Temporal Feature Alignment in Contrastive Self-Supervised Learning for Human Activity Recognition

B. Khaertdinov*, S. Asteriadis

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingAcademicpeer-review

Abstract

Automated Human Activity Recognition has long been a problem of great interest in human-centered and ubiquitous computing. In the last years, a plethora of supervised learning algorithms based on deep neural networks has been suggested to address this problem using various modalities. While every modality has its own limitations, there is one common challenge. Namely, supervised learning requires vast amounts of annotated data which is practically hard to collect. In this paper, we benefit from the self-supervised learning paradigm (SSL) that is typically used to learn deep feature representations from unlabeled data. Moreover, we upgrade a contrastive SSL framework, namely SimCLR, widely used in various applications by introducing a temporal feature alignment procedure for Human Activity Recognition. Specifically, we propose integrating a dynamic time warping (DTW) algorithm in a latent space to force features to be aligned in a temporal dimension. Extensive experiments have been conducted for the unimodal scenario with inertial modality as well as in multimodal settings using inertial and skeleton data. According to the obtained results, the proposed approach has a great potential in learning robust feature representations compared to the recent SSL baselines, and clearly outperforms supervised models in semi-supervised learning. The code for this paper is available via the following link: https://github.com/bulatkh/csshar_tfa.
Original languageEnglish
Title of host publication2022 IEEE INTERNATIONAL JOINT CONFERENCE ON BIOMETRICS (IJCB)
PublisherIEEE
Number of pages9
ISBN (Print)9781665463942
DOIs
Publication statusPublished - 2022
EventIEEE International Joint Conference on Biometrics (IJCB) - Abu Dhabi, United Arab Emirates
Duration: 10 Oct 202213 Oct 2022
https://ijcb2022.org/#/

Conference

ConferenceIEEE International Joint Conference on Biometrics (IJCB)
Abbreviated titleIJCB 2022
Country/TerritoryUnited Arab Emirates
CityAbu Dhabi
Period10/10/2213/10/22
Internet address

Fingerprint

Dive into the research topics of 'Temporal Feature Alignment in Contrastive Self-Supervised Learning for Human Activity Recognition'. Together they form a unique fingerprint.

Cite this