# Localized Trajectories for 2D and 3D Action Recognition

## TL;DR

This paper introduces Localized Trajectories, an improved action recognition method that clusters motion trajectories around human joints using RGB-D data, enhancing discriminative power over traditional Dense Trajectories.

## Contribution

It proposes a novel clustering of trajectories around human joints with RGB-D data and extends the approach to 3D, improving action recognition accuracy.

## Key findings

- Localized Trajectories outperform Dense Trajectories in recognition tasks.
- The method effectively incorporates 3D motion information from RGB-D data.
- Extensive experiments validate the approach across five datasets.

## Abstract

The Dense Trajectories concept is one of the most successful approaches in action recognition, suitable for scenarios involving a significant amount of motion. However, due to noise and background motion, many generated trajectories are irrelevant to the actual human activity and can potentially lead to performance degradation. In this paper, we propose Localized Trajectories as an improved version of Dense Trajectories where motion trajectories are clustered around human body joints provided by RGB-D cameras and then encoded by local Bag-of-Words. As a result, the Localized Trajectories concept provides a more discriminative representation of actions as compared to Dense Trajectories. Moreover, we generalize Localized Trajectories to 3D by using the modalities offered by RGB-D cameras. One of the main advantages of using RGB-D data to generate trajectories is that they include radial displacements that are perpendicular to the image plane. Extensive experiments and analysis are carried out on five different datasets.