A Unified Approach for Modeling and Recognition of Individual Actions and Group Activities

TL;DR

This paper introduces a unified framework for recognizing both individual actions and group activities in videos by modeling their shared motion features, enabling unsupervised retrieval and recognition without explicit actor segmentation.

Contribution

It proposes a novel unified model that assesses activity similarity and captures inter-person interactions without explicit actor extraction, applicable to various activity recognition tasks.

Findings

Effective recognition of human actions and football plays

Unsupervised video retrieval and activity recognition

No need for explicit actor segmentation

Abstract

Recognizing group activities is challenging due to the difficulties in isolating individual entities, finding the respective roles played by the individuals and representing the complex interactions among the participants. Individual actions and group activities in videos can be represented in a common framework as they share the following common feature: both are composed of a set of low-level features describing motions, e.g., optical flow for each pixel or a trajectory for each feature point, according to a set of composition constraints in both temporal and spatial dimensions. In this paper, we present a unified model to assess the similarity between two given individual or group activities. Our approach avoids explicit extraction of individual actors, identifying and representing the inter-person interactions. With the proposed approach, retrieval from a video database can be performed through Query-by-Example; and activities can be recognized by querying videos containing known activities. The suggested video matching process can be performed in an unsupervised manner. We demonstrate the performance of our approach by recognizing a set of human actions and football plays.