Structural Recurrent Neural Network (SRNN) for Group Activity Analysis
This work addresses group activity analysis for computer vision applications, but it appears incremental as it builds on prior structural RNNs by adding a grid pooling layer for variable group sizes.
The paper tackles the problem of analyzing group activities at multiple semantic levels by proposing a Structural Recurrent Neural Network (SRNN) that uses interconnected RNNs to capture individual actions, interactions, and group activity, and it addresses variable group sizes with a grid pooling layer, evaluating two variants on the Volleyball Dataset.
A group of persons can be analyzed at various semantic levels such as individual actions, their interactions, and the activity of the entire group. In this paper, we propose a structural recurrent neural network (SRNN) that uses a series of interconnected RNNs to jointly capture the actions of individuals, their interactions, as well as the group activity. While previous structural recurrent neural networks assumed that the number of nodes and edges is constant, we use a grid pooling layer to address the fact that the number of individuals in a group can vary. We evaluate two variants of the structural recurrent neural network on the Volleyball Dataset.