教师简介
尧思远，副教授，博士生导师。博士毕业于中国科学院大学，长期从事多媒体内容理解与人工智能安全领域的研究。近年在TIP, TGRS, TMM, ICCV, CVPR，ECCV, AAAI, ACM MM等国际高水平期刊和会议上发表学术论文20余篇，获授权国家发明专利11项。承担国家自然科学基金青年项目、腾讯犀牛鸟基金等课题，参与国家自然科学基金重点/面上项目多项。曾获中国通信学会科技进步一等奖、中国安全生产协会科技进步一等奖各一项。
教育工作经历
2016.09~2022.06 中国科学院信息工程研究所工学博士
2011.09~2014.06中国电子科学研究院 工学硕士
研究方向
视频目标跟踪与分割，复杂环境下的目标感知探测，2D/3D重建
模型安全和鲁棒性，多模态视觉-语言大模型
近五年内发表论文
Siyuan Yao, Rui Zhu, Ziqi Wang, Wenqi Ren, Yanyang Yan and Xiaochun Cao, UMDATrack: Unified Multi-Domain Adaptive Tracking Under Adverse Weather Conditions, 6466-6475, ICCV 2025. (CCF-A);
Siyuan Yao, Yang Guo, Yanyang Yan, Wenqi Ren and Xiaochun Cao, UncTrack: Reliable Visual Object Tracking with Uncertainty-Aware Prototype Memory Network. IEEE Transactions on Image Processing. 2025. (CCF-A，SCI一区TOP);
Siyuan Yao, Hao Sun, Tian-Zhu Xiang, Xiao Wang, Xiaochun Cao, Hierarchical Graph Interaction Transformer With Dynamic Token Clustering for Camouflaged Object Detection. IEEE Transactions on Image Processing. 33: 5936-5948, 2024. (CCF-A，SCI一区TOP);
Siyuan Yao, Hua Zhang, Wenqi Ren, Chao Ma, Xiaoguang Han and Xiaochun Cao, Robust Online Tracking via Contrastive Spatio-Temporal Aware Network, IEEE Transactions on Image Processing. 30:1989-2002, 2021. (CCF-A, SCI一区TOP);
Siyuan Yao, Xiaoguang Han, Hua Zhang, Xiao Wang and Xiaochun Cao, Learning Deep Lucas-Kanade Siamese Network for Visual Tracking, IEEE Transactions on Image Processing. 30:4814–4827, 2021. (CCF-A, SCI一区TOP);
Siyuan Yao, Dongxiu Liu, Taotao Li, Shengjie Li, Wenqi Ren and Xiaochun Cao, UAGLNet: Uncertainty-Aggregated Global-Local Fusion Network with Cooperative CNN-Transformer for Building Extraction, IEEE Transactions on Geoscience and Remote Sensing. 64:1-14, 2026. (CCF-B，SCI一区TOP);
Hongjing Wu, Siyuan Yao*, Feng Huang, Shu Wang, Linchao Zhang, Zhuoran Zheng, Wenqi Ren*, LVPTrack: High Performance Domain Adaptive UAV Tracking with Label Aligned Visual Prompt Tuning. AAAI, 2025. (CCF-A，通讯作者);
Yan, Yanyang, Siyuan Yao, Wenqi Ren, Rui Zhang, Qi Guo, and Xiaochun Cao. CAN: Cascade Augmentations Against Noise for Image Restoration. IEEE Transactions on Image Processing. 34:5131-5146, 2025. (CCF-A，SCI一区TOP);
Pengwen Dai, Siyuan Yao, Zekun Li, Sanyi Zhang and Xiaochun Cao, ACE: Anchor-Free Corner Evolution for Real-Time Arbitrary-Oriented Object Detection. IEEE Transactions on Image Processing. 31:4076-4089,2022. (CCF-A，SCI一区TOP);
Feifei Kou, Yuhan Yao, Siyuan Yao, Jiahao Wang, Lei Shi, Yawen Li, Xuejing Kang, IWRN: A Robust Blind Watermarking Method for Artwork Image Copyright Protection Against Noise Attack. AAAI, 2025. (CCF-A, Oral);
Siyuan Liang, Xingxing Wei, Siyuan Yao, and Xiaochun Cao, Efficient Adversarial Attacks for Visual Object Tracking, European Conference on Computer Vision, 34-50, 2020. (计算机视觉顶会);
工作经历
2014.07-2016.03：中国电子科技集团第十一研究所
2022.07-2026.01：北京邮电大学计算机学院
奖励荣誉
2025中国通信学会科技进步一等奖（排名第5）
2024中国安全生产协会科技进步一等奖（排名第5）
2021年度腾讯“犀牛鸟精英科研人才培养计划”
指导1名学生获北京市优秀毕业论文，北京市优秀毕业生。指导的大多数学生在清华大学、伦敦大学学院、南洋理工大学、香港科技大学、中山大学等国内外著名院校深造。
代表性专利
基于层级图交互和单元聚类的伪装目标检测方法和系统，专利号：ZL 2024 1 1219639.9 授权日：2025年07月08日
多模态融合模型的对抗样本生成方法及装置，专利号：ZL 2024 1 1229248.5 授权日： 2025年10月10日
目标跟踪器训练方法和目标跟踪方法，专利号：ZL 2024 1 1695700.7 授权日： 2025年10月28日
基于协作编码器和不确定性聚合解码器的建筑物提取方法及系统，专利号：ZL 2024 1 1894317.4 授权日： 2025年08月12日
学术服务
期刊审稿人：
International Journal of Computer Vision（CCF-A, SCI一区）
IEEE Transactions on Image Processing (TIP) (CCF-A，SCI一区)
IEEE Transactions on Multimedia (TMM) (CCF-B，SCI一区)
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT) (CCF-B，SCI一区)
会议审稿人：
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) （CCF-A）
International Conference on Computer Vision (ICCV) （CCF-A）
International Conference on Machine Learning (ICML) (CCF-A)
Conference on Neural Information Processing Systems (NeurIPS) (CCF-A)
Association for the Advancement of Artificial Intelligence (AAAI) (CCF-A)
ACM International Conference on Multimedia (ACM MM) (CCF-A)
International Conference on Learning Representations (ICLR)
International Conference on Artificial Intelligence and Statistics (AISTATS)
