Structural Recurrent Neural Network (SRNN) for Group Activity Analysis

TL;DR

This paper introduces a novel SRNN architecture that models individual actions, interactions, and group activity in dynamic groups, using grid pooling to handle varying group sizes, and demonstrates its effectiveness on volleyball data.

Contribution

The paper presents a new SRNN model with grid pooling for variable group sizes, advancing group activity analysis in complex scenarios.

Findings

Effective modeling of individual and group actions

Handles varying group sizes with grid pooling

Validated on Volleyball Dataset

Abstract

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.