Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points

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.

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Action Recognition NTU RGB+D Glimpse Clouds (RGB only) Accuracy (CS) 86.6 # 20
Accuracy (CV) 93.2 # 16
Skeleton Based Action Recognition N-UCLA Glimpse Clouds Accuracy 87.6% # 19

Methods


No methods listed for this paper. Add relevant methods here