Boosting the Performance of Deep Approaches through Fusion with Handcrafted Features

Dimitrios Koutrintzes, Eirini Mathe, Eirini Mathe, Evaggelos Spyrou, Evaggelos Spyrou

2022

Abstract

Contemporary human activity recognition approaches are heavily based on deep neural network architectures, since the latter do not require neither significant domain knowledge, nor complex algorithms for feature extraction, while they are able to demonstrate strong performance. Therefore, handcrafted features are nowadays rarely used. In this paper we demonstrate that these features are able to learn complementary representations of input data and are able to boost the performance of deep approaches, i.e., when both deep and handcrafted features are fused. To this goal, we choose an existing set of handcrafted features, extracted from 3D skeletal joints. We compare its performance with two approaches. The first one is based on a visual representation of skeletal data, while the second is a rank pooling approach on raw RGB data. We show that when fusing both types of features, the overall performance is significantly increased. We evaluate our approach using a publicly available, challenging dataset of human activities.

Paper Citation

in Harvard Style

Koutrintzes D., Mathe E. and Spyrou E. (2022). Boosting the Performance of Deep Approaches through Fusion with Handcrafted Features. In Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-549-4, pages 370-377. DOI: 10.5220/0010982700003122

in Bibtex Style

@conference{icpram22,
author={Dimitrios Koutrintzes and Eirini Mathe and Evaggelos Spyrou},
title={Boosting the Performance of Deep Approaches through Fusion with Handcrafted Features},
booktitle={Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2022},
pages={370-377},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010982700003122},
isbn={978-989-758-549-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Boosting the Performance of Deep Approaches through Fusion with Handcrafted Features
SN - 978-989-758-549-4
AU - Koutrintzes D.
AU - Mathe E.
AU - Spyrou E.
PY - 2022
SP - 370
EP - 377
DO - 10.5220/0010982700003122