C3D Model for Keras trained over Sports 1M

Resource Type | Date |
---|---|
Software | 2016-04-07 |
Description
Author: Alberto Montes
Advisors: Xavier Giro and Amaia Salvador
We provide an adaptation to Keras of the C3D model used with a fork of Caffe, which was trained over the Sports1M dataset.
Details about the network architecture can be found in the following paper:
Tran, Du, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. "Learning Spatiotemporal Features With 3D Convolutional Networks." In Proceedings of the IEEE International Conference on Computer Vision, pp. 4489-4497. 2015.
Find our model and an example of how to use on this page on Github Gist.
People involved
Xavier Giró | Associate Professor |
Amaia Salvador | PhD Candidate |