MIR第2期已于4月正式出版，本期12篇好文均来自"微视觉计算"特约专题，欢迎阅读！

Special Issue

Vol. 23, No.2

Editorial节选：

微视觉信号虽常为人眼所难以察觉，却蕴含着隐晦却至关重要的信息，能够揭示视觉数据中潜藏的规律。对微信号的检测与分析能力，在诸多领域均具有深远意义，例如：1) 医学领域：尽早识别医学影像中的微小异常，可实现挽救生命的早期干预；2) 工业领域：发现生产线上的微小缺陷，能够避免造成高昂损失的故障发生；3) 情感计算领域：在人机交互场景中解析微表情、微动作及隐藏的生理信号，有助于开展测谎研究。检测并解码这类“微视觉信号”的能力，为预判趋势、识别新兴威胁与发掘新机遇提供了一种新颖且高效的方法。

本专题旨在研发创新的表征学习模型，专门用于捕捉与解读微视觉信号。我们征集了探讨理论基础、算法创新与新型应用的相关研究成果。最终，专题共收录12篇论文，每篇均通过强化视觉、音频及各类成像传感器模态间的感知与交互，推动了微视觉计算领域的发展，为测谎、微手势识别、人脸反欺诈、远程生理测量及尘肺病诊断等应用提供了决策支持。

专题客座编委：

余梓彤, 大湾区大学, 中国

Sergio Escalera, Universitat de Barcelona and Computer Vision Center, Spain 

范登平, 南开大学, 中国

Björn Schuller, Technische Universität München, Germany & Imperial College London, UK 

Philip H. S. Torr, University of Oxford, UK

专题 · Editorial

Editorial for Special Issue on Subtle Visual Computing

Zitong Yu, Sergio Escalera, Deng-Ping Fan, Björn Schuller, Philip H. S. Torr

https://link.springer.com/article/10.1007/s11633-026-1650-0

https://www.mi-research.net/article/doi/10.1007/s11633-026-1650-0

专题 · 综述

Multimodal Deception Detection: A Survey

Jiayu Zhang, Xun Lin, Jiajian Huang, Shuo Ye, Xiaobao Guo, Dongliang Zhu, Ruimin Hu, Dan Guo, Yanyan Liang, Zitong Yu, Xiaochun Cao

https://link.springer.com/article/10.1007/s11633-025-1625-x

https://www.mi-research.net/article/doi/10.1007/s11633-025-1625-x

专题 · 综述

Micro-gesture Recognition: A Comprehensive Survey of Datasets, Methods, and Challenges

Taorui Wang, Xun Lin, Yong Xu, Qilang Ye, Dan Guo, Sergio Escalera, Ghada Khoriba, Zitong Yu

https://link.springer.com/article/10.1007/s11633-025-1629-x

https://www.mi-research.net/article/doi/10.1007/s11633-025-1629-x

专题 · 研究论文

AI-driven Remote Facial Skin Hydration and TEWL Assessment from Selfie Images: A Systematic Solution

Cecelia Soh, Rizhao Cai, Monalisha Paul, Dennis Sng, Alex Kot

https://link.springer.com/article/10.1007/s11633-025-1577-x

https://www.mi-research.net/article/doi/10.1007/s11633-025-1577-x

专题 · 研究论文

MGMILA: Eulerian Motion-aware MILA for Micro-gesture Recognition

Bohao Xing, Deng Li, Rong Gao, Xin Liu, Heikki Kälviäinen

https://link.springer.com/article/10.1007/s11633-025-1587-8

https://www.mi-research.net/article/doi/10.1007/s11633-025-1587-8

专题 · 研究论文

CM-CLIP: Few-shot Cross-modal Generalization for Face Anti-spoofing via Prompt Learning

Hui Ma, Ajian Liu, Xun Lin, Hugo Jair Escalante, Isabelle Guyon, Jun Wan, Zhen Lei, Yanyan Liang

https://link.springer.com/article/10.1007/s11633-025-1575-z

https://www.mi-research.net/article/doi/10.1007/s11633-025-1575-z

专题 · 研究论文

A Non-intrusive Plug-and-play Method for Hallucination Mitigation via LID-guided Input Preprocessing

Ziqiang He, Jun Wang, Xiangui Kang, Z. Jane Wang

https://link.springer.com/article/10.1007/s11633-025-1596-7

https://www.mi-research.net/article/doi/10.1007/s11633-025-1596-7

专题 · 研究论文

Unveiling Hidden Psychological States: Synergistic Fusion of Amplified Color and Motion from Video

Yiwei Ru, Qi Li, Yongji Liu, Huijia Wu, Zhaofeng He, Zhenan Sun

https://link.springer.com/article/10.1007/s11633-025-1601-1

https://www.mi-research.net/article/doi/10.1007/s11633-025-1601-1

专题 · 研究论文

StegaFFD: Privacy-preserving Face Forgery Detection via Fine-grained Steganographic Domain Lifting

Guoqing Ma, Xun Lin, Hui Ma, Ajian Liu, Yizhong Liu, Wenzhong Tang, Shan Yu, Chenqi Kong, Yi Yu

https://link.springer.com/article/10.1007/s11633-025-1612-y

https://www.mi-research.net/article/doi/10.1007/s11633-025-1612-y

专题 · 研究论文

IKA2: Internal Knowledge Adaptive Activation for Robust Recognition in Complex Scenarios

Shuo Ye, Lixin Chen, Qiaoqi Li, Jiayu Zhang, Chaomeng Chen, Shutao Xia

https://link.springer.com/article/10.1007/s11633-025-1618-5

https://www.mi-research.net/article/doi/10.1007/s11633-025-1618-5

专题 · 研究论文

A Clinically Aligned Local-global Mutual Learning Framework for Interpretable Pneumoconiosis Diagnosis

Jiarui Wang, Xuerong Wang, Le Yang, Binglu Wang

https://link.springer.com/article/10.1007/s11633-025-1619-4

https://www.mi-research.net/article/doi/10.1007/s11633-025-1619-4

专题 · 研究论文

FrePL: Frequency-guided Pseudo-labeling for Semi-supervised Remote Physiological Measurement

Qi Li, Wei Qian, Dan Guo, Meng Wang

https://link.springer.com/article/10.1007/s11633-025-1621-x

https://www.mi-research.net/article/doi/10.1007/s11633-025-1621-x

专题 · 研究论文

From Uni- to Multi-modal: Progressive Multi-source Domain Adaptation with Gradient Disentangling for Audio-visual Deception Detection

Ronghao Lin, Aolin Xiong, Qiaolin He, Sijie Mai, Li Huang, Haifeng Hu

https://link.springer.com/article/10.1007/s11633-025-1630-x

https://www.mi-research.net/article/doi/10.1007/s11633-025-1630-x

纸刊免费寄送

Machine Intelligence Research

MIR为所有读者提供免费寄送纸刊服务，如您对本篇文章感兴趣，请点击下方链接填写收件地址，编辑部将尽快为您免费寄送纸版全文！

说明：如遇特殊原因无法寄达的，将推迟邮寄时间，咨询电话010-82544737

收件信息登记：

https://lcn76mgd97vz.feishu.cn/share/base/form/shrcnsQ6cmRjqoxPF5WDowSBFVr

关于Machine Intelligence Research

Machine Intelligence Research（简称MIR）由中国科学院自动化研究所主办，于2022年正式出版。MIR立足国内、面向全球，着眼于服务国家战略需求，刊发机器智能领域最新原创研究性论文、综述、评论等，全面报道国际机器智能领域的基础理论和前沿创新研究成果，促进国际学术交流与学科发展，服务国家人工智能科技进步。期刊入选"中国科技期刊卓越行动计划"，已被ESCI、EI、Scopus、中国科技核心期刊、CSCD等20余家国际数据库收录，入选图像图形领域期刊分级目录-T2级知名期刊。2022年首个CiteScore分值在计算机科学、工程、数学三大领域的八个子方向排名均跻身Q1区，最佳排名挺进Top 4%，2023年CiteScore分值继续跻身Q1区。2024年获得首个影响因子(IF) 6.4，位列人工智能及自动化&控制系统两个领域JCR Q1区；2025年发布的最新影响因子达8.7，继续跻身JCR Q1区，最佳排名进入全球第6名；2026年进入期刊分区表1区。