Human activity recognition with deep metric learners.

Martin, Kyle; Wijekoon, Anjana; Wiratunga, Nirmalie

Abstract

Establishing a strong foundation for similarity-based return is a top priority in Case-Based Reasoning (CBR) systems. Deep Metric Learners (DMLs) are a group of neural network architectures which learn to optimise case representations for similarity-based return by training upon multiple cases simultaneously to incorporate relationship knowledge. This is particularly important in the Human Activity Recognition (HAR) domain, where understanding similarity between cases supports aspects such as personalisation and open-ended HAR. In this paper, we perform a short review of three DMLs and compare their performance across three HAR datasets. Our findings support research which indicates DMLs are valuable to improve similarity-based return and indicate that considering more cases simultaneously offers better performance.

Citation

MARTIN, K., WIJEKOON, A. and WIRATUNGA, N. 2019. Human activity recognition with deep metric learners. In Kapetanakis, S. and Borck, H. (eds.) Proceedings of 27th International conference on case-based reasoning workshop (ICCBR-WS19), co-located with the 27th International conference on case-based reasoning (ICCBR19), 8-12 September 2019, Otzenhausen, Germany. CEUR Workshop Proceedings, 2567. Aachen: CEUR-WS [online], pages 8-17. Available from: http://ceur-ws.org/Vol-2567/paper1.pdf

• Conference Name: 27th International conference on case-based reasoning workshop (ICCBR-WS19), co-located with the 27th International conference on case-based reasoning (ICCBR19)
• Conference Location: Otzenhausen, Germany
• Start Date: Sep 8, 2019
• End Date: Sep 12, 2019
• Acceptance Date: Aug 9, 2019
• Online Publication Date: Jan 20, 2020
• Publication Date: Mar 4, 2020
• Deposit Date: Aug 15, 2019
• Publicly Available Date: Aug 15, 2019
• Publisher: CEUR Workshop Proceedings
• Volume: 2567
• Pages: 8-17
• Series Title: CEUR workshop proceedings
• Series ISSN: 1613-0073
• Keywords: Human activity recognition; Deep metric learning; Deep learning; Metric learning; Matching networks
• Public URL: https://rgu-repository.worktribe.com/output/350316
• Publisher URL: http://ceur-ws.org/Vol-2567/paper1.pdf