张冬明-中国科学院大学-UCAS

研究领域

多媒体数据处理与分析

机器学习

招生信息

招生专业

081203-计算机应用技术
083900-网络空间安全

招生方向

多媒体信号编码
多媒体数据处理与分析
机器学习

教育背景

2002-09--2006-07 中科院计算所博士

工作经历

2022-09至今人民日报社传播内容认知全国重点实验室研究员

2017-04~2022-09 国家计算机网络应急技术处理协调中心研究员

2006-07~2017-03 中国科学院计算技术研究所副研究员

专利与奖励

奖励信息

（1）大规模网络视频处理与内容分析关键技术及应用, 一等奖, 省级, 2014
（2）大规模网络视频内容分析关键技术及应用, 一等奖, 部委级, 2012
（3） Best Paper, 一等奖, 其他, 2010

专利成果

（ 1 ）一种联合轻量化网络和个性化特征提取的字符图片检测及快速匹配方法, 发明专利, 2021, 第 1 作者, 专利号: CN112560858A

（ 2 ）基于多处理器平台的视觉特征并行快速匹配方法和系统, 专利授权, 2021, 第 1 作者, 专利号: CN108052535B

（ 3 ）基于跨层特征提取的像素级台标识别网络的台标分割方法, 发明专利, 2018, 第 4 作者, 专利号: CN108009637A

（ 4 ）基于排序测度特征的图像检索方法及系统, 发明专利, 2018, 第 2 作者, 专利号: CN104408092B

（ 5 ）局部特征点筛选方法及系统, 发明专利, 2017, 第 1 作者, 专利号: CN106372111A

（ 6 ）面向排序测度特征的图像匹配方法及系统, 发明专利, 2015, 第 1 作者, 专利号: CN104484869A

出版信息

[1] Bing Li, Jiaxin Chen, Dongming Zhang. Representation Learning for Compressed Video Action Recognition via Attentive Cross-modal Interaction with Motion Enhancement. IJCAI2022null. 2022,

[2] Xuena Ren, Dongming Zhang, bao xiuguo. Person Re-identification with a Cloth-Changing Aware Transformer. IJCNN2022null. 2022,

[3] 任雪娜, Dongming Zhang, bao xiuguo, yongdong zhang. S2-Net:Semantic and Saliency Attention Network for Person Re-Identification. Transaction on Multimedia[J]. 2022, 1-13,

[4] Xuena Ren, Dongming Zhang, bao xiuguo. Double Granularity Relation Network with Self-Criticism for Occluded Person Re-identification. ICMM2022null. 2022,

[5] 张广朋, 张冬明, 张菁. 基于数据合成和度量学习的台标检测与识别. 软件学报[J]. 2022, 33(9):

[6] 任雪娜, 张冬明, 包秀国. 语义引导的遮挡行人再识别注意力网络. 通信学报[J]. 2021, 42(10): 106-116,

[7] 袁庆升, 靳国庆, 张冬明, 包秀国. 仿视网膜采样的二进制描述子. 通信学报[J]. 2019, 40(1): 15-23, http://lib.cqvip.com/Qikan/Article/Detail?id=7001188992.

[8] Jin, Guoqing, Shen, Shiwei, Zhang, Dongming, Dai, Feng, Zhang, Yongdong, IEEE. APE-GAN: ADVERSARIAL PERTURBATION ELIMINATION WITH GAN. 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)null. 2019, 3842-3846,

[9] 张冬明, 靳国庆, 代锋, 袁庆升, 包秀国, 张勇东. 基于深度融合的显著性目标检测算法. 计算机学报[J]. 2019, 42(9): 2076-2086, http://dx.doi.org/10.11897/SP.J.1016.2019.02076.

[10] 徐佳宇, 张冬明, 靳国庆, 包秀国, 袁庆升, 张勇东. PNET：像素级台标识别网络. 计算机辅助设计与图形学学报[J]. 2018, 30(10): 1878-1889, http://lib.cqvip.com/Qikan/Article/Detail?id=7000866110.
[11] Zhang, Dongming, Tang, Jingya, Jin, Guoqing, Zhang, Yongdong, Tian, Qi. Region similarity arrangement for large-scale image retrieval. NEUROCOMPUTING[J]. 2018, 272: 461-470, https://www.webofscience.com/wos/woscc/full-record/WOS:000413821400048.

[12] Zhang, Xishan, Gao, Ke, Zhang, Yongdong, Zhang, Dongming, Li, Jintao, Tian, Qi, IEEE. Task-Driven Dynamic Fusion: Reducing Ambiguity in Video Description. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)null. 2017, 6250-6258,

[13] Zhang, Xishan, Jia, Jia, Gao, Ke, Zhang, Yongdong, Zhang, Dongming, Li, Jintao, Tian, Qi. Trip Outfits Advisor: Location-Oriented Clothing Recommendation. IEEE TRANSACTIONS ON MULTIMEDIA[J]. 2017, 19(11): 2533-2544, https://www.webofscience.com/wos/woscc/full-record/WOS:000413068200014.

[14] Yao, Hantao, Zhang, Shiliang, Zhang, Dongming, Zhang, Yongdong, Li, Jintao, Wang, Yu, Tian, Qi, IEEE. LARGE-SCALE PERSON RE-IDENTIFICATION AS RETRIEVAL. 2017 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME)null. 2017, 1440-1445,

[15] Yao, Hantao, Zhang, Dongming, Li, Jintao, Zhou, Jianshe, Zhang, Shiliang, Zhang, Yongdong. DSP: Discriminative Spatial Part modeling for Fine-Grained Visual Categorization. IMAGE AND VISION COMPUTING[J]. 2017, 63: 24-37, http://dx.doi.org/10.1016/j.imavis.2017.05.003.

[16] 袁庆升, 张冬明, 靳国庆, 刘菲, 包秀国. 视频检索中图像信息量度量. 通信学报[J]. 2016, 37(2): 2016033-1, http://lib.cqvip.com/Qikan/Article/Detail?id=668040329.
[17] Zhuang, Dongye, Zhang, Dongming, Li, Lintao, Tian, Qi. Binary feature from intensity quantization and weakly spatial contextual coding for image search. INFORMATION SCIENCES[J]. 2015, 302: 94-107, https://www.webofscience.com/wos/woscc/full-record/WOS:000350924000007.

[18] Yao Hantao, Zhang Shiliang, Xie Fei, Zhang Yongdong, Zhang Dongming, Su Yu, Tian Qi, Altintas O, Zhang J. Orientational Spatial Part Modeling for Fine-Grained Visual Categorization. 2015 IEEE THIRD INTERNATIONAL CONFERENCE ON MOBILE SERVICES MS 2015null. 2015, 360-367,

[19] Ye, Tiancai, Zhang, Dongming, Gao, Ke, Jin, Guoqing, Zhang, Yongdong, Yuan, Qingsheng, IEEE. SALIENT REGION DETECTION : INTEGRATE BOTH GLOBAL AND LOCAL CUES. 2014 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME)null. 2014,

[20] 包秀国, 张冬明, 张曦珊, 刘菲. 基于选择性Gabor滤波器组的网络视频台标识别. 计算机辅助设计与图形学学报[J]. 2014, 26(2): 248-257, http://lib.cqvip.com/Qikan/Article/Detail?id=48679650.

[21] 庄东晔, 张冬明, 张勇东, 李锦涛. 随机亮度差量化的二进制特征描述. 中国图象图形学报[J]. 2014, 19(4): 630-636,

[22] Zhang Dongming. Monte Carlo Sampling based Salient Region Detection. ACM International Conference on Multimedia Retrieval. 2014,

[23] Zhang Dongming. Spatial HOG based TV logo detection. ACM Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service. 2013,

[24] Zhang Dongming. Improved binary feature matching through fusion of hamming distance and fragile bit weight. Proceedings of the 3rd ACM international workshop on Interactive multimedia on mobile and portable devices. 2013,

[25] Gu, Xiaoguang, Zhang, Dongming, Zhang, Yongdong, Li, Jintao, Zhang, Lei, IEEE. A VIDEO COPY DETECTION ALGORITHM COMBINING LOCAL FEATURE'S ROBUSTNESS AND GLOBAL FEATURE'S SPEED. 2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)null. 2013, 1508-1512,

[26] Mengmeng ZhangJianfeng QuHuihui Bai. Fast Intra Prediction Mode Decision Algorithm for HEVC. Telkomnika Indonesion Journal of Electrical Engineering[J]. 2013, 11(10): http://gooa.las.ac.cn/external/index?type=-1&pid=981588.

[27] Zhang Dongming. Efficient Partial Decoding Scheme for Intra Frame in H.264/AVC Stream. PCM2012. 2012,

[28] Zhang Dongming. Improved motion estimation based on motion region identification. International Conference on Systems and Informatics (ICSAI)2012. 2012,

[29] Wang, Wenying, Zhang, Dongming, Zhang, Yongdong, Li, Jintao, Gu, Xiaoguang. Robust Spatial Matching for Object Retrieval and Its Parallel Implementation on GPU. IEEE TRANSACTIONS ON MULTIMEDIA[J]. 2011, 13(6): 1308-1318, https://www.webofscience.com/wos/woscc/full-record/WOS:000297343400011.

[30] Wang Wenying, Zhang Dongming, Zhang Yongdong, Li Jintao, IEEE. FAST AND ROBUST SPATIAL MATCHING FOR OBJECT RETRIEVAL. 2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSINGnull. 2010, 1238-1241,

[31] 汪文英, 张冬明, 张勇东, 李锦涛. 利用仿射变换的快速空间关系验证. 计算机辅助设计与图形学学报[J]. 2010, 625-631, http://lib.cqvip.com/Qikan/Article/Detail?id=33524002.

[32] Wang, Wenying, Zhang, Dongming, Zhang, Yongdong, Li, Jintao, Gu, Xiaoguang, IEEE. PARALLEL SPATIAL MATCHING FOR OBJECT RETRIEVAL IMPLEMENTED ON GPU. 2010 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME 2010)null. 2010, 890-895,

[33] Zhang Dongming. Compressive video sensing based on user attention model. PCS2010. 2010,

[34] 张勇东, 张冬明, 郭俊波, 唐胜. 压缩域快速视频拷贝检测算法. 通信学报[J]. 2009, 135-140, http://lib.cqvip.com/Qikan/Article/Detail?id=30057480.

[35] 郭俊波, 张冬明, 张勇东, 徐杰, 汪文英. 面向互联网视频的人体皮肤区域检测. 通信学报[J]. 2009, 6-10, http://lib.cqvip.com/Qikan/Article/Detail?id=30213587.

科研活动

科研项目

（ 1 ）基于感兴趣区域的互联网级在线视频拷贝检测技术, 负责人, 国家任务, 2013-01--2016-12
（ 2 ）基于视觉关注度的复杂度可分级视频编码研究, 负责人, 国家任务, 2009-01--2011-12
（ 3 ）视频检索系统, 负责人, 国家任务, 2013-03--2014-03
（ 4 ）视频分析平台, 负责人, 国家任务, 2016-08--2017-07
（ 5 ）基于像素级深度网络学习的互联网视频嵌入式标识识别, 负责人, 国家任务, 2017-01--2020-12
（ 6 ）实时网络流量解码还原技术研究, 负责人, 国家任务, 2018-12--2022-12
（ 7 ）新型视频内容检测, 负责人, 国家任务, 2016-12--2019-11
（ 8 ） “新一代人工智能”——视频场景推理, 参与, 国家任务, 2019-12--2023-12