hexiangquan / LRCN-for-Activity-Recognition

A implemetation of the LRCN in mxnet

##Abstract LRCN is a combination of CNN and RNN

##Installation

1. Download UCF101 dataset
2. ./avi2jpg.sh to split the video of UCF101
3. Download the pretrained model of vgg16
4. python cnn_predict.py to get the pretrained data
5. python train_ucf101.py

##Reference Donahue, J., Hendricks, L. A., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., & Darrell, T. (2014). Long-term recurrent convolutional networks for visual recognition and description. arXiv preprint arXiv:1411.4389.Chicago