Deep Structured Models For Group Activity Recognition
This work addresses activity recognition for surveillance applications, but it is incremental as it builds on existing deep learning and graphical model techniques.
The paper tackled group activity recognition in surveillance scenes by combining deep networks for individual action recognition with a neural-network-based hierarchical graphical model to refine predictions through class dependencies, resulting in improved recognition rates over baseline methods.
This paper presents a deep neural-network-based hierarchical graphical model for individual and group activity recognition in surveillance scenes. Deep networks are used to recognize the actions of individual people in a scene. Next, a neural-network-based hierarchical graphical model refines the predicted labels for each class by considering dependencies between the classes. This refinement step mimics a message-passing step similar to inference in a probabilistic graphical model. We show that this approach can be effective in group activity recognition, with the deep graphical model improving recognition rates over baseline methods.