姓名:苏航

职称:助理研究员

邮箱:suhangss@mail.tsinghua.edu.cn

主页:http://www.suhangss.me

教育背景

2009/09-2014/12       上海交通大学            电子工程系           工学博士

2007/07-2009/09       上海交通大学            电子工程系           工学硕士

2003/09-2007/07       上海交通大学            电子工程系           工学学士

工作履历

2017/12- 现在                清华大学                                                                 助理研究员

2015/01 - 2017/12         清华大学                                                                 博士后

2011/09 - 2013/08        卡内基梅隆大学 (Carnegie Mellon University )   访问学者

社会兼职

2016年9月-至今          中国计算机学会 计算机视觉专委会        专委会委员

2017年1月-至今          中国图象图形学会  视觉大数据专委会     专委会委员

2017年7月-至今          中国人工智能学会  机器学习专委会        通讯委员

2015年9月-至今          视觉与学习青年学者研讨会             执行AC委员会 副主席

研究领域

可信赖和可理解人工智能理论、计算机视觉、强化学习

研究概况

本人一直从事可信赖人工智能理论、关键技术与相关应用研究,主要关注可理解人工智能理论、计算机视觉和强化学习等相关领域,先后CVPR、IJCAI、ECCV和TMI等人工智能顶级国际会议和期刊发表论文将50余篇,并荣获ICME2018“白金最佳论文”,AVSS2012“最佳论文奖”和MICCAI2012的“青年学者奖”,作为主要技术负责人,获得 ViZDoom 2018国际FPS赛事历史上首个中国区冠军。过去几年中,本人连续受邀担任人工智能顶级国际会议IJCAI、AAAI、CVPR的程序委员会高级委员或委员,以及TPAMI、ICML,NIPS等十余个重要国际会议和期刊的审稿人。近年来,本人作为项目负责人,受到国家自然科学基金面上项目、中国博士后基金等多个国家级项目资助,总金额超过300万元;并作为核心成员参与国家自然科学基金国际合作重点项目和国家重点研发计划等多个国家级项目中。

奖励与荣誉

1. ICME 白金最佳论文

2. MICCAI2012 青年学者

3. AVSS2012最佳论文

学术成果

[1] Yinpeng Dong, Tianyu Pang, Hang Su, and Jun Zhu. Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks, In Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, 2019. (CCF A, Oral)

[2] Yinpeng Dong, Hang Su, Baoyuan Wu, Zhifeng Li, Wei Liu, Tong Zhang, and Jun Zhu. Efficient Decision-based Black-box Adversarial Attacks on Face Recognition, In Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, 2019 (CCF A)

[3] Shiyu Huang, Hang Su, Jun Zhu, and Tim Chen. Combo-Action: Training Agent For FPS Game with Auxiliary Tasks, To appear in the 33rd AAAI Conference on Artificial Intelligence (AAAI-19), Honolulu, Hawaii, USA, 2019.

[4] Yulong Wang, Hang Su, Xiaolin Hu, Interpret Neural Networks by Identifying Critical Data Routing Paths, in the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, USA, 2018. (CCF A, Spotlight)

[5] Yinpeng Dong, Fangzhou Liao, Tianyu Pang, Hang Su, Jun Zhu, Xiaolin Hu, and Jianguo Li. Boosting Adversarial Attacks with Momentum, in the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, USA, 2018. (CCF A, Spotlight)

[6] Haosheng Zou, Hang Su, Shihong Song, and Jun Zhu. Understanding Human Behavior in Crowds by Imitating the Decision-Making Process, in 32nd AAAI Conference on Artificial Intelligence (AAAI), New Orleans, USA, 2018. (CCF A)

[7] Hang Su, Jun Zhu, Yinpeng Dong, and Bo Zhang. Forecast the Plausible Paths in Crowd Scenes, in International Joint Conference on Artificial Intelligence (IJCAI), Melbourne, Australia, 2017 (CCF A)

[8] Yinpeng Dong, Hang Su, Jun Zhu, and Bo Zhang. Improving Interpretability of Deep Neural Networks with Semantic Information, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, Hawaii, 2017 (CCF A)

[9] Hang Su, Jun Zhu, Zhaozheng Yin, Yinpeng Dong, and Bo Zhang. Efficient and Robust Semi-supervised Learning over a Sparse-Regularized Graph, European Conference on Computer Vision (ECCV), Amsterdam, The Netherlands, 2016 (CCF B)

[10] Hang Su, Zhaozheng Yin, Takeo Kanade, Seungil Huh, Active Sample Selection and Correction Propagation on a Gradually-Augmented Graph , Computer Vision and Pattern Recognition, IEEE Conference on (CVPR), 2015. (CCF A)

[11] Hang Su, Zhaozheng Yin, Seungil Huh, Takeo Kanade, Jun Zhu, “Interactive Cell Segmentation based on Active and Semi-supervised Learning,” IEEE Transactions on Medical Imaging (TMI), 2015

[12] Hang Su, Zhaozheng Yin, Seungil Huh, Takeo Kanade, Cell Segmentation in Phase Contrast Microscopy Images via Semi-supervised Classification over Optics-related Features, Medical Image Analysis (MIA), vol. 17, pp. 746-765, Oct. 2013.

[13] Hang Su, Hua Yang, Shibao Zheng, Yawen Fan, and Sha Wei, The Large-Scale Crowd Behavior Perception Based on Spatio-Temporal Viscous Fluid Field, Information Forensics and Security, IEEE Transactions on (TIFS), vol.8, pp.1575-1589, Oct. 2013

[14] Hang Su, Zhaozheng Yin, Takeo Kanade, Seungil Huh, Phase Contrast Image Restoration via Dictionary Representation of Diffraction Patterns, the 15th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2012, pp. 615-622. (Young Investigator Award)

[15] Hang Su, Hua Yang, Shibao Zheng, Yawen Fan, and Sha Wei, Crowd Event Perception Based On Spatio-Temporal Viscous Fluid Field, International Conference on Advanced Video and Signal Based Surveillance (AVSS), 2012, pp. 458-463. (Best Paper Award)