Action Recognition with Joint Attention on Multi-Level Deep Features

Understand

We propose a novel deep supervised neural network for the task of action recognition in videos, which implicitly takes advantage of visual tracking and shares the robustness of both deep Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN).

• In our method, a multi-branch model is proposed to suppress noise from background jitters.
• Specifically, we firstly extract multi-level deep features from deep CNNs and feed them into 3d-convolutional network.
• After that we feed those feature cubes into our novel joint LSTM module to predict labels and to generate attention regularization.