论文阅读12.09: Spatial Temporal Recognition Jan 4, 2019 Algorithm 前言 P3D Deformable Convolutional Networks 前言 P3D 本文的关键是将\(3 \times 3 \times 3\)卷积解耦为\(1 \times 3 \times 3\)卷积和\(3 \times 1 \times 1\) 卷积。 Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks Deformable Convolutional Networks Please enable JavaScript to view the comments powered by Disqus.
