Human Activity Recognition Using Robust Adaptive Privileged Probabilistic Learning

TL;DR

This paper introduces HCRF+ a probabilistic model that leverages privileged information and robustness techniques for improved human activity recognition, especially in the presence of missing data and noise.

Contribution

It presents a novel HCRF+ model integrating privileged information with robustness to outliers, trained via maximum likelihood or margin methods, and automatically estimates regularization parameters.

Findings

Effective on four challenging datasets

Outperforms state-of-the-art in LUPI-based recognition

Works with both handcrafted and CNN features

Abstract

In this work, a novel method based on the learning using privileged information (LUPI) paradigm for recognizing complex human activities is proposed that handles missing information during testing. We present a supervised probabilistic approach that integrates LUPI into a hidden conditional random field (HCRF) model. The proposed model is called HCRF+ and may be trained using both maximum likelihood and maximum margin approaches. It employs a self-training technique for automatic estimation of the regularization parameters of the objective functions. Moreover, the method provides robustness to outliers (such as noise or missing data) by modeling the conditional distribution of the privileged information by a Student's \textit{t}-density function, which is naturally integrated into the HCRF+ framework. Different forms of privileged information were investigated. The proposed method was evaluated using four challenging publicly available datasets and the experimental results demonstrate its effectiveness with respect to the-state-of-the-art in the LUPI framework using both hand-crafted features and features extracted from a convolutional neural network.