Data augmentation by separating identity and emotion representations for emotional gait recognition

Abstract

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.

Emotion Recognition in Learning Scenes Supported by Smart Classroom and Its Application

“…In today's society, student-centered teaching methods are becoming mainstream, and personalized and contextualized learning are receiving increasing attention [1][2][3][4][5]. Therefore, it is necessary for teachers to understand and adjust students' learning emotions in a timely manner to achieve optimal learning outcomes [6][7][8][9][10][11]. The smart classroom is an important product of new education technology, which uses the latest computer, communication, and Internet technologies to achieve deep perception, intelligent analysis, and accurate delivery of the education process [12][13][14][15][16][17].…”