General

Junge Zhang, Ph.D.  Professor, Institute of Automation, Chinese Academy of Sciences. 

Email: jgzhang@nlpr.ia.ac.cn

Address:  95 Zhongguancun East Road, BEIJING, CHINA 
Postcode: 100190 

Research Areas

Game AI and decision-making, Reinforcement Learning, Multi-agent Learning, Pattern Recognition, Computer Vision

Education

2008 - 2013, Ph.D degree, Institute of Automation, Chinese Academy of Sciences. Supervisor: Prof. Tieniu Tan

Publications

[1]. Wenzhen Huang, Qiyue Yin, Junge Zhang, Kaiqi Huang, Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning, In Proceedings of AAAI Conference on Artificial Intelligence, AAAI 2021. 

[2]. Debang Li, Junge Zhang, Kaiqi Huang, Universal Adversarial Perturbations against Object Detection. Pattern Recognition 2021. 

[3]. Debang Li, Junge Zhang, Kaiqi Huang and Ming-Hsuan Yang, Composing Good Shots by Exploiting Mutual Relations. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2020. 

[4]. Debang Li, Junge Zhang, Kaiqi Huang, Learning to learn Cropping Models for Different Aspect Ratio Requirements. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2020. 

[5]. Kaiqi Huang, Junliang Xing, Junge Zhang, Wancheng Ni and Bo Xu, Human-Machine Gaming Intelligence: A Review, Science China, 2019.

[6]. Wenzhen Huang, Junge Zhang, and Kaiqi Huang. Bootstrap estimated uncertainty of the environment model for model-based reinforcement learning. In Proceedings of AAAI Conference on Artificial Intelligence, AAAI 2019. 

[7]. Ziyu Wan, Dongdong Chen, Yan Li, Xingguang Yan, Junge Zhang, Yizhou Yu and Jing Liao, Transductive Zero-Shot Learning with Visual Structure Constraint, In Proceedings of Neural Information Processing Systems, NeurIPS 2019. 

[8]. Huikai Wu, Junge Zhang and Kaiqi Huang, SparseMask: Differentiable Connectivity Learning for Dense Image Prediction, In Proceedings of IEEE International Conference on Computer Vision, ICCV 2019. 

[9]. Zhimao Peng, Zechao Li, Junge Zhang, Yan Li, Guo-Jun Qi, Jinhui Tang, Few-shot Image Recognition with Knowledge Transfer, In Proceedings of IEEE International Conference on Computer Vision, ICCV 2019. 

[10]. Huikai Wu, Shuai Zheng, Junge Zhang and Kaiqi Huang, GP-GAN: Towards Realistic High-Resolution Image Blending, In Proceedings of ACM International Conference on Multimedia, MM 2019. 

[11]. Zihao Li, Shu Zhang, Junge Zhang, Kaiqi Huang, Yizhou Wang and Yizhou Yu, MVP-Net: Multi-view FPN with Position-aware Attention for Deep Universal Lesion Detection, In Proceedings of International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2019. 

[12]. Debang Li, Huikai Wu, Junge Zhang and Kaiqi Huang, Fast A3RL: Aesthetics Aware Adversarial Reinforcement Learning for Image Cropping, IEEE Transactions on Image Processing, 2019. 

[13]. Yan Li, Junge Zhang, Kaiqi Huang, and Jianguo Zhang. Mixed supervised object detection with robust objectness transfer. IEEE Trans. Pattern Anal. Mach. Intell., 41(3):639–653, 2019.

[14]. Qiyue Yin, Junge Zhang*, Shu Wu, and Hexi Li. Multi-view clustering via joint feature selection and partially constrained cluster label learning. Pattern Recognition, 93:380–391, 2019.

[15]. Ziyu Wan, Yan Li, Min Yang, and Junge Zhang. Transductive zero-shot learning via visual center adaptation. In Proceedings of AAAI Conference on Artificial Intelligence, AAAI 2019.

[16]. Yan Li, Zhen Jia, Junge Zhang, Kaiqi Huang, and Tieniu Tan. Deep semantic structural constraints for zero-shot learning. In Proceedings of AAAI Conference on Artificial Intelligence, AAAI 2018.

[17]. Yabei Li, Junge Zhang, Yanhua Cheng, Kaiqi Huang, and Tieniu Tan. Df^2net: Discriminative feature learning and fusion network for RGB-D indoor scene classification. In Proceedings of AAAI Conference on Artificial Intelligence, AAAI 2018.

[18]. Debang Li, Huikai Wu, Junge Zhang, and Kaiqi Huang. A2-RL: aesthetics aware reinforcement learning for image cropping. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018.

[19]. Yan Li, Junge Zhang, Jianguo Zhang, and Kaiqi Huang. Discriminative learning of latent features for zero-shot recognition. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018 (Oral).

[20]. Huikai Wu, Shuai Zheng, Junge Zhang, and Kaiqi Huang. Fast end-to-end trainable guided filter. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018.

[21]. Junge Zhang, Kaiqi Huang, Tieniu Tan, and Zhaoxiang Zhang. Local structured representation for generic object detection. Frontiers Comput. Sci., 11(4):632–648, 2017.

[22]. Kangwei Liu, Junge Zhang, Peipei Yang, Stephen J. Maybank, and Kaiqi Huang. GRMA: generalized range move algorithms for the efficient optimization of mrfs. International Journal of Computer Vision, 121(3):365–390, 2017.

[23]. Junge Zhang*, Lianrui Fu* and Kaiqi Huang. ORGM: occlusion relational graphical model for human pose estimation. IEEE Trans. Image Processing, 26(2):927–941, 2017.

[24]. Kangwei Liu, Junge Zhang, Peipei Yang, and Kaiqi Huang. Fastlcd: Fast label coordinate descent for the efficient optimization of 2d label mrfs. In Proceedings of International Joint Conference on Artificial Intelligence, IJCAI 2016.

[25]. Junge Zhang, Yanhu Shan, and Kaiqi Huang. ISEE smart home (ISH): smart video analysis for home security. Neurocomputing, 149:752–766, 2015.

[26]. Chong Wang, Kaiqi Huang, Weiqiang Ren, Junge Zhang, and Stephen J. Maybank. Large-scale weakly supervised object localization via latent category learning. IEEE Trans. Image Processing, 24(4):1371–1385, 2015.

[27]. Kangwei Liu, Junge Zhang, Peipei Yang, and Kaiqi Huang. GRSA: generalized range swap algorithm for the efficient optimization of mrfs. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015.

[28]. Lianrui Fu, Junge Zhang, and Kaiqi Huang. Beyond tree structure models: A new occlusion aware graphical model for human pose estimation. In Proceedings of IEEE International Conference on Computer Vision, ICCV 2015.

[29]. Kangwei Liu, Junge Zhang, Kaiqi Huang, and Tieniu Tan. Deformable object matching via deformation decomposition based 2d label MRF. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014.

[30]. Weihua Chen, Lijun Cao, Junge Zhang, and Kaiqi Huang. An adaptive combination of multiple features for robust tracking in real scene. In Proceedings of IEEE International Conference on Computer Vision Workshops, ICCV 2013. 

[31]. Junge Zhang, Kaiqi Huang, Yinan Yu, and Tieniu Tan. Boosted local structured HOG-LBP for object localization. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011.

[32]. Shuai Zheng, Junge Zhang, Kaiqi Huang, Ran He, and Tieniu Tan. Robust view transformation model for gait recognition. In Proceedings of IEEE International Conference on Image Processing, ICIP 2011.


Research Interests

My research interests include computer vision, pattern recognition, particularly on continual / lifelong learning and deep reinforcement learning based sequential decision making.

Honors & Distinctions

Starcraft AI, Rank 4, AIIDE Starcraft AI Challenge 2017

Starcraft AI, Rank 3, AIIDE Starcraft AI Challenge 2018

Winner, Detection task, PASCAL VOC 2010

Winner, Detection task, PASCAL VOC 2011

Beijing Nova Star 2019