Biography

Dr. Xin Liu is a Tenured Associate Professor at the School of Psychology, Shanghai Jiao Tong University (2026–present). Prior to this, he served as an Associate Professor at LUT University in Finland (2021–2025) and as an Associate Professor at Tianjin University, China. He continues his affiliation with LUT University as an Adjunct Doctoral Supervisor.

He received dual Ph.D. degrees—one in Computer Science from the University of Oulu, Finland, supervised by Prof. Guoying Zhao, and another in Information and Communication Engineering from Xi'an Jiaotong University, China, supervised by Prof. Chun Qi. His academic journey includes research collaborations with Prof. Dacheng Tao at the University of Sydney as an Endeavour Research Fellow, and with Prof. Stefanos Zafeiriou at Imperial College London. He later returned to the University of Oulu as an Academy of Finland Postdoctoral Fellow, working alongside Prof. Guoying Zhao and Prof. Matti Pietikäinen at the CMVS group.

Dr. Liu's contributions to artificial intelligence have been recognized through numerous grants and awards. He has led multiple research projects funded by the National Natural Science Foundation of China, the Academy of Finland, the Finnish Ministry of Education, and CSC–IT Center for Science. His work has also received support from foundations and industry partners including the Finnish Foundation for Technology Promotion , the Nokia Foundation, the KAUTE Foundation, the Otto A. Malm Foundation, the Tauno Tönning Foundation, and the Riitta and Jorma J. Takanen Foundation. He was also the recipient of the prestigious Endeavour Research Fellowship awarded by the Australian Government. Dr. Liu is a Senior Member of IEEE and an active member of ACM, SPIE, ELLIS, and APA.

His research lies at the intersection of artificial intelligence and psychology, with a focus on developing objective computational methods and tools for emotion understanding and mental health assessment using computer vision and machine learning. His core interests include trustworthy affective computing and human-machine empathy, and he has made innovative contributions to multimodal large language models for emotion analysis, micro-gesture and micro-expression analysis, and remote physiological signal detection. He has published over 80 papers in leading international journals and conferences, including IEEE TPAMI, IJCV, CVPR, and ICLR, and holds more than 20 patents. He currently serves as an Associate Editor for several international journals, including IEEE Transactions on Multimedia.

刘鑫,上海交通大学心理学院长聘副教授,入选上海市海外高层次人才“白玉兰人才计划创新项目”。同时担任芬兰拉彭兰塔-拉赫蒂工业大学(LUT University)兼职博士生导师。2019年获芬兰奥卢大学计算机科学博士学位,师从赵国英教授(欧洲科学院院士,芬兰科学院院士),2016年获西安交通大学信息与通信工程博士学位,师从齐春教授。拥有十余年海外科研与教学经历,曾任芬兰拉彭兰塔-拉赫蒂工业大学副教授,并先后在澳大利亚悉尼大学(陶大程教授课题组)、英国帝国理工学院(Stefanos Zafeiriou教授课题组)及芬兰奥卢大学(赵国英教授和Matti Pietikäinen教授课题组)等机构从事研究工作。

他的研究致力于人工智能与心理学的交叉前沿探索,旨在通过计算机视觉与机器学习技术,为情感理解与心理健康评估提供客观的计算方法与工具。核心研究方向为可信情感智能与人机共情,在情感多模态大模型、微姿态与微表情分析、远程生理信号检测等领域取得系列创新成果。先后主持国家自然科学基金、芬兰科学院、芬兰教育部、芬兰国家IT科学研究中心、澳大利亚教育部等国内外重要科研项目,研究成果获得KAUTE基金会、诺基亚等知名企业及基金会资助。在PAMI、IJCV、CVPR、ICLR等国际顶级期刊和会议上发表论文80余篇,获批专利20余项。目前担任包括中科院一区期刊IEEE Transactions on Multimedia在内的多个国际期刊编委。

News

📌 We are recruiting postdoctoral fellows, visiting scholars, PhD students, master's students, visiting students, and undergraduate students to join the Center for Affective Computing and Intelligent Interaction at Shanghai Jiao Tong University. More info »
  • [03.2026] One paper on Micro-Expression Recognition is accepted by IEEE T-AFFECT
  • [03.2026] One paper on Image Compression via Dual Domain Alignment is accepted by IEEE T-IP
  • [02.2026] Invited to be an Area Chair for ICPR 2026
  • [01.2026] One paper on Evaluating Emotion Hallucinations in MLLMs is accepted by ICLR 2026
  • [01.2026] One paper on Hemoglobin-Assistant Network for rPPG is accepted by IEEE T-CSVT
  • [01.2026] Joined Shanghai Jiao Tong University as a Tenured Associate Professor
  • [12.2025] One paper on Identity-free Micro-Gesture Understanding for Emotion AI is accepted by IEEE T-AFFECT
  • [12.2025] One paper on Facial Action Unit-based Emotion Recognition is accepted by IEEE T-IP
  • [10.2025] I will serve as Associate Editor at IEEE T-MM
  • [10.2025] One paper on Mamba for Micro-Gesture Recognition is accepted by IEEE T-MM

Selected Publications

  • EmotionHallucer: Evaluating Emotion Hallucinations in Multimodal Large Language Models. Bohao Xing, Xin Liu, Guoying Zhao, Chengyu Liu, Xiaolan Fu, and Heikki Kälviäinen. International Conference on Learning Representations (ICLR), 2026.
  • DEEMO: De-identity Multimodal Emotion Recognition and Reasoning. Deng Li, Bohao Xing, Xin Liu, Baiqiang Xia, Bihan Wen, and Heikki Kälviäinen. ACM International Conference on Multimedia (ACMMM), 2025.
  • FEALLM: Advancing Facial Emotion Analysis in Multimodal Large Language Models with Emotional Synergy and Reasoning. Zhuozhao Hu, Kaishen Yuan, Xin Liu, Zitong Yu, Yuan Zong, Jingang Shi, Huanjing Yue, and Jingyu Yang. ACM International Conference on Multimedia (ACMMM), 2025.source code
  • To Remember, To Adapt, To Preempt: A Stable Continual Test-Time Adaptation Framework for Remote Physiological Measurement in Dynamic Domain Shifts. Shuyang chu, Jingang Shi, Xu Cheng, Haoyu Chen, Xin Liu, Xu Jian, and Guoying Zhao. ACM International Conference on Multimedia (ACMMM), 2025.source code
  • DADM: Dual Alignment of Domain and Modality for Face Anti-spoofing. Jingyi Yang, Xun Lin, Zitong Yu, Liepiao Zhang, Xin Liu, Hui Li, Xiaochen Yuan, Xiaochun Cao. International Conference on Computer Vision (ICCV), 2025.source code
  • CAT+: Investigating and Enhancing Audio-visual Understanding in Large Language Models. Qilang Ye, Zitong Yu, Rui Shao, Yawen Cui, Xiangui Kang, Xin Liu, Philip Torr, and Xiaochun Cao. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2025. source code
  • FSBench: A Figure Skating Benchmark for Advancing Artistic Sports Understanding. Rong Gao, Xin Liu, Zhuozhao Hu, Bohao Xing, Baiqiang Xia, Zitong Yu, and Heikki Kälviäinen. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025. project & source code
  • Period-LLM: Extending the Periodic Capability of Multimodal Large Language Model. Yuting Zhang, Hao Lu, Qingyong Hu, Yin Wang, Kaishen Yuan, Xin Liu, and Kaishun Wu. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025. source code
  • Zero-shot Video Restoration and Enhancement Using Pre-Trained Image Diffusion Model. Cong Cao, Huanjing Yue, Xin Liu, and Jingyu Yang. AAAI Conference on Artificial Intelligence (AAAI), 2025. source code
  • DiffFAS: Face Anti-Spoofing via Generative Diffusion Models. Xinxu Ge, Xin Liu, Zitong Yu, Jingang Shi, Chun Qi, Jie Li, and Heikki Kälviäinen. European Conference on Computer Vision (ECCV), 2024. source code
  • AUFormer: Vision Transformers are Parameter-Efficient Facial Action Unit Detectors. Kaishen Yuan, Zitong Yu, Xin Liu, Weicheng Xie, Huanjing Yue, and Jingyu Yang. European Conference on Computer Vision (ECCV), 2024. source code
  • Rethinking Vision Transformer and Masked Autoencoder in Multimodal Face Anti-Spoofing. Zitong Yu, Rizhao Cai, Yawen Cui, Xin Liu, Yongjian Hu, and Alex C. Kot. International Journal of Computer Vision (IJCV), 2024.
  • Recaptured Raw Screen Image and Video Demoiréing via Channel and Spatial Modulations. Huanjing Yue, Yijia Cheng, Xin Liu, and Jingyu Yang. Neural Information Processing Systems (NeurIPS), 2023. source code
  • SMG: A Micro-Gesture Dataset Towards Spontaneous Body Gestures for Emotional Stress State Analysis. Haoyu Chen, Henglin Shi, Xin Liu, Xiaobai Li, and Guoying Zhao. International Journal of Computer Vision (IJCV), 2023.source code
  • iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis. Xin Liu, Henglin Shi, Haoyu Chen, Zitong Yu, Xiaobai Li, and Guoying Zhao. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021. project page