Joint Learning of Social Groups, Individuals Action and Sub-group Activities in Videos

TL;DR

This paper introduces an end-to-end framework that simultaneously identifies social groups, individual actions, and group activities in videos, advancing understanding of complex social interactions.

Contribution

It proposes a novel trainable model for social grouping and activity recognition, achieving state-of-the-art results and extending existing datasets with new annotations.

Findings

State-of-the-art performance on social activity benchmarks

Effective social grouping and action prediction in videos

Enhanced dataset annotations for social activity analysis

Abstract

The state-of-the art solutions for human activity understanding from a video stream formulate the task as a spatio-temporal problem which requires joint localization of all individuals in the scene and classification of their actions or group activity over time. Who is interacting with whom, e.g. not everyone in a queue is interacting with each other, is often not predicted. There are scenarios where people are best to be split into sub-groups, which we call social groups, and each social group may be engaged in a different social activity. In this paper, we solve the problem of simultaneously grouping people by their social interactions, predicting their individual actions and the social activity of each social group, which we call the social task. Our main contributions are: i) we propose an end-to-end trainable framework for the social task; ii) our proposed method also sets the state-of-the-art results on two widely adopted benchmarks for the traditional group activity recognition task (assuming individuals of the scene form a single group and predicting a single group activity label for the scene); iii) we introduce new annotations on an existing group activity dataset, re-purposing it for the social task.