This is 3-D Convolution (C3D) and video reader implementation in the latest Caffe (as of Feb 2016). The original Facebook C3D implementation is branched out from Caffe on July 17, 2014 with git_id b80fc86, and has not been rebased with the original Caffe hence missing out quite a few new features in the lastest Caffe. I therefore tried to pull in C3D concept and also an accompanying video reader and apply to the latest Caffe. Please reach me for any feedback or question. Thank you.

Check out the original Caffe readme for Caffe-specific information.

Caffe is released under the BSD 2-Clause license.