YUANYUAN LIU
Professor School of Information and Engineering China University of Geosciences (Wuhan) IEEE/CSIG/CAAI/ACM Member CCF Senior Member No. 68 Jincheng Road,Wuhan, P.R. China Postcode: 430074. Google Scholar  dblp Telephone: 86-013349830890 Email: liuyy@cug.edu.cn

Research Area

My research interests fall into the areas of computer vision, emotion computing, image and video understanding, etc. More specifically, I am interested in the following topics:

1. Emotion Computing including facial expression recognition, human-centric emotion analysis, emotion captioning, multimodal emotion recognition
2. Image/Video understanding including scene segmentation, cross-domain object detection, and temporal action localization
3. Deep Learning Methods and Application including open-set learning, zero-shot/few-shot learning, and domain adaptation etc.

Rencent News:

1. Attended ChinaMM 2025, 22 - 24 August 2025 • Weihai, Shandong, China • Awarded Best Student Paper Award



2. Attended the 32nd ACM Multimedia Conference, 28 October - 1 November 2024 • Melbourne, Australia



3. Taking part in Valse 2023, 10-12 June 2023 • WuXi, China



4. Five papers from our group accepted, February 2023 • One accepted by CVPR 2023



5. Presented at ACM Multimedia 2022, 10-14 October 2022 • Lisbon, Portugal



6. Taking part in Valse 2021, 8-10 October 2021 • Hangzhou, China



7. Presentation at ICIP 2021, 19-22 September 2021 • Anchorage, Alaska, USA

Published Datesets:

MAFW
	A large-scale, multi-modal, compound affective database for dynamic facial expression recognition in the wild. Contains 10,045 video clips from global regions (China, Japan, Korea, Europe, America, India) across various themes. Each clip was annotated 11 times by trained annotators, featuring: • 11-dimensional expression distribution vectors • Single/multiple expression labels & bilingual descriptions • 11 single-emotion classes and 32 compound-emotion classes • Automatic annotations (68 facial landmarks, face bounding boxes) Dataset Details： https://mafw-database.github.io/MAFW/

Recent Publications:

2025
	Yuanyuan Liu, Lin Wei, Kejun Liu, Zijing Chen, Zhe Chen*, Chang Tang, Jingying Chen, Shiguang Shan*. "Leveraging Eye Movement for Instructing Robust Video-based Facial Expression Recognition." IEEE Transactions on Affective Computing (2025). [PDF] [DOI: 10.1109/TAFFC.2025.3599859] [Code (GitHub)]
	Ke Wang, Yuanyuan Liu*, Chang Tang, Kun Sun, Yibing Zhan, Zhe Chen. "Degradation-adaptive attack-robust self-supervised facial representation learning." Neurocomputing 655: 131356 (2025). [PDF] [DOI: 10.1016/j.neucom.2025.131356] [Code (GitHub)]
	Kejun Liu, Xuesong Yan, Yuanyuan Liu*, Chang Tang, Yibing Zhan, Wei Luo, Wujie Zhou, Hongyan Zhang. "PMTSeg: Prompt-Driven Multimodal Transformer for Task-Adapted Remote Sensing Image Segmentation." IEEE Transactions on Geoscience and Remote Sensing 63: 1-15 (2025) [PDF] [DOI:10.1109/TGRS.2025.3586620]
	Yu Wang, Yuanyuan Liu*, Shunping Zhou, Yuxuan Huang, Chang Tang, Wujie Zhou, Zhe Chen. "Emotion-oriented Cross-modal Prompting and Alignment for Human-centric Emotional Video Captioning." IEEE Transactions on Multimedia 27: 3766-3780 (2025). [PDF] [DOI: 10.1109/TMM.2025.3535292] [Code (GitHub)]
	刘袁缘, 刘树阳, 刘云娇, 袁雨晨, 唐厂, 罗威. 提示学习在计算机视觉中的分类、应用及展望. 自动化学报, 2025, 51(5): 1021−1040 [PDF] [DOI: 10.16383/j.aas.c240177]
	Yuanyuan Liu, Ning Zhou, Yuxuan Huang, Shuyang Liu, Leyuan Liu, Wujie Zhou, Chang Tang, Ke Wang*. "Beyond boundaries: Hierarchical-contrast unsupervised temporal action localization with high-coupling feature learning.Pattern Recognition 162: 111421 (2025) [PDF] [DOI: 10.1016/j.patcog.2025.111421] [Code (GitHub)]
	Yuanyuan Liu, Shaoze Feng, Shuyang Liu, Yibing Zhan, Dapeng Tao, Zijing Chen, Zhe Chen*. "Sample-Cohesive Pose-Aware Contrastive Facial Representation Learning." International Journal of Computer Vision 133(6): 3727-3745 (2025). [PDF] [DOI: 10.1007/s11263-025-02348-z] [Code (GitHub)]
	Yuanyuan Liu, Haoyu Zhang*, Yibing Zhan, Zijing Chen, Guanghao Yin, Lin Wei, Zhe Chen. "Noise-Resistant Multimodal Transformer for Emotion Recognition." International Journal of Computer Vision 133(5): 3020-3040 (2025). [PDF] [DOI: 10.1007/s11263-024-02304-3]
	Lin Wei, Yuanyuan Liu*, Kejun Liu, Yuxuan Huang, Shaozhe Feng. "Emotion-Aware Text Generation for Instructing Audio-Visual Emotion Recognition." IEEE IJCNN. (2025).
2024
	Guanghao Yin, Yuanyuan Liu*, Tengfei Liu, Haoyu Zhang, Fang Fang, Chang Tang, Liangxiao Jiang. "Token-disentangling Mutual Transformer for Multimodal Emotion Recognition." Engineering Applications of Artificial Intelligence, Volume 133, Part D, July 2024, Page 108348. [PDF] [DOI: 10.1016/j.engappai.2024.108348] [Code (GitHub)]
	Fayong Zhang, Kejun Liu, Yuanyuan Liu*, Chaofan Wang, Wujie Zhou, Hongyan Zhang, Lizhe Wang. "Multi-target Domain Adaptation Building Instance Extraction of Remote Sensing Imagery with Domain-common Approximation Learning." IEEE Transactions on Geoscience and Remote Sensing 62: 1-16 (2024). [PDF] [DOI: 10.1109/TGRS.2024.3376719] [Code (GitHub)]
	刘袁缘, 王超凡, 王文斌, 张浩宇, 罗忠文*. 面向多种天气场景下目标检测的多域动态平均教师模型. 计算机辅助设计与图形学学报, 2024, 36(3): 388-398. [PDF] [DOI: 10.3724/SP.J.1089.2024.19820]
	Yuanyuan Liu, Yuxuan Huang*, Shuyang Liu, Yibing Zhan, Zijing Chen, Zhe Chen. "Open-Set Video-based Facial Expression Recognition with Human Expression-sensitive Prompting." In Proceedings of the 32nd ACM International Conference on Multimedia (ACM MM 2024), Melbourne, Australia, October 2024. [PDF] [Code (GitHub)] [Supplementary]
2023
	Yuanyuan Liu, Ning Zhou, Fayong Zhang, Wenbin Wang, Yu Wang, Kejun Liu, Ziyuan Liu. "APSL: Action-positive Separation Learning for Unsupervised Temporal Action Localization." Information Sciences, Volume 630, 2023, Pages 206-221. [PDF] [DOI: 10.1016/j.ins.2023.02.047] [Code (GitHub)]
	Yuanyuan Liu, Wenbin Wang, Chuanxu Feng, Haoyu Zhang, Zhe Chen, Yibing Zhan. "Expression Snippet Transformer for Robust Video-based Facial Expression Recognition." Pattern Recognition, Volume 138, 2023, Page 109368. [PDF] [DOI: 10.1016/j.patcog.2023.109368] [Code (GitHub)]
	Yuanyuan Liu, Wenbin Wang, Yibing Zhan, Shaoze Feng, Kejun Liu, Zhe Chen. "Pose-disentangled Contrastive Learning for Self-supervised Facial Representation." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), Vancouver, Canada, June 2023. [PDF]
	Haoyu Zhang, Yu Wang, Guanghao Yin, Kejun Liu, Yuanyuan Liu, Tianshu Yu*. EMNLP 2023: 756-767. [PDF]
2022
	Yu Wang, Shunping Zhou, Yuanyuan Liu*, Kunpeng Wang, Fang Fang, Haoyue Qian. "ConGNN: Context-consistent Cross-graph Neural Network for Group Emotion Recognition in the Wild." Information Sciences 610: 707-724 (2022). [PDF] [DOI: 10.1016/j.ins.2022.08.003] [Code (GitHub)] [SiteGroEmo Dataset] Note: The data are passcode protected. Please download and send the signed [EULA] to qianying@cug.edu.cn for access request.
	Yuanyuan Liu, Chuanxu Feng, Xiaohui Yuan*, Lin Zhou, Wenbin Wang, Jie Qin, Zhongwen Luo. "Clip-aware Expressive Feature Learning for Video-based Facial Expression Recognition." Information Sciences 598: 182-195 (2022). [PDF] [DOI: 10.1016/j.ins.2022.03.062] [Code (GitHub)]
	Yuanyuan Liu, Wei Dai, Chuanxu Feng, Wenbin Wang, Guanghao Yin, Jiabei Zeng, Shiguang Shan*. "MAFW: A Large-scale, Multi-modal, Compound Affective Database for Dynamic Facial Expression Recognition in the Wild." In Proceedings of the 30th ACM International Conference on Multimedia (ACM MM 2022) (Oral Presentation), Lisbon, Portugal, October 2022. [PDF] [MAFW Database URL] [Supplementary]
2021
	Yuanyuan Liu, Wei Dai, Fang Fang, Yongquan Chen*, Rui Huang, et al. "Dynamic Multi-channel Metric Network for Joint Pose-aware and Identity-invariant Facial Expression Recognition." Information Sciences, Volume 578, 2021. [PDF] [DOI: 10.1016/j.ins.2021.07.034]
	Yuanyuan Liu, Wenbin Wang, Fang Fang, Lin Zhou, Chenxing Sun, Ying Zheng, Zhanlong Chen*. "CscGAN: Conditional Scale-Consistent Generation Network for Multi-Level Remote Sensing Image to Map Translation." Remote Sensing, Volume 13, No. 10, 2021, Page 1936. [PDF] [DOI: 10.3390/rs13101936]
	Yuanyuan Liu, Jiyao Peng, Jing-Hao Xue, Yongquan Chen, Zhang-Hua Fu. "TSingNet: Scale-aware and Context-rich Feature Learning for Traffic Sign Detection and Recognition in the Wild." Neurocomputing, Volume 447, Issue 4, 2021. [pdf] [doi] [Code (Baidu Cloud, Password: code)] [Code (GitHub)]
	Yuanyuan Liu, Ziyang Liu, Fang Fang*, Zhanghua Fu, Zhanlong Chen. "Hierarchical Domain-Consistent Network for Cross-Domain Object Detection." In Proceedings of the IEEE International Conference on Image Processing (ICIP 2021), Anchorage, Alaska, USA, September 2021. [PDF]
2020
	Yuanyuan Liu, Dingyuan Chen*, Ailong Ma*, Yanfei Zhong, Fang Fang, Kai Xu. "A Multi-Scale U-Shaped CNN Building Instance Extraction Framework With Edge Constraint for High Spatial Resolution Remote Sensing Imagery." IEEE Transactions on Geoscience and Remote Sensing, 2020, DOI: 10.1109/TGRS.2020.3022410. [PDF]
2018
	Yuanyuan Liu, Xiaohui Yuan*, Xi Gong, Zhong Xie, Fang Fang, Zhongwen Luo. "Conditional Convolution Neural Network Enhanced Random Forest for Facial Expression Recognition." Pattern Recognition, Volume 84, 2018, Pages 251-261. [PDF] [DOI: 10.1016/j.patcog.2018.07.016]
	Yuanyuan Liu, Jiabei Zeng, Shiguang Shan*, Zuo Zheng. "Multi-Channel Pose-Aware Convolution Neural Networks for Multi-View Facial Expression Recognition." In Proceedings of the 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018), Xi'an, China, May 2018, Pages 458-464. [PDF]

PROFESSIONAL ACTIVITIES:

Academic Appointments

Paper Reviewer

Team Member

Liu Kejun	Wang Ke	Liu Shuyang	Liu Yunjiao	Yuan Yuchen	Qian Ying
Xu Lei	Zhou Qiyin	Ke Lv	Zhang Jiahao	Xia Yuyang	Peng Jiyao（guaduated）
Dai Wei（guaduated）	Wang Yu（guaduated）	Liu Ziyang（guaduated）	Wang Kunpeng（guaduated）	Feng Chuanxu（guaduated）	Wang Wenbin（guaduated）
Zhang Haoyu（guaduated）	Wang Chaofan（guaduated）	Zhou Ning（guaduated）	Yin Guanghao（guaduated）	Li Kanglin（guaduated）	Zhao Yaowu（guaduated）
Feng Shaoze（guaduated）	Huang Yuxuan（guaduated）	Wei Lin（guaduated）

WEBSITE VISITING STATISTICS