骨干人才
张兆翔
张兆翔，1983年3月生，博士，研究员。2004年毕业于中国科学技术大学电子科学与技术系，2009年于中国科学院自动化研究所获得博士学位，2009年-2015年在北京航空航天大学计算机学院先后任讲师、副教授、计算机应用技术系副主任，2015年任中国科学院自动化研究所研究员。研究兴趣包括：视觉认知计算、类脑学习和面向开放环境的视觉感知与理解。在本领域国际主流期刊与会议上发表论文200余篇，近五年来在JMLR、IEEE T-IP、IEEE T-NN等顶级期刊与CVPR、ICCV、ECCV、NIPS、AAAI、IJCAI等顶级会议发表论文50余篇，申请专利20余项，已授权10项，承担了国家自然科学基金重点项目、国家重点研发项目课题、北京市新一代人工智能重点研发项目等多项国家级科研项目和企业合作项目；是IEEE高级会员，中国计算机学会CCF杰出会员、中国人工智能学会CAAI杰出会员、中国人工智能学会CAAI副秘书长、中国人工智能学会CAAI模式识别专委会秘书长；是IEEET-CSVT、Patten Recognition、NeuroComputing 编委，CVPR、ICCV、AAAI、IJCAI、ACM MM、ICPR、ACCV等国际会议的领域主席（Area Chair）或高级程序委员会主席（Senior PC）。入选“教育部新世纪优秀人才支持计划”。曾获得中国人工智能学会技术发明奖二等奖（排名第一）。
主要研究方向及内容
1、基于认知机理和脑启发的视觉计算方法
研究以面向大数据的智能视觉监控等为应用背景，开展基于视觉认知机理和脑启发的视觉计算方法研究，研究视觉计算的整体化感知与层次化表达机制，研究视觉计算不同层次间的相互导出和反馈机制，利用大数据冗余信息构建高性能的视觉计算模型。
2、多尺度类脑神经网络计算模型
研究人工神经网络伴随着人工智能学科的成长取得了长足的发展，以深度学习为代表神经网络方法目前在各种视听觉应用中取得突破。但深度神经网络与人脑的架构、机制、功能等各方面存在显著差异。如何借鉴和模仿人脑，构建多尺度的类脑神经网络，对不同功能区进行模块化整合，突破深度神经网络现有的局限性，是我们重点研究的问题。
3、类人自主学习方法研究
人的学习机制在宏观上存在高度自主性特色，能够对已有知识进行归纳和总结，并举一反三、触类旁通的应用于其他问题。我们主要借鉴人的学习特性，开展基于大样本的学习模型构建和基于小样本的模型自适应，引入长期学习机制，探讨学习目标随着时间、任务变化的自适应性，进而达到类人自主学习的目标。
4、面向开放环境的智能计算
以视觉和多模态感知为主要应用背景，探索在开放环境中能够举一反三、有效进行类别发现和噪声拒识的的计算模型与方法，在机器人等应用中验证其优越性。
代表性论文
Zhaoxiang Zhang, Jiaxin Chen, Qiang Wu, Ling Shao. (2018) GII Representation-Based Cross-View Gait Recognition by Discriminative Projection With List-Wise Constraints, IEEE Transactions on Cybernetics, 48(10): 2935-2947.
Yuntao Chen, Chenxia Han, Yanghao Li, Zehao Huang, Yi Jiang, Naiyan Wang, Zhaoxiang Zhang*(2019), SimpleDet: A Simple and Versatile Distributed Framework for Object Detection and Instance Recognition, Journal of Machine Learning Research (JMLR),20(156).
Ke Chen, Zhaoxiang Zhang*. (2017) Pedestrian Counting With Back-Propagated Information and Target Drift Remedy, IEEE Transactions on Systems, Man, and Cybernetics: Systems, 47(4): 639-647.
Guibo Zhu, Zhaoxiang Zhang*, Jinqiao Wang, Yi Wu, Hanqing Lu. (2019) Dynamic Collaborative Tracking, IEEE Transactions on Neural Networks and Learning Systems, 30(1): 3035-3046.
Song Bai, Xiang Bai, Zhichao Zhou, Zhaoxiang Zhang, Qi Tian, Longin Jan Latecki. (2017) GIFT: Towards Scalable 3D Shape Retrieval, IEEE Transactions on Multimedia, 19(6): 1257-1271.
Jie Qin, Li Liu, Zhaoxiang Zhang, Yunhong Wang, Ling Shao. (2016) Compressive Sequential Learning for Action Similarity Labeling, IEEE Transactions on Image Processing, 25(2): 756-769.
Jiaxin Chen, Zhaoxiang Zhang*, Yunhong Wang. (2015) Relevance Metric Learning for Person Re-Identification by Exploiting Listwise Similarities, IEEE Transactions on Image Processing, 24(12): 4741-4755.
Wenkai Dong, Zhaoxiang Zhang*, Chunfeng Song, Tieniu Tan*. (2020) Instance Guided Proposal Network for Person Search, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, Washington, USA, June 14-19, 2020.
Wenkai Dong, Zhaoxiang Zhang*, Chunfeng Song, Tieniu Tan*. (2020) Bi-directional Interaction Network for Person Search, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, Washington, USA, June 14-19, 2020.
Junran Peng, Xingyuan Bu, Ming Sun, Zhaoxiang Zhang*, Tieniu Tan, Junjie Yan. (2020) Object Detection in the Wild with Imbalanced Multi-labels, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, Washington, USA, June 14-19, 2020.
Junsong Fan, Zhaoxiang Zhang*, Chunfeng Song, Tieniu Tan. (2020) Learning Integral Objects with Intra-Class Discriminator for Weakly-Supervised Semantic Segmentation, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, Washington, USA, June 14-19, 2020.
Junsong Fan, Zhaoxiang Zhang*, Tieniu Tan, Chunfeng Song, Jun Xiao. (2020) CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic Segmentation, Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, New York, USA, February 7-12, 2020.
Junran Peng, Ming Sun, Zhaoxiang Zhang*, Tieniu Tan, Junjie Yan. (2019) Efficient Neural Architecture Transformation Search in Channel-Level for Object Detection, Thirty-third Conference on Neural Information Processing Systems, NeurIPS 2019, Vancouver, Canada, December 8-14, 2019.
Yanghao Li, Yuntao Chen, Naiyan Wang, Zhaoxiang Zhang*. (2019) Scale-Aware Trident Networks for Object Detection, IEEE International Conference on Computer Vision, ICCV 2019, Seoul, Korea, October 27-November 2, 2019.
Chuanchen Luo, Yuntao Chen, Naiyan Wang, Zhaoxiang Zhang*. (2019) Spectral Feature Transformation for Person Re-Identification, IEEE International Conference on Computer Vision, ICCV 2019, Seoul, Korea, October 27-November 2, 2019.
Junran Peng, Ming Sun, Zhaoxiang Zhang*, Tieniu Tan, Junjie Yan. (2019) POD: Practical Object Detection with Scale-Sensitive Network, IEEE International Conference on Computer Vision, ICCV 2019, Seoul, Korea, October 27-November 2, 2019.
Haiping Wu, Yuntao Chen, Naiyan Wang, Zhaoxiang Zhang. (2019) Sequence Level Semantics Aggregation for Video Object Detection, IEEE International Conference on Computer Vision, ICCV 2019, Seoul, Korea, October 27-November 2, 2019.
Wenkai Dong, Zhaoxiang Zhang*, Tieniu Tan. (2019) Attention-aware Sampling via Deep Reinforcement Learning for Action Recognition, The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, Hawaii, USA, January 27-February 1, 2019.
Qing En, Lijuan Duan, Zhaoxiang Zhang*, Xiang Bai, Yundong Zhang. (2019) Human-like Delicate Region Erasing Strategy for Weakly Supervised Detection, The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, Hawaii, USA, January 27-February 1, 2019.
Wangli Hao, Zhaoxiang Zhang*, He Guan. (2018) Integrating both Visual and Audio Cues for Enhanced Video Caption, The Thirty-Second AAAI Conference on Artificial Intelligence, AAAI 2018, USA, February 2-7, 2018.
Wangli Hao, Zhaoxiang Zhang*, He Guan. (2018) CMCGAN: A Uniform Framework for Cross-Modal Visual-Audio Mutual Generation, The Thirty-Second AAAI Conference on Artificial Intelligence, AAAI 2018, USA, February 2-7, 2018.
Yuntao Chen, Naiyan Wang, Zhaoxiang Zhang*, DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer; The Thirty-Second AAAI Conference on Artificial Intelligence, AAAI 2018, USA, February 2-7, 2018.
Jie Qin, Li Liu, Zhaoxiang Zhang, Yunhong Wang and Ling Shao* (2016), Compressive Sequential Learning for Action Similarity Labeling, IEEE Transactions on Image Processing.
Jiaxin Chen, Zhaoxiang Zhang*, Yunhong Wang (2015): Relevance Metric Learning for Person Re-Identification by Exploiting Listwise Similarities. IEEE Transactions on Image Processing 24(12): 4741-4755
Zhaoxiang Zhang*, Tieniu Tan, Kaiqi Huang, Yunhong Wang (2013): Practical Camera Calibration From Moving Objects for Traffic Scene Surveillance. IEEE Trans. Circuits Syst. Video Techn. 23(3): 518-533
Maodi Hu, Yunhong Wang, Zhaoxiang Zhang* (2013), De Zhang, James J. Little: Incremental Learning for Video-Based Gait Recognition With LBP Flow. IEEE T. Cybernetics 43(1): 77-89
Zhaoxiang Zhang*, Yuhang Zhao, Yunhong Wang, Jianyun Liu, Zhenjun Yao, Jun Tang (2013): Transferring Training Instances for Convenient Cross-View Object Classification in Surveillance. IEEE Transactions on Information Forensics and Security 8(10): 1632-1641
Maodi Hu, Yunhong Wang, Zhaoxiang Zhang*, James J. Little, Di Huang (2013): View-Invariant Discriminative Projection for Multi-View Gait-Based Human Identification. IEEE Transactions on Information Forensics and Security 8(12): 2034-2045
Peijiang Liu*, Yunhong Wang, Di Huang, Zhaoxiang Zhang, Liming Chen (2013): Learning the Spherical Harmonic Features for 3-D Face Recognition. IEEE Transactions on Image Processing 22(3): 914-925
Zhaoxiang Zhang*, Tieniu Tan, Kaiqi Huang, Yunhong Wang (2012): Three-Dimensional Deformable-Model-Based Localization and Recognition of Road Vehicles. IEEE Transactions on Image Processing 21(1): 1-13
Yunhong Wang, Zhaoxiang Zhang*, Weixin Li, Fangyuan Jiang (2012): Combining Tensor Space Analysis and Active Appearance Models for Aging Effect Simulation on Face Images. IEEE Transactions on Systems, Man, and Cybernetics, Part B 42(4): 1107-1118
Maodi Hu*, Yunhong Wang, Zhaoxiang Zhang, De Zhang (2011): Gait-Based Gender Classification Using Mixed Conditional Random Field. IEEE Transactions on Systems, Man, and Cybernetics, Part B 41(5): 1429-1439