Recurrent Spatiotemporal Feature Learning for Action Recognition
Ze Chen, Hongtao Lu · 2018
Recurrent neural networks (RNNs) like Long Short-term Memory (LSTM) have shown excellent performance for a variety of sequence learning problems on language and speech processing. Previous works leveraging RNNs for action recognition mainly apply LSTM on the top of Convolutional Neural Networks (CNNs), feeding high level semantic feature to RNNs and neglecting to learn spatiotemporal features in video, which makes the models unable to capture complex action patterns and lead to inferior performance.