This is an implementation which allows training and testing of temporal embedding models described in: Learning Temporal Embeddings for Complex Video Analysis Vignesh Ramanathan, Kevin Tang, Greg Mori and Li Fei-Fei arXiv:1505.00315 (http://arxiv.org/pdf/1505.00315v1.pdf)

• We provide sample scripts to extract features from a list of image-frames in "projects/videovec_embedding/feature_extraction_pretrained_mednet.sh"

For general questions about Caffe, please refer to the BVLC project website for all documentation.