Xin Liu is an Associate Professor in the Computational Engineering Department at the Lappeenranta-Lahti University of Technology LUT, Finland. He received his Ph.D. degree in Computer Science from University of Oulu, Finland in 2019, and Information and Communication Engineering from Xi'an Jiaotong University, China in 2016. His major research interests include machine learning and computer vision for social signal processing for emotion AI applications, human behavior analysis (body gestures, actions, facial expression), foreground detection, and image restoration (denoising, deblurring, super-resolution).
Xin Liu was a Endeavour Research Fellow at the University of Sydney, Australia, worked with Professor Dacheng Tao. He also worked with Professor Stefanos Zafeiriou at the Imperial College London, United Kingdom. He was an Academy of Finland postdoc fellow worked with Professor Guoying Zhao and Professor Matti Pietikainen at CMVS group at University of Oulu, Finland. Dr. Liu has been awarded and funded by the Academy of Finland, Finnish Foundation for Technology Promotion (TES), Nokia Foundation, KAUTE Foundation, Otto A. Malm Foundation, Tauno Tonning Foundation, and Riitta Ja Jorma J. Takanen Foundation for his research excellence on computer vision and artificial intelligence. He was the winner of the Endeavour Research Fellowship by Australian Government Department of Education and Training. Xin Liu is a senior member of IEEE, and a member of ACM, SPIE, ELLIS, and APA.
Selected publications:
Chao Hao, Zezheng Wang, Yanhua Huang, Ruiwen Xu, Wenzhe Niu, Xin Liu, and Zitong Yu. "Dynamic Collaboration of Multi-Language Models based on Minimal Complete Semantic Units." Empirical Methods in Natural Language Processing (EMNLP). 2025.
Deng Li, Bohao Xing, Xin Liu, Baiqiang Xia, Bihan Wen, and Heikki Kälviäinen. "DEEMO: De-identity Multimodal Emotion Recognition and Reasoning." ACM International Conference on Multimedia (ACMMM), 2025.
Zhuozhao Hu, Kaishen Yuan, Xin Liu, Zitong Yu, Yuan Zong, Jingang Shi, Huanjing Yue, and Jingyu Yang. "FEALLM: Advancing Facial Emotion Analysis in Multimodal Large Language Models with Emotional Synergy and Reasoning."ACM International Conference on Multimedia (ACMMM), 2025.
Shuyang chu, Jingang Shi, Xu Cheng, Haoyu Chen, Xin Liu, Xu Jian, and Guoying Zhao. "To Remember, To Adapt, To Preempt: A Stable Continual Test-Time Adaptation Framework for Remote Physiological Measurement in Dynamic Domain Shifts." ACM International Conference on Multimedia (ACMMM), 2025.
Jingyi Yang, Xun Lin, Zitong Yu, Liepiao Zhang, Xin Liu, Hui Li, Xiaochen Yuan, Xiaochun Cao. “DADM: Dual Alignment of Domain and Modality for Face Anti-spoofing.” International Conference on Computer Vision (ICCV). 2025
Qilang Ye, Zitong Yu, Rui Shao, Yawen Cui, Xiangui Kang, Xin Liu, Philip Torr, and Xiaochun Cao. "CAT+: Investigating and Enhancing Audio-visual Understanding in Large Language Models." IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI). 2025
Rong Gao, Xin Liu, Zhuozhao Hu, Bohao Xing, Baiqiang Xia, Zitong Yu, and Heikki Kälviäinen. “FSBench: A Figure Skating Benchmark for Advancing Artistic Sports Understanding.” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2025.
Yuting Zhang, Hao Lu, Qingyong Hu, Yin Wang, Kaishen Yuan, Xin Liu, and Kaishun Wu. “Period-LLM: Extending the Periodic Capability of Multimodal Large Language Model.” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2025.
Cong Cao, Huanjing Yue, Xin Liu, and Jingyu Yang, “Zero-shot Video Restoration and Enhancement Using Pre-Trained Image Diffusion Model.” AAAI Conference on Artificial Intelligence (AAAI). 2025.
Xinxu Ge, Xin Liu, Zitong Yu, Jingang Shi, Chun Qi, Jie Li, and Heikki Kälviäinen. “DiffFAS: Face Anti-Spoofing via Generative Diffusion Models.” European Conference on Computer Vision (ECCV). 2024.
Kaishen Yuan, Zitong Yu, Xin Liu, Weicheng Xie, Huanjing Yue, and Jingyu Yang. “AUFormer: Vision Transformers are Parameter-Efficient Facial Action Unit Detectors.” European Conference on Computer Vision (ECCV). 2024.
Zitong Yu, Rizhao Cai, Yawen Cui, Xin Liu, Yongjian Hu, and Alex C. Kot. “Rethinking Vision Transformer and Masked Autoencoder in Multimodal Face Anti-Spoofing.” International Journal of Computer Vision (IJCV). 2024.
Huanjing Yue, Yijia Cheng, Xin Liu, and Jingyu Yang. “Recaptured Raw Screen Image and Video Demoiréing via Channel and Spatial Modulations”. Neural Information Processing Systems (NeurIPS). 2023.
Haoyu Chen, Henglin Shi, Xin Liu, Xiaobai Li, and Guoying Zhao. “SMG: A Micro-Gesture Dataset Towards Spontaneous Body Gestures for Emotional Stress State Analysis.” International Journal of Computer Vision (IJCV). 2023.
Xin Liu, Henglin Shi, Haoyu Chen, Zitong Yu, Xiaobai Li, and Guoying Zhao. “iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis.” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2021.
[08.2025] Invited to be a Senior Program Committee of AAAI 2026 AI Alignment Track
[08.2025] One paper on Dynamic Collaboration of Multi-Language Models is accepted by EMNLP 2025
[07.2025] Three papers on MLLM for de-identity body and facial emotion understanding, and rPPG are accepted by ACMMM 2025
[06.2025] One paper on face anti-spoofing is accepted by ICCV 2025
[06.2025] One paper on Audio-visual Understanding with MLLM is accepted by IEEE T-PAMI
[05.2025] One paper on rPPG via Integration of Explicit and Implicit Prior Knowledge is accepted by IEEE T-IP
[04.2025] We are organizing the Multimodal Emotion Recognition Challenge and Workshop with ACMMM 2025
[03.2025] We are organizing the Subtle Visual Computing Workshop & 1st Multimodal Deception Detection Competition with ACMMM 2025
[02.2025] Two papers on Artistic Sports Understanding and Periodic Capability of Multimodal Large Language Model are accepted by CVPR 2025
[01.2025] One paper on Vision Transformer for Camouflaged Object and Salient Object Detection is accepted by IEEE T-IP
[12.2024] One paper on Zero-shot Video Restoration and Enhancement is accepted by AAAI 2025
[10.2024] Became a member of the ELLIS Society and ELLIS Unit Helsinki
[09.2024] One paper on Self-adjusting Correlation Learning for Facial Action Unit Detection is accepted by IEEE T-AFFC
[09.2024] Become an Editorial Board Member of journal Computing and Artificial Intelligence
[07.2024] One paper on Action Anticipation is accepted by ACM TOMM
[06.2024] Two papes on Facial Action Unit Detection and Face Anti-spoofing are accepted by ECCV 2024
[05.2024] We are organizing the IJCB 2024 Special Session of Multimodal Human Behavior Understanding and Generation (MUG), welcome to submit
[03.2024] One paper on Multimodal Face Anti-spoofing is accepted by IJCV
[01.2024] One paper on Self-supervised Facial rPPG is accepted by IEEE T-MM
[12.2023] One paper on Multi-Channel Fused Lasso for Motion Detection is accepted by IEEE T-CE
[09.2023] One paper on Video Demoiréing via Channel and Spatial Modulations is accepted by NeurIPS 2023
[06.2023] One paper on HDR Image and Video Tone Mapping is accepted by IEEE T-CSVT
[04.2023] We are organizing the 1st Workshop & Challenge on Micro-gesture Analysis for Hidden Emotion Understanding with IJCAI 2023
[03.2023] We are organizing a Special Issue Application of Affective Computing on Applied Sciences, welcome to submit
[02.2023] Promoted to IEEE Senior Member