
Motion Generation Using 3-Layer-LSTM
CS 231N (Convolutional Neural Networks) / 231A (Computer Vision) Joint Project
Jihee Hwang, Danish Shabbir (2017)
By feeding motion data from joint-annotated videos (JHMDB data set) into a 3-Layer-LSTM (Long-Term Short Memory) Recurrent Neural Network structure, we were able to accurately generate human motion of a certain action given 5 to 10 initial frames of an unseen motion.
Tensorflow was used for modeling the neural network, and Python was the primary language.
Read the poster below for more detailed information.