First-Person Activity Recognition Based on Three-Stream Deep Features

摘要

In this paper, we present a novel three-stream deep feature fusion technique to recognize interaction-level human activities from a first-person viewpoint. Specifically, the proposed approach distinguishes human motion and camera ego-motion to focus on human's movement. The features of human and camera ego-motion information are extracted from the three-stream architecture. These features are fused by considering a relationship of human action and camera ego-motion. To validate the effectiveness of our approach, we perform experiments on UTKinect-FirstPerson dataset, and achieve state-of-the-art performance.