目录

Vol.20, No.4

MIR第四期已于8月正式出版，其中包括4篇综述，分别来自北京大学高文院士团队、悉尼大学冯大淦团队、自动化所宗成庆团队及西安电子科技大学公茂果团队，涵盖大规模多模态预训练模型、机器翻译、联邦学习等前沿内容；本期同时出版了4篇研究论文，其中包括京东探索研究院陶大程院士团队和中国人民大学卢志武团队的最新成果，全文免费下载，文末提供纸刊免费邮寄服务，欢迎阅读！

Large-scale Multi-modal Pre-trained Models: A Comprehensive Survey

Xiao Wang, Guangyao Chen, Guangwu Qian, Pengcheng Gao, Xiao-Yong Wei, Yaowei Wang, Yonghong Tian, Wen Gao

https://link.springer.com/article/10.1007/s11633-022-1410-8

https://www.mi-research.net/en/article/doi/10.1007/s11633-022-1410-8

中文导读：

高文院士团队 | 综述: 大规模多模态预训练模型 

A Review of Predictive and Contrastive Self-supervised Learning for Medical Images

Wei-Chien Wang, Euijoon Ahn, Dagan Feng, Jinman Kim

https://link.springer.com/article/10.1007/s11633-022-1406-4

https://www.mi-research.net/en/article/doi/10.1007/s11633-022-1406-4

Transformer: A General Framework from Machine Translation to Others

Yang Zhao, Jiajun Zhang, Chengqing Zong

https://www.mi-research.net/en/article/doi/10.1007/s11633-022-1393-5

https://link.springer.com/article/10.1007/s11633-022-1393-5

中文导读：

自动化所宗成庆团队 | 综述: Transformer模型-从机器翻译到其他任务的通用框架 

Federated Learning on Multimodal Data: A Comprehensive Survey

Yi-Ming Lin, Yuan Gao, Mao-Guo Gong, Si-Jia Zhang, Yuan-Qiao Zhang, Zhi-Yuan Li

https://www.mi-research.net/en/article/doi/10.1007/s11633-022-1398-0

https://link.springer.com/article/10.1007/s11633-022-1398-0

中文导读：

西电公茂果团队 | 综述: 多模态数据的联邦学习 

Region-adaptive Concept Aggregation for Few-shot Visual Recognition

Mengya Han, Yibing Zhan, Baosheng Yu, Yong Luo, Han Hu, Bo Du, Yonggang Wen, Dacheng Tao

https://www.mi-research.net/en/article/doi/10.1007/s11633-022-1358-8

https://link.springer.com/article/10.1007/s11633-022-1358-8

Cross-modal Contrastive Learning for Generalizable and Efficient Image-text Retrieval

Haoyu Lu, Yuqi Huo, Mingyu Ding, Nanyi Fei, Zhiwu Lu

https://www.mi-research.net/en/article/doi/10.1007/s11633-022-1386-4

https://link.springer.com/article/10.1007/s11633-022-1386-4

A New Diagnosis Method with Few-shot Learning Based on a Class-rebalance Strategy for Scarce Faults in Industrial Processes

Xinyao Xu, De Xu, Fangbo Qin

https://www.mi-research.net/en/article/doi/10.1007/s11633-022-1363-y

https://link.springer.com/article/10.1007/s11633-022-1363-y

Speech Emotion Recognition Using Cascaded Attention Network with Joint Loss for Discrimination of Confusions

Yang Liu, Haoqin Sun, Wenbo Guan, Yuqi Xia, Zhen Zhao

https://www.mi-research.net/en/article/doi/10.1007/s11633-022-1356-x

https://link.springer.com/article/10.1007/s11633-022-1356-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://www.wjx.cn‍/vm/eIyIAAI.aspx#  

∨关于Machine Intelligence Research

Machine Intelligence Research（简称MIR，原刊名International Journal of Automation and Computing）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等数据库收录。