Hui Zhang

Hui Zhang

Auto-generated profile, based on publicly available information

Hui Zhang

School of Design, Hunan University, Changsha, Hunan, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

4 August 2021 in IEEE Transactions on Affective Computing
Verified
Journal Article
Closed access
KZKejun Zhang
Kejun Zhang
XWXinda Wu
Xinda Wu
XXXinhang Xie
Xinhang Xie
XZXiaoran Zhang
Xiaoran Zhang
HZHui Zhang
Hui Zhang
LSLingyun Sun
Lingyun Sun
Affective computing and natural human-computer interaction, which would be capable of interpreting and responding intelligently to the social cues of interaction in crowds, are more needed than ever as an individuals affective experience is often related to others in group activities. To develop the next-generation intelligent interactive systems, we require numerous human facial expressions with accurate annotations. However, existing databases usually consider nonspontaneous human behavior (posed or induced), individual or dyadic setting, and a single type of emotion annotation. To address this need, we created the Werewolf-XL database, which contains a total of 890 minutes of spontaneous audio-visual recordings of 129 subjects in a group interaction of nine individuals playing a conversational role-playing game called Werewolf. We provide 131,688 individual utterance-level video clips with internal self-assessment of 18 non-prototypical emotional categories and external assessment of pleasure, arousal, and dominance, including 14,632 speakers' samples and the rest of listeners' samples. Besides, the results of the annotation agreement analysis show fair reliability and validity. Role information and outcomes of the game are also recorded. Furthermore, we provided extensive benchmarks of unimodal and multimodal emotional recognition results. The database is made publicly available.

11 May 2024
Verified
Conference Paper
Open access
HZHui Zhang
Hui Zhang
RZRuixiao Zheng
Ruixiao Zheng
SYShirao Yang
Shirao Yang
WWWanyi Wei
Wanyi Wei
HSHuafeng Shan
Huafeng Shan
JZJianwei Zhang
Jianwei Zhang
Despite the fact that spatio-temporal patterns of vibration, characterized as rhythmic compositions of tactile content, have exhibited an ability to elicit specific emotional responses and enhance the emotion conveyed by music, limited research has explored their underlying mechanism in regulating emotional states within the pre-sleep context. Aiming to investigate whether synergistic spatio-temporal tactile displaying of music can facilitate relaxation before sleep, we developed 16 vibration patterns and an audio-tactile prototype for presenting an ambient experience in a pre-sleep scenario. The stress-reducing effects were further evaluated and compared via a user experiment. The results showed that the spatio-temporal tactile display of music significantly reduced stress and positively influenced users’ emotional states before sleep. Furthermore, our study highlights the therapeutic potential of incorporating quantitative and adjustable spatio-temporal parameters correlated with subjective psychophysical perceptions in the audio-tactile experience for stress management.

7 December 2019 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
HZHui Zhang
Hui Zhang
KZKejun Zhang
Kejun Zhang
YCYingping Cao
Yingping Cao
JZJun Zheng
Jun Zheng
XHXiaoyi Huang
Xiaoyi Huang
LSLingyun Sun
Lingyun Sun

27 January 2025 in International Journal of Human-Computer Studies
Verified
Journal Article
Closed access
SYShirao Yang
Shirao Yang
HZHui Zhang
Hui Zhang
RZRuixiao Zheng
Ruixiao Zheng
ZLZepeng Lin
Zepeng Lin
HSHuafeng Shan
Huafeng Shan
JZJianwei Zhang
Jianwei Zhang

3 August 2020 in arXiv
Verified
Preprint
Open access
PDF file
GYGuanghao Yin
Guanghao Yin
SSShouqian Sun
Shouqian Sun
HZHui Zhang
Hui Zhang
DYDian Yu
Dian Yu
CLChao Li
Chao Li
NZNing Zou
Ning Zou
User independent emotion recognition with large scale physiological signals is a tough problem. There exist many advanced methods but they are conducted under relatively small datasets with dozens of subjects. Here, we propose Res-SIN, a novel end-to-end framework using Electrodermal Activity(EDA) signal images to classify human emotion. We first apply convex optimization-based EDA (cvxEDA) to decompose signals and mine the static and dynamic emotion changes. Then, we transform decomposed signals to images so that they can be effectively processed by CNN frameworks. The Res-SIN combines individual emotion features and external emotion benchmarks to accelerate convergence. We evaluate our approach on the PMEmo dataset, the currently largest emotional dataset containing music and EDA signals. To the best of author's knowledge, our method is the first attempt to classify large scale subject-independent emotion with 7962 pieces of EDA signals from 457 subjects. Experimental results demonstrate the reliability of our model and the binary classification accuracy of 73.65% and 73.43% on arousal and valence dimension can be used as a baseline.