Data augmentation by separating identity and emotion representations for emotional gait recognition
Robotica · 2023-05 · 41 (5) · 1452-1465
DOI: 10.1017/s0263574722001813 ↗Kurz gefasst
Fachartikel in der Zeitschrift Robotica, online erschienen am 06.02.2023. Verfasst von Weijie Sheng und 2 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 39 Literaturangaben.
Abstract (Originalsprache)
Human-centered intelligent human–robot interaction can transcend the traditional keyboard and mouse and have the capacity to understand human communicative intentions by actively mining implicit human clues (e.g., identity information and emotional information) to meet individuals’ needs. Gait is a unique biometric feature that can provide reliable information to recognize emotions even when viewed from a distance. However, the insufficient amount and diversity of training data annotated with emotions severely hinder the application of gait emotion recognition. In this paper, we propose an adversarial learning framework for emotional gait dataset augmentation, with which a two-stage model can be trained to generate a number of synthetic emotional samples by separating identity and emotion representations from gait trajectories. To our knowledge, this is the first work to realize the mutual transformation between natural gait and emotional gait. Experimental results reveal that the synthetic gait samples generated by the proposed networks are rich in emotional information. As a result, the emotion classifier trained on the augmented dataset is competitive with state-of-the-art gait emotion recognition works.
Zitieren
APA
Sheng, W., Lu, X., & Li, X. (2023). Data augmentation by separating identity and emotion representations for emotional gait recognition. Robotica, 41(5), 1452-1465. https://doi.org/10.1017/s0263574722001813
Vancouver
Sheng W, Lu X, Li X. Data augmentation by separating identity and emotion representations for emotional gait recognition. Robotica. 2023;41(5):1452-1465. doi:10.1017/s0263574722001813
BibTeX
@article{Sheng2023,
author = {Sheng, Weijie and Lu, Xiaoyan and Li, Xinde},
title = {Data augmentation by separating identity and emotion representations for emotional gait recognition},
journal = {Robotica},
year = {2023},
volume = {41},
number = {5},
pages = {1452--1465},
doi = {10.1017/s0263574722001813}
}
EUVIMED