for spa-tiotemporal feature Learning using deep 3-dimensional con-volutional networks (3D ConvNets) trained on a large scalesupervised video dataset. Our findings are three-fold: 1)3D ConvNets are more suitable for Spatiotemporal featurelearning compared to 2D ConvNets; 2) A homogeneous ar-chitecture with small3 3 3convolution kernels in alllayers is among the best performing architectures for 3 DConvNets; and 3) Our learned Features , namely C3D (Con-volutional 3D), with a simple linear classifier outperformstate-of-the-art methods on 4 different benchmarks and arecomparable with current best methods on the other 2 bench-marks.

2D convolution output 3D convolution output output (a) (b) 2D convolution on multiple frames (c) H W L k k L H k d < L k H k W Figure 1. 2D and 3D convolution operations. a) Applying 2D convolution on an image results in an image. b) Applying 2D convolution on a video volume (multiple frames as multiple channels) also results in an image.

Loading..

Information

Related search queries