基本信息
张彰  男  硕导  中国科学院自动化研究所
电子邮件: zzhang@nlpr.ia.ac.cn
通信地址: 中关村东路95号中科院自动化所
邮政编码:

招生信息

   
招生专业
081104-模式识别与智能系统
招生方向
模式识别、计算机视觉

教育背景

2019-01--2019-12   美国加州大学洛杉矶分校   公派访问学者
2002-09--2009-03   中国科学院自动化研究所   硕博连读/工学博士
1998-09--2002-07   河北工业大学   工学学士

工作经历

工作简历
2009-03~2010-09,新加坡南洋理工大学, Research Fellow

教授课程

视频处理与分析
视频分析与处理

专利与奖励

   
专利成果
[1] 王亮, 张彰, 李达. 基于增量学习的行人属性识别模型训练方法及装置. CN: CN114724174A, 2022-07-08.

[2] 黄凯奇, 张彰, 李俊, 李达, 余铠. 基于Spark的分布式海量视频解析系统. CN: CN108683877A, 2018-10-19.

[3] 冯柏岚, 姚春凤, 黄凯奇, 张彰, 周阳. 行人属性识别与定位方法以及卷积神经网络系统. CN: CN111052126A, 2020-04-21.

[4] 黄凯奇, 张彰, 单言虎. 一种基于隐结构推理的行为识别方法. CN: CN103136540A, 2013-06-05.

[5] 王亮, 张彰, 王开业. 基于慢特征分析的暴力视频检测方法. CN: CN102902981A, 2013-01-30.

[6] 谭铁牛, 黄凯奇, 张彰, 王亮生. 一种基于轨迹序列分析和规则归纳的视频行为识别方法. CN: CN101334845A, 2008-12-31.

出版信息

   
发表论文
[1] Yan Huang, Zhang Zhang, Yan Huang, Qiang Wu, Han Huang, Yi Zhong, Liang Wang. Customized meta-dataset for automatic classifier accuracy evaluation. PATTERN RECOGNITION. 2024, 146: http://dx.doi.org/10.1016/j.patcog.2023.110026.
[2] Yi-Fan Zhang, Xue Wang, Jian Liang, Zhang Zhang, 王亮, Rong Jin, Tieniu Tan. Free lunch for domain adversarial training: Environment label smoothing. The Eleventh International Conference on Learning Representations (ICLR 2023)null. 2023, https://openreview.net/forum?id=GPTjnA57h_3.
[3] Yi-Fan Zhang, Xue Wang, Kexin Jin, Kun Yuan, Zhang Zhang, 王亮, Rong Jin, Tieniu Tan. Adanpc: Exploring non-parametric classifier for test-time adaptation. International Conference on Machine Learning (ICML 2023)null. 2023, https://openreview.net/forum?id=2DiZF15Kgc.
[4] Li, Da, Zhang, Zhang, Shan, Caifeng, Wang, Liang. Incremental Pedestrian Attribute Recognition via Dual Uncertainty-Aware Pseudo-Labeling. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY[J]. 2023, 18: 2622-2636, http://dx.doi.org/10.1109/TIFS.2023.3268887.
[5] Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Jindong Wang, Jian Liang, Zhang Zhang, Baosheng Yu, 王亮, Dacheng Tao, Xing Xie. Domain-Specific Risk Minimization for Domain Generalization. Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2023)null. 2023, https://dl.acm.org/doi/abs/10.1145/3580305.3599313.
[6] Zhang, YiFan, Zhang, Zhang, Li, Da, Jia, Zhen, Wang, Liang, Tan, Tieniu. Learning Domain Invariant Representations for Generalizable Person Re-Identification. IEEE TRANSACTIONS ON IMAGE PROCESSING[J]. 2023, 32: 509-523, http://dx.doi.org/10.1109/TIP.2022.3229621.
[7] Ming-Zhe Li, Zhen Jia, Zhang Zhang, Zhanyu Ma, 王亮. Multi-semantic Fusion Model For Generalized Zero-Shot Skeleton-Based Action Recognition. International Conference on Image and Graphics (ICIG 2023)null. 2023, https://link.springer.com/chapter/10.1007/978-3-031-46305-1_6.
[8] Zhen Jia, Zhang Zhang, Caifeng Shan, Liang Wang, Tieniu Tan. Dual-focus transfer network for zero-shot learning. NEUROCOMPUTING[J]. 2023, 541: http://dx.doi.org/10.1016/j.neucom.2023.126264.
[9] Zhang, YiFan, Ren, Weiqiang, Zhang, Zhang, Jia, Zhen, Wang, Liang, Tan, Tieniu. Focal and efficient IOU loss for accurate bounding box regression. NEUROCOMPUTING[J]. 2022, 506: 146-157, http://dx.doi.org/10.1016/j.neucom.2022.07.042.
[10] Liu, Zhenyu, Zhang, Zhang, Li, Da, Zhang, Peng, Shan, Caifeng. Dual-branch self-attention network for pedestrian attribute recognition. PATTERN RECOGNITION LETTERS[J]. 2022, 163: 112-120, http://dx.doi.org/10.1016/j.patrec.2022.10.003.
[11] Chen, Wentao, Zhang, Zhang, Wang, Wei, Wang, Liang, Wang, Zilei, Tan, Tieniu. Few-shot learning with unsupervised part discovery and part-aligned similarity. PATTERN RECOGNITION[J]. 2022, 133: http://dx.doi.org/10.1016/j.patcog.2022.108986.
[12] Song, YiFan, Zhang, Zhang, Shan, Caifeng, Wang, Liang. Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)[J]. 2022, [13] Song, YiFan, Zhang, Zhang, Shan, Caifeng, Wang, Liang. Richly Activated Graph Convolutional Network for Robust Skeleton-Based Action Recognition. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY[J]. 2021, 31(5): 1915-1925, http://dx.doi.org/10.1109/TCSVT.2020.3015051.
[14] Hu, Xuecai, Zhang, Zhang, Shan, Caifeng, Wang, Zilei, Wang, Liang, Tan, Tieniu. Meta-USR: A Unified Super-Resolution Network for Multiple Degradation Parameters. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS[J]. 2021, 32(9): 4151-4165, http://dx.doi.org/10.1109/TNNLS.2020.3016974.
[15] Jia, Zhen, Zhang, Zhang, Wang, Liang, Shan, Caifeng, Tan, Tieniu. Deep Unbiased Embedding Transfer for Zero-Shot Learning. IEEE TRANSACTIONS ON IMAGE PROCESSING[J]. 2020, 29: 1958-1971, http://dx.doi.org/10.1109/TIP.2019.2947780.
[16] Zhao, Cairong, Lv, Xinbi, Zhang, Zhang, Zuo, Wangmeng, Wu, Jun, Miao, Duoqian. Deep Fusion Feature Representation Learning With Hard Mining Center-Triplet Loss for Person Re-Identification. IEEE TRANSACTIONS ON MULTIMEDIA[J]. 2020, 22(12): 3180-3195, http://dx.doi.org/10.1109/TMM.2020.2972125.
[17] Song, YiFan, Zhang, Zhang, Shan, Caifeng, Wang, Liang. Richly Activated Graph Convolutional Network for Robust Skeleton-based Action Recognition. 2020, http://arxiv.org/abs/2008.03791.
[18] Song, YiFan, Zhang, Zhang, Shan, Caifeng, Wang, Liang. Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition. 2020, http://arxiv.org/abs/2010.09978.
[19] Jain, Deepak Kumar, Zhang, Zhang, Huang, Kaiqi. Multi angle optimal pattern-based deep learning for automatic facial expression recognition. PATTERN RECOGNITION LETTERS[J]. 2020, 139: 157-165, http://dx.doi.org/10.1016/j.patrec.2017.06.025.
[20] Liu, Jinde, Zhang, Zhang, Shan, Caifeng, Tan, Tieniu. Kinematic skeleton graph augmented network for human parsing. NEUROCOMPUTING[J]. 2020, 413: 457-470, http://dx.doi.org/10.1016/j.neucom.2020.07.002.
[21] Li, Da, Zhang, Zhang, Shan, Caifeng, Wang, Liang, Tan, Tieniu, IEEE. A Comprehensive Study on Large-Scale Person Retrieval in Real Surveillance Scenarios. 2019 16TH IEEE INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL BASED SURVEILLANCE (AVSS)null. 2019, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000524684300031.
[22] Yang, Wenjie, Huang, Houjing, Zhang, Zhang, Chen, Xiaotang, Huang, Kaiqi, Zhang, Shu, IEEE Comp Soc. Towards Rich Feature Discovery with Class Activation Maps Augmentation for Person Re-Identification. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)null. 2019, 1389-1398, [23] Li, Da, Zhang, Zhang, Yu, Kai, Huang, Kaiqi, Tan, Tieniu. ISEE: An Intelligent Scene Exploration and Evaluation Platform for Large-Scale Visual Surveillance. IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS[J]. 2019, 30(12): 2743-2758, http://dx.doi.org/10.1109/TPDS.2019.2921956.
[24] Li, Yabei, Zhang, Zhang, Cheng, Yanhua, Wang, Liang, Tan, Tieniu. MAPNet: Multi-modal attentive pooling network for RGB-D indoor scene classification. PATTERN RECOGNITION[J]. 2019, 90: 436-449, http://ir.ia.ac.cn/handle/173211/23477.
[25] Li, Da, Li, Dangwei, Zhang, Zhang, Wang, Liang, Tan, Tieniu, IEEE. UNSUPERVISED CROSS-DOMAIN PERSON RE-IDENTIFICATION: A NEW FRAMEWORK. 2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)null. 2019, 1222-1226, [26] Song, YiFan, Zhang, Zhang, Wang, Liang, IEEE. Richly Activated Graph Convolutional Network for Action Recognition with Incomplete Skeletons. 2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)null. 2019, 1-5, [27] Yabei Li, Zhang Zhang, Yanhua Cheng, Liang Wang, Tieniu Tan. Corrigendum to "MAPNet: Multi-modal attentive pooling network for RGB-D indoor scene classification" Pattern Recognition 90 (2019) 436-449. PATTERN RECOGNITION. 2019, 94: 250-250, http://dx.doi.org/10.1016/j.patcog.2019.05.034.
[28] Li, Yabei, Zhang, Zhang, Cheng, Yanhua, Wang, Liang, Tan, Tieniu. MAPNet: Multi-modal attentive pooling network for RGB-D indoor scene classification (vol 90, pg 436, 2019). PATTERN RECOGNITIONnull. 2019, 94: 250-250, [29] Li, Dangwei, Zhang, Zhang, Chen, Xiaotang, Huang, Kaiqi. A Richly Annotated Pedestrian Dataset for Person Retrieval in Real Surveillance Scenarios. IEEE TRANSACTIONS ON IMAGE PROCESSING[J]. 2019, 28(4): 1575-1590, http://ir.ia.ac.cn/handle/173211/25707.
[30] Huang, Houjing, Li, Dangwei, Zhang, Zhang, Chen, Xiaotang, Huang, Kaiqi, IEEE. Adversarially Occluded Samples for Person Re-identification. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)null. 2018, 5098-5107, [31] Jain, Deepak Kumar, Zhang, Zhang, Huang, Kaiqi. Random walk-based feature learning for micro-expression recognition. PATTERN RECOGNITION LETTERS[J]. 2018, 115(XX): 92-100, http://dx.doi.org/10.1016/j.patrec.2018.02.004.
[32] Li, Dangwei, Chen, Xiaotang, Zhang, Zhang, Huang, Kaiqi, IEEE. POSE GUIDED DEEP MODEL FOR PEDESTRIAN ATTRIBUTE RECOGNITION IN SURVEILLANCE SCENARIOS. 2018 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME)null. 2018, [33] Zhao, Weiqi, Zhang, Zhang, Huang, Kaiqi. Gestalt laws based tracklets analysis for human crowd understanding. PATTERN RECOGNITION[J]. 2018, 75: 112-127, http://dx.doi.org/10.1016/j.patcog.2017.06.020.
[34] Zhang Zhang, Chunfeng Yao, Bailan Feng, Kaiqi Huang, Dangwei Li, Biao Leng, Kai Yu, Yang Zhou. Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization. 2017, http://arxiv.org/abs/1611.05603.
[35] Zhang Zhang, Chen Xiaotang, Kaiqi Huang, Dangwei Li, Huang Kaiqi. Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification. 2017, http://arxiv.org/abs/1710.06555.
[36] Li, Dangwei, Chen, Xiaotang, Zhang, Zhang, Huang, Kaiqi, IEEE. Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)null. 2017, 7398-7407, [37] Li Da, Zhang Zhang, Tan Tieniu, Yang J, Hu Q, Cheng MM, Wang L, Liu Q, Bai X, Meng D. Large-Scale Slow Feature Analysis Using Spark for Visual Object Recognition. COMPUTER VISION, PT IIInull. 2017, 773: 132-142, [38] Huang Kaiqi, Zhang Zhang, Zhao Weiqi, Kaiqi Huang. Joint Crowd Detection and Semantic Scene Modeling Using a Gestalt Laws-based Similarity. PROCINTERNATIONALCONFERENCEONIMAGEPROCESSINGICIP2016null. 2016, http://ir.ia.ac.cn/handle/173211/12663.
[39] Jain Deepak Kumar, Zhang Zhang, Huang Kaiqi, Zhang Z, Huang K. Hybrid Patch Based Diagonal Pattern Geometric Appearance Model for Facial Expression Recognition. INTELLIGENT VISUAL SURVEILLANCE (IVS 2016)null. 2016, 664: 107-113, [40] Jain Deepak Kumar, Zhang Zhang, Huang Kaiqi, Zhang Z, Huang K. Hybrid Patch Based Diagonal Pattern Geometric Appearance Model for Facial Expression Recognition. INTELLIGENT VISUAL SURVEILLANCE (IVS 2016)null. 2016, 664: 107-113, [41] 张彰, 单言虎, HuangKaiqi, 黄凯奇. 人的视觉行为识别研究回顾、现状及展望. 计算机研究与发展[J]. 2016, 53(1): 93-112, http://lib.cqvip.com/Qikan/Article/Detail?id=667688332.
[42] zhao weiqi, zhang zhang, 黄凯奇. Joint Crowd Ddtection and Semantic Scene Modeling Using a Gestalt Laws-based Similarity. 2016, http://ir.ia.ac.cn/handle/173211/20245.
[43] Zhang, Zhang, Huang, Kaiqi, Tan, Tieniu, Yang, Peipei, Li, Jun, IEEE. ReD-SFA: Relation Discovery Based Slow Feature Analysis for Trajectory Clustering. 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)null. 2016, 752-760, [44] Shan, Yanhu, Zhang, Zhang, Yang, Peipei, Huang, Kaiqi. Adaptive Slice Representation for Human Action Classification. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY[J]. 2015, 25(10): 1624-1636, http://dx.doi.org/10.1109/TCSVT.2014.2376136.
[45] Shan Yanhu, Huang Kaiqi, Zhang Zhang. Learning Skeleton Stream Patterns with Slow Feature Analysis for Action Recognition. PROC. EUROPE CONFERENCE ON COMPUTER VISION WORKSHOPSnull. 2014, http://ir.ia.ac.cn/handle/173211/12664.
[46] Liang Wang, Kaiye Wang, Zhang Zhang. Violence detection in video by slow feature analysis. 2012, 137-144, http://ir.ia.ac.cn/handle/173211/14073.
[47] Dong Wang, Zhang Zhang, Wei Wang, Liang Wang, Tieniu Tan. Baseline results for violence detection in still images. PROC. IEEE INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL-BASED SURVEILLANCEnull. 2012, 54-57, http://ir.ia.ac.cn/handle/173211/13825.
[48] Zhang, Zhang, Tao, Dacheng. Slow Feature Analysis for Human Action Recognition. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE[J]. 2012, 34(3): 436-450, http://dx.doi.org/10.1109/TPAMI.2011.157.
[49] Yongming Chen, Wang Liang, Wang Wei, Zhang Zhang. CONTINUUM REGRESSION FOR CROSS-MODAL MULTIMEDIA RETRIEVAL. INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)null. 2012, 1949-1952, http://ir.ia.ac.cn/handle/173211/5411.
[50] Wang Kaiye, Zhang Zhang, Wang Liang, Liu CL, Zhang CS, Wang L. Violence Video Detection by Discriminative Slow Feature Analysis. PATTERN RECOGNITIONnull. 2012, 321: 137-+, [51] Shan Yanhu, Huang Kaiqi, Zhang Zhang. Interest point selection with spatio-temporal context for realistic action recognition. PROC. INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL-BASED SURVEILLANCE (AVSS) 2012null. 2012, http://ir.ia.ac.cn/handle/173211/12665.
[52] Zhang, Zhang, Cheng, Jun, Li, Jun, Bian, Wei, Tao, Dacheng. Segment-Based Features for Time Series Classification. COMPUTER JOURNAL[J]. 2012, 55(9): 1088-1102, http://dx.doi.org/10.1093/comjnl/bxs029.
[53] Zhang, Zhang, Tan, Tieniu, Huang, Kaiqi. An Extended Grammar System for Learning and Recognizing Complex Visual Events. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE[J]. 2011, 33(2): 240-255, http://dx.doi.org/10.1109/TPAMI.2010.60.
[54] Huang Kaiqi, Zhang Zhang. An X-T slice based method for action recognition. IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)null. 2011, 1897-1903, http://ir.ia.ac.cn/handle/173211/5357.
[55] Zhang Zhang, Huang Kaiqi, Tan Tieniu. Multi-Thread Parsing for Recognizing Complex Events in Videos. PROC. OF THE 10TH EUROPEAN CONFERENCE ON COMPUTER VISION (ECCV) 2008null. 2008, http://ir.ia.ac.cn/handle/173211/12666.
[56] Zhang Zhang, Huang Kaiqi, Tan Tieniu, Forsyth D, Torr P, Zisserman A. Multi-thread Parsing for Recognizing Complex Events in Videos. COMPUTER VISION - ECCV 2008, PT III, PROCEEDINGSnull. 2008, 5304: 738-751, [57] Zhang Zhang, Huang Kaiqi, Tan Tieniu, Wang Liangsheng. Trajectory Series Analysis based Event Rule Induction for Visual Surveillance. PROC. IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) 2007null. 2007, http://ir.ia.ac.cn/handle/173211/12667.
[58] Zhang, Z, Huang, KQ, Tan, TN. Complex activity representation and recognition by extended stochastic grammar. COMPUTER VISION - ACCV 2006, PT I[J]. 2006, 3851(1): 150-159, http://www.irgrid.ac.cn/handle/1471x/1005782.
[59] Zhang Zhang, Huang Kaiqi, Tan Tieniu. Comparison of similarity measures for trajectory clustering in outdoor surveillance scenes. 18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 3, PROCEEDINGS[J]. 2006, 1135-+, [60] Zhang Zhang, Huang Kaiqi, Tan Tieniu. Comparison of Similarity Measures for Trajectory Clustering in Outdoor Surveillance Scene. PROC. THE 18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR) 2016null. 2006, http://ir.ia.ac.cn/handle/173211/12668.

科研活动

   
科研项目
( 1 ) 面向智能视觉监控的大规模慢特征学习研究, 负责人, 国家任务, 2015-01--2018-12
( 2 ) 仿生眼感知与识别处理, 负责人, 国家任务, 2015-01--2018-12
( 3 ) 基于非欧氏空间的视觉计算理论与方法, 参与, 国家任务, 2012-01--2016-12
( 4 ) 地外星表对象多维度信息的样本生成与特征标注模块, 负责人, 境内委托项目, 2022-04--2022-10
( 5 ) 滑雪场景中图像智能分析技术, 负责人, 境内委托项目, 2021-04--2022-03
( 6 ) 隐能量场诱导的可解释层级复合模型, 参与, 国家任务, 2021-01--2024-12
( 7 ) 行人多特征识别的改进和优化, 负责人, 境内委托项目, 2019-06--2020-06
( 8 ) 结合影像学与行为分析的神经系统退行性和发育障碍疾病辅助诊断系统, 负责人, 境内委托项目, 2018-12--2024-06
( 9 ) 面向人机协同任务的情境认知与效能优化, 参与, 国家任务, 2023-03--2026-02
( 10 ) 面向开放环境的多模态交互式行人检索, 负责人, 国家任务, 2024-01--2027-12
参与会议
(1)ReD-SFA: Relation Discovery Based Slow Feature Analysis for Trajectory Clustering   2016-06-27