VideoCaption
Video captioning using LSTM and CNN following the paper sequence to sequence - video to text. This is the Visual Learning project done by Rui Zhang, Yujia Huang and Yu Zhang. Neuraltalk2 from Karpathy is taken as reference.
##Model
As states in the paper, the model can be divided into two parts: encoder and decoder. Encoder and Decoder share the same architecture but: frames are fed into the framework and outputs are ignored during encoding while both frames and words get fed into the framework and output taken as final output during decoding.
