@inproceedings{ec76c95f3edb48d89dab9bda7dfc64f0,
title = "Contrastive Domain Adaptation: A Self-Supervised Learning Framework for sEMG-Based Gesture Recognition",
abstract = "Gesture recognition using surface electromyography (sEMG) shows its great potential in the field of human-computer interaction (HCI). Previous works achieve relatively good performance based on the assumption of invariant statistic distribution. However, the practical application effect is unsatisfactory due to the problem of domain shift. Existing approaches need plenty of labeled sEMG samples from target scenarios for calibration, which is burdensome for experimenters and users. In this work, we present a contrastive self-supervised learning framework (ConSSL) for sEMG-based gesture recognition to realize domain adaptation in target domains. After pretraining on a bunch of unlabeled samples, only a small number of labeled samples are needed for calibration and domain adaptation. Experimental results indicate that the proposed framework out-performs other approaches even ifleq 50% labeled samples in target scenarios are available and achieves the state-of-the-art.",
author = "Zhiping Lai and Xiaoyang Kang and Hongbo Wang and Xueze Zhang and Weiqi Zhang and Fuhao Wang",
note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE International Joint Conference on Biometrics, IJCB 2022 ; Conference date: 10-10-2022 Through 13-10-2022",
year = "2022",
doi = "10.1109/IJCB54206.2022.10008005",
language = "English (US)",
series = "2022 IEEE International Joint Conference on Biometrics, IJCB 2022",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2022 IEEE International Joint Conference on Biometrics, IJCB 2022",
address = "United States",
}