张俊格-中国科学院大学-UCAS

研究领域

（一）持续学习，终生学习，小样本学习

（二）博弈决策, 强化学习，多智能体系统

招生信息

目前还有少量硕士指标，欢迎大家联系。

希望学生具有优秀的编程（C/C++, Python）、数学、英语基础。

招生专业

081104-模式识别与智能系统

招生方向

博弈决策、多智能体系统、强化学习、模式识别、计算机视觉

教育背景

2008-09--2013-06 中国科学院自动化研究所博士

工作经历

工作简历

2013-07~现在, 中国科学院自动化研究所, 助理研究员、副研究员、研究员

社会兼职

2018-08-01-今,中国图象图形学会青年工作委员会委员,
2017-09-01-今,中国自动化学会混合智能专业委员会委员,
2017-05-01-今,中关村管委会专家委员会委员,
2015-10-01-今,中国计算机学会计算机视觉专业委员会委员,

专利与奖励

奖励信息

（1）北京市科技新星, , 省级, 2019
（2）中科院青年促进会成员, 部委级, 2019
（3） AIIDE星际争霸AI竞赛国际季军, 其他, 2018
（4） AIIDE星际争霸AI竞赛国际第四名, 其他, 2017
（5）中国人工智能学会优秀博士学位论文提名, 部委级, 2013
（6） PASCAL VOC国际冠军, 其他, 2011

专利成果

[1] 张俊格, 李庆明, 尹奇跃. 非平稳环境中去中心化多智能系统的决策方法. CN: CN112668721B, 2021-07-02.

[2] 张俊格, 李庆明. 在多任务数据流中持续学习的方法及装置. CN: CN112698933A, 2021-04-23.

[3] 徐名源, 姚春凤, 冯柏岚, 黄凯奇, 张俊格, 陈晓棠, 李德榜. 一种对象检测模型的对抗扰动生成方法和装置. CN: CN109902705A, 2019-06-18.

[4] 黄凯奇, 张俊格, 李德榜. 基于强化学习的图片自动裁剪的方法及装置. CN: CN108154464A, 2018-06-12.

[5] 张俊格. 一种图像处理方法及系统. CN: CN107391505A, 2017-11-24.

[6] 张俊格, 谭铁牛, 黄凯奇, 贾真. 基于百科知识语义增强的零样本分类方法、装置. CN: CN107292349A, 2017-10-24.

[7] 黄凯奇, 张俊格, 付连锐. 二维图像人体关节点定位模型的构建方法及定位方法. CN: CN106548194A, 2017-03-29.

[8] 黄凯奇, 徐冉, 张俊格. 基于双向递归卷积神经网络的图像超分辨率增强方法. CN: CN106127684A, 2016-11-16.

[9] 黄凯奇, 任伟强, 王冲, 张俊格. 一种视觉目标检测与标注方法. CN: CN104217225A, 2014-12-17.

[10] 黄凯奇, 任伟强, 张俊格. 一种基于数据与任务驱动的图像分类方法. CN: CN103984959A, 2014-08-13.

[11] 吴娜, 陆京, 金永哲, 黄凯奇, 马丹, 张俊格. 基于视频的摔倒检测方法和设备. CN: CN103186902A, 2013-07-03.

[12] 黄凯奇, 单言虎, 张俊格, 金永哲, 吴娜. 利用视频检测打架行为的方法和装置. CN: CN102750709A, 2012-10-24.

出版信息

发表论文

[1] 尹奇跃, 赵美静, 倪晚成, 张俊格, 黄凯奇. 兵棋推演的智能决策技术与挑战. 自动化学报[J]. 2022, [2] Huang, Wenzhen, Yin, Qiyue, Zhang, Junge, Huang, Kaiqi. Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning. AAAI[J]. 2021, http://arxiv.org/abs/2104.04174.
[3] Li, Debang, Zhang, Junge, Huang, Kaiqi. Universal adversarial perturbations against object detection. PATTERN RECOGNITION[J]. 2021, 110: http://dx.doi.org/10.1016/j.patcog.2020.107584.
[4] 尹奇跃, 黄岩, 张俊格, 吴书, 王亮. 基于深度学习的跨模态检索综述. 中国图象图形学报. 2021, 26(6): 1368-1388, [5] 黄凯奇, 兴军亮, 张俊格, 倪晚成, 徐博. 人机对抗智能技术. 中国科学:信息科学[J]. 2020, 50(4): 540-550, http://lib.cqvip.com/Qikan/Article/Detail?id=7101802834.
[6] Huang Kaiqi. Learning to Learn Cropping Models for Different Aspect Ratio Requirements. IEEE Conference on Computer Vision and Pattern Recognition. 2020, [7] 张俊格. Human-Machine Gaming Intelligence: A Review. Science China. 2020, [8] Li, Debang, Zhang, Junge, Huang, Kaiqi, Yang, MingHsuan, IEEE. Composing Good Shots by Exploiting Mutual Relations. 2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)null. 2020, 4212-4221, [9] Li Debang, Wu Huikai, Zhang Junge, Huang Kaiqi. Fast A3RL: Aesthetics-Aware Adversarial Reinforcement Learning for Image Cropping.. IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2019, http://kns.cnki.net/KCMS/detail/detail.aspx?QueryID=0&CurRec=1&recid=&FileName=SJPDB237893583FD6FF6AB737715EDEB1EAD&DbName=SJPD_06&DbCode=SJPD&yx=&pr=&URLID=&bsm=.
[10] Wu, Huikai, Zhang, Junge, Huang, Kaiqi, IEEE. SparseMask: Differentiable Connectivity Learning for Dense Image Prediction. 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)null. 2019, 6767-6776, [11] Li, Yan, Zhang, Junge, Huang, Kaiqi, Zhang, Jianguo. Mixed Supervised Object Detection with Robust Objectness Transfer. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE[J]. 2019, 41(3): 639-653, http://ir.ia.ac.cn/handle/173211/23345.
[12] Wu, Huikai, Zheng, Shuai, Zhang, Junge, Huang, Kaiqi, ACM. GP-GAN: Towards Realistic High-Resolution Image Blending. PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19)null. 2019, 2487-2495, http://dx.doi.org/10.1145/3343031.3350944.
[13] Li, Zihao, Zhang, Shu, Zhang, Junge, Huang, Kaiqi, Wang, Yizhou, Yu, Yizhou, Shen, D, Liu, T, Peters, TM, Staib, LH, Essert, C, Zhou, S, Yap, PT, Khan, A. MVP-Net: Multi-view FPN with Position-Aware Attention for Deep Universal Lesion Detection. MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2019, PT VInull. 2019, 11769: 13-21, [14] Peng, Zhimao, Li, Zechao, Zhang, Junge, Li, Yan, Qi, GuoJun, Tang, Jinhui, IEEE. Few-Shot Image Recognition with Knowledge Transfer. 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)null. 2019, 441-449, [15] Yin, Qiyue, Zhang, Junge, Wu, Shu, Li, Hexi. Multi-view clustering via joint feature selection and partially constrained cluster label learning. PATTERN RECOGNITION[J]. 2019, 93: 380-391, http://dx.doi.org/10.1016/j.patcog.2019.04.024.
[16] Wan, Ziyu, Li, Yan, Yang, Min, Zhang, Junge, AAAI. Transductive Zero-Shot Learning via Visual Center Adaptation. THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCEnull. 2019, 10059-10060, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000486572504167.
[17] Wan, Ziyu, Chen, Dongdong, Li, Yan, Yan, Xingguang, Zhang, Junge, Yu, Yizhou, Liao, Jing, Wallach, H, Larochelle, H, Beygelzimer, A, dAlcheBuc, F, Fox, E, Garnett, R. Transductive Zero-Shot Learning with Visual Structure Constraint. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019)null. 2019, 32: [18] Li, Debang, Wu, Huikai, Zhang, Junge, Huang, Kaiqi. Fast A3RL: Aesthetics-Aware Adversarial Reinforcement Learning for Image Cropping. IEEE TRANSACTIONS ON IMAGE PROCESSING[J]. 2019, 28(10): 5105-5120, https://www.webofscience.com/wos/woscc/full-record/WOS:000482599100009.
[19] Huang Wenzhen, Zhang Junge, Huang Kaiqi, AAAI. Bootstrap Estimated Uncertainty of the Environment Model for Model-Based Reinforcement Learning. THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCEnull. 2019, 3870-3877, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000485292603109.
[20] 张俊格. Df^2net: Discriminative feature learning and fusion network for RGB-D indoor scene classification. AAAI. 2018, [21] Li, Debang, Wu, Huikai, Zhang, Junge, Huang, Kaiqi, IEEE. A2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)null. 2018, 8193-8201, [22] 黄凯奇, 张俊格, 程衍华, 李亚蓓, 谭铁牛. DF2Net: A Discriminative Feature Learning and Fusion Network for RGB-D Indoor Scene Classification.. 2018, http://ir.ia.ac.cn/handle/173211/19711.
[23] Li Yan, Jia Zhen, Zhang Junge, Huang Kaiqi, Tan Tieniu, AAAI. Deep Semantic Structural Constraints for Zero-Shot Learning. THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCEnull. 2018, 7049-7056, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000485488907018.
[24] Li, Yan, Zhang, Junge, Zhang, Jianguo, Huang, Kaiqi, IEEE. Discriminative Learning of Latent Features for Zero-Shot Recognition. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)null. 2018, 7463-7471, [25] Han, Xue, Yan, Hongping, Zhang, Junge, Wang, Lingfeng, Kurkova, V, Manolopoulos, Y, Hammer, B, Iliadis, L, Maglogiannis, I. ACM: Learning Dynamic Multi-agent Cooperation via Attentional Communication Model. ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2018, PT IInull. 2018, 11140: 219-229, [26] Wu, Huikai, Zheng, Shuai, Zhang, Junge, Huang, Kaiqi, IEEE. Fast End-to-End Trainable Guided Filter. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)null. 2018, 1838-1847, [27] 谭铁牛, 张俊格, 李亚蓓, 黄凯奇, 程衍华. Semantics-guided Multi-level RGB-D Feature Fusion for Indoor Semantic Segmentation. 2017, http://ir.ia.ac.cn/handle/173211/19698.
[28] Huang Kaiqi, Tan Tieniu, Jia Zhen, Zhang Junge. Encyclopedia Enhanced Semantic Embedding for Zero-Shot Learning. 2017, http://ir.ia.ac.cn/handle/173211/19662.
[29] 黄凯奇, 张俊格, 徐冉. 利用双通道卷积神经网络的图像超分辨率算法. 中国图象图形学报[J]. 2016, 21(5): 556-564, [30] 张俊格. 基于视觉结构表达与建模的物体检测研究. 2013, http://www.irgrid.ac.cn/handle/1471x/977191.

科研活动

科研项目

（ 1 ）博弈决策智能理论与技术研究, 主持, 省级, 2019-11--2022-12
（ 2 ）中科院青年促进会项目, 主持, 部委级, 2019-01--2022-12
（ 3 ）智能博弈**中的关键理论与技术研究, 主持, 国家级, 2019-01--2021-12
（ 4 ）场景元素的时空演化分析与高层次事件检测, 主持, 国家级, 2016-07--2020-12
（ 5 ）小样本条件下的物体检测研究, 主持, 国家级, 2019-01--2022-12
（ 6 ）小样本博弈学习与可解释性建模, 主持, 部委级, 2020-10--2024-12
（ 7 ）智能博弈决策AI训练学习与推理平台, 主持, 国家级, 2020-01--2022-06
（ 8 ）面向图像分析的带噪声小样本学习技术, 主持, 院级, 2018-09--2021-12
（ 9 ）自动化算子设计, 主持, 院级, 2019-04--2020-07