Huiyuan Yang

Assistant Professor
Department of Computer Science
Missouri University of Science & Technology
Rolla, MO, 65401
Email: duhmg@tsn.yae unscramble
Office hours: CS-333, 2:00pm-4:00pm (Th)


Google Scholar

Bio

Huiyuan Yang is an Assistant Professor in the Department of Computer Science at the Missouri S&T. Prior to this role, he was a Postdoctoral Research Associate at Rice University, where he worked with Prof. Akane Sano in both the Computational Wellbeing Group and Scalable Health Labs. He received his PhD in Computer Science from Binghamton Univeristy-SUNY in 2021, where he was advised by Prof.Lijun Yin. He received his Master degree from Chinese Academy of Sciences, Beijing in 2014, and B.E from Wuhan University in 2011.

His work has appeared in top-tier venues including CVPR, ICCV, Transactions on Affective Computing, ACM MM and others. He has been a PC member/reviewer for NeurIPS, ICLR, KDD, IJCAI, AAAI, AISTATS, ACM MM Asia, ACII, FG and others. He is also an active reviewer for journals such as T-AFFC, T-MM, T-CSVT, T-IP, T-PAMI, SIVP, ACM-TOMM, AIHC, IMAGE, IMAVIS, JEI, PR, PRL, MMSJ, NCAA and many others. He has been co-organizer for the 3DFAW-2019 Challenge and workshop (ICCV 2019), AAAI 2022 Workshop on Human Centric Self-supervised Learning (AAAI 2022), and leading organizer for the workshop of towards multimodal wearable signals for stress detection (EMBC 2022). He won an award for Excellence in Research from the department of computer science, Binghamton University 2021, and also Binghamton University Distinguished Dissertation Award (2021). He also co-released several popular multimodal facial datasets, including BU-EEG, 3DFAW, BP4D+ and BP4D++.

News

[11/2023] Missouri S&T will be an (Carnegie Classifications) R1 research institution in fall 2025 [Link].
[09/2023] One paper got accepted by WACV 2023 [preprint].
[08/2023] One paper got accepted by Journal of NeuroImage 2023 [Link].
[07/2023] One paper got accepted by ICCV 2023 [preprint].
[06/2023] One paper got accepted by Journal of Transactions on Affective Computing [Link].
[04/2023] I will join the Department of Computer Science at Missouri University S&T in this Fall as a Tenure-Track Assistant Professor.
[12/2022] Attend the NeurIPS 2022 conference.
[11/2022] Two papers get accepted by the Learning from Time Series for Health Workshop at NeurIPS 2022.
[11/2022] Gave a talk at the AI in Health conference .
[10/2022] Organize a special session of Representation Learning of Wearable Data in ACII 2022
[07/2022] Organize the EMBC 2022 Workshop and Challenging on the Detection of Stress and Mental Health Using Wearable Sensors [ Link].
[03/2022] Organize the AAAI 2022 Workshop on Human Centric Self-supervised Learning (HC-SSL) [Link]

Research Interests:

His research interests lie at the intersection of machine learning and multimodal human-centered data. He utilizes a variety of sensory data, including video, wearable sensors, EHR, fMRI, and human biomedical and behavioral data, to develop models and datasets aimed at understanding human behaviors and activities, health conditions, emotional state and more.
  • Human-centric AI : 3D facial modeling, facial expression/action units recognition, activity recognition, affective computing, health analytics, etc;

  • Multimodal Machine Learning: how to fusion information from multiple modalities (i.e., 2D image, 3D geometric image, thermal image, natural language, physiological signal, etc), improve the performance, and make the model more robust to the uncertainties (i.e., data corruption or missing, malicious attack, etc);

  • Machine Learning in Healthcare: Medical data are highly multimodal, with various data types, scales and styles. We face the challenge of jointly learning from diverse modalities, along with providing interpretable evidence for decision making, hoping to improve the delivery of care to patients through healthcare providers and hospitals.

Selected Publications

2023

Disagreement Matters: Exploring Internal Diversification for Redundant Attention in Generic Facial Action Analysis

IEEE Transactions on Affective Computing
Xiaotian Li, Zheng Zhang, Xiang Zhang, Taoyue Wang, Zhihua Li, Huiyuan Yang, Umur Ciftci,Qiang Ji, Jeffrey Cohn, and Lijun Yin
Paper



Weakly-Supervised Text-driven Contrastive Learning for Facial Behavior Understanding

IEEE/CVF International Conference on Computer Vision (ICCV 2023)
Xiang Zhang, Xiaotian Li, Taoyue Wang, Huiyuan Yang, Lijun Yin
arXiv



Affine image registration of arterial spin labeling MRI using deep learning networks

Journal of NeuroImage (NeuroImage 2023)
Zongpai Zhang, Huiyuan Yang, Yanchen Guo, Nicolas R. Bolo, Matcheri Keshavan, Eve DeRosa, Adam K. Anderson, David. Alsop, Lijun Yin, Weiying Dai
Paper



Multimodal Channel-Mixing: Channel and Spatial Masked AutoEncoder on Facial Action Unit Detection

EEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Xiang Zhang, Huiyuan Yang, Taoyue Wang, Xiaotian Li, Lijun Yin
arXiv



2022

Empirical Evaluation of Data Augmentations for Biobehavioral Time Series Data with Deep Learning

NeurIPS Workshop, 2022
Huiyuan Yang, Han Yu, Akane Sano
Paper arXiv GitHub



More to Less (M2L): Enhanced Health Recognition in the Wild with Reduced Modality of Wearable Sensors

The IEEE Engineering in Medicine and Biology Society(EMBC), 2022
Huiyuan Yang, Han Yu, Kusha Sridhar, Thomas Vaessen, Inez Myin-Germeys, Akane Sano.
arXiv GitHub



2021

Exploiting Semantic Embedding and Visual Feature for Facial Action Unit Detection

the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
Huiyuan Yang, Lijun Yin, Yi Zhou and Jiuxiang Gu.
Paper Supp



Multimodal Learning for Hateful Memes Detection

IEEE International Conference on Multimedia and Expo (ICME) Workshop 2021 (ICME), 2021
Yi Zhou, Zhenhao Chen, Huiyuan Yang.
Paper GitHub



2020

RE-Net:An Relation Embedded Deep Model for Action Unit Detection

Proceedings of the Asian Conference on Computer Vision (ACCV), 2020
Huiyuan Yang and Lijun Yin
Paper



Adaptive Multimodal Fusion for Facial Action Units Recognition

Proceedings of the 28th ACM International Conference on Multimedia (ACM MM), 2020
Huiyuan Yang, Taoyue Wang, Lijun Yin
Paper



Set Operation Aided Network for Action Units Detection

15th IEEE International Conference on Automatic Face and Gesture Recognition (FG), 2020
Huiyuan Yang, Taoyue Wang, Lijun Yin.
Paper



An EEG-Based Multi-Modal Emotion Database with Both Posed and Authentic Facial Actions for Emotion Analysis

15th IEEE International Conference on Automatic Face and Gesture Recognition (FG), 2020
Xiaotian Li, Xiang Zhang,Huiyuan Yang ,Wenna Duan, Weiying Dai, Lijun Yin.
Paper BU-EEG dataset



2019

The 2nd 3D Face Alignment in the Wild Challenge (3DFAW-Video): Dense Reconstruction From Video

IEEE/CVF International Conference on Computer Vision Workshop(ICCVW), 2019
Rohith Pillai, Laszlo Jeni, Huiyuan Yang, Zheng Zhang, Lijun Yin, Jeffrey F Cohn
Paper Project Page





Learning Temporal Information From A Single Image for AU Detection.

14th IEEE International Conference on Automatic Face and Gesture Recognition(FG), 2019 [Oral]
Huiyuan Yang, Lijun Yin
Paper



Multi-modality Empowered Network for Facial Action Unit Detection

2019 IEEE Winter Conference on Applications of Computer Vision (WACV), 2019
Peng Liu, Zheng Zhang, Huiyuan Yang and Lijun Yin
Paper



2018

Facial Expression Recognition by De-expression Residue Learning

the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
Huiyuan Yang, Umur Ciftci and Lijun Yin.
Paper



Identity-Adaptive Facial Expression Recognition Through Expression Regeneration Using Conditional Generative Adversarial Networks

13th IEEE International Conference on Automatic Face and Gesture Recognition (FG), 2018
Huiyuan Yang, Zheng Zhang and Lijun Yin.
Paper





2017

CNN based 3D facial expression recognition using masking and landmark features

Seventh International Conference on Affective Computing and Intelligent Interaction (ACII), 2017
Huiyuan Yang, and Lijun Yin.
Paper



2016

Multimodal spontaneous emotion corpus for human behavior analysis

the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
Zhang Z, Girard JM, Wu Y, Zhang X, Liu P, Ciftci U, Canavan S, Reale M, Horowitz A, Yang H , Cohn JF.
Paper BP4D+ dataset



Research Group

Teaching

Released Datasets

BU-EEG (2020) [Link] An EEG-Based Multi-Modal Emotion Database.
BU-EEG database records both the 128-channel EEG signals and face videos, including posed expressions, facial action units and spontaneous expressions from 29 participants with different ages, genders, ethnic backgrounds. BU-EEG features the correspondence between EEG and individual AU, which is the first of this kind. A total of 2,320 experiment trails were recorded and released to the public.



3DFAW (2019) [Link] 3D Face Alignment in the Wild Challenge

3DFAW dataset contains 3 different components for each of the 70 different subjects: 1) a high resolution 2D video; 2) high resolution 3D ground truth mesh model; 3) unconstrained 2D video from an iPhone. The goal of this dataset is to facilitate the research on 3D face alignment in the wild, and also to be used as benchmark for dense 3D face reconstruction evaluation. The dataset is publicly accessible to the research community.



BP4D+ (2016) [Link] Multimodal Spontaneous Emotion database

P4D+ is a Multimodal Spontaneous Emotion Corpus, which contains multimodal datasets including synchronized 3D, 2D, thermal, physiological data sequences (e.g., heart rate, blood pressure, skin conductance (EDA), and respiration rate), and meta-data (facial features and FACS codes). The dataset was collected from 140 subjects (58 males and 82 females) with diverse age and ethnicity. This results in a dataset with more than 10TB high quality data for the research community.



Award

Activities & Services

Hobbies

You are the visitor.
Last updated: 11/01/2024