Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points

TL;DR

This paper introduces a novel RGB-based human activity recognition method that uses a visual attention module to select interest points without pose information, improving accuracy on large datasets.

Contribution

The proposed approach uniquely employs unstructured glimpse sequences and a set of recurrent workers for motion tracking and activity recognition, outperforming existing methods.

Findings

Outperforms state-of-the-art on NTU RGB+D dataset

Effective use of unstructured interest points for activity recognition

Demonstrates robustness without pose information

Abstract

We propose a method for human activity recognition from RGB data that does not rely on any pose information during test time and does not explicitly calculate pose information internally. Instead, a visual attention module learns to predict glimpse sequences in each frame. These glimpses correspond to interest points in the scene that are relevant to the classified activities. No spatial coherence is forced on the glimpse locations, which gives the module liberty to explore different points at each frame and better optimize the process of scrutinizing visual information. Tracking and sequentially integrating this kind of unstructured data is a challenge, which we address by separating the set of glimpses from a set of recurrent tracking/recognition workers. These workers receive glimpses, jointly performing subsequent motion tracking and activity prediction. The glimpses are soft-assigned to the workers, optimizing coherence of the assignments in space, time and feature space using an external memory module. No hard decisions are taken, i.e. each glimpse point is assigned to all existing workers, albeit with different importance. Our methods outperform state-of-the-art methods on the largest human activity recognition dataset available to-date; NTU RGB+D Dataset, and on a smaller human action recognition dataset Northwestern-UCLA Multiview Action 3D Dataset. Our code is publicly available at https://github.com/fabienbaradel/glimpse_clouds.