苗振江
博士、教授、文化和旅游部民族民间文艺发展中心数字文化研究基地主任
博士、教授、文化和旅游部民族民间文艺发展中心数字文化研究基地主任
办公电话:51683149 | 电子邮件: zjmiao@bjtu.edu.cn |
通讯地址:北京交通大学信息所 | 邮编:100044 |
1987年本科毕业于清华大学无线电系, 1990和1994年于北方交通大学获硕士和博士学位。
近几年代表性论文(IEEE Trans期刊论文):
1. Wanru Xu; Zhenjiang Miao; Jian Yu; Yi Tian; Lili Wan; Qiang Ji ; Bridging Video and Text: A Two-Step Polishing Transformer for Video Captioning, IEEE Transactions on Circuits and Systems for Video Technology, 2022, 32(9): 6293-6307 (一区)
2. Min Li; Zhenjiang Miao; Xiao-Ping Zhang; Wanru Xu; Cong Ma; Ningwei Xie ; Rhythm-Aware Sequence-to-Sequence Learning for Labanotation Generation With Gesture-Sensitive Graph Convolutional Encoding, IEEE Transactions on Multimedia, 2022, 24: 1488-1502 (一区)
3. Shaoyue Song; Zhenjiang Miao; Hongkai Yu; Jianwu Fang; Kang Zheng; Cong Ma; Song Wang ; Deep Domain Adaptation Based Multi-Spectral Salient Object Detection, IEEE Transactions on Multimedia, 2022, 24: 128-140 (一区)
4. Ningwei Xie; Zhenjiang Miao; Xiao-Ping Zhang; Wanru Xu; Min Li; Jiaji Wang ; Sequential Gesture Learning for Continuous Labanotation Generation based on the Fusion of Graph Neural Networks, IEEE Transactions on Circuits and Systems for Video Technology, 2022, 32(6): 3722-3734 (一区)
5. Wanru Xu, Jian Yu, Zhenjiang Miao, Lili Wan, Yi Tian, Qiang Ji: Deep Reinforcement Polishing Network for Video Captioning. IEEE Transactions on Multimedia . Vol. 23, June 2021, pp.1772-1784 (一区)
6. Wanru Xu; Zhenjiang Miao; Jian Yu; Qiang Ji ; Deep reinforcement learning for weak human activity localization, IEEE Transactions on Image Processing, 2020, 29: 1522-1535 (一区)
7. Wanru Xu, Jian Yu, Zhenjiang Miao, et al. Spatio-temporal deep Q-networks for human activity localization. IEEE Transactions on Circuits and Systems for Video Technology, 2020,30(9):2984–2999. (一区)
8. Cong Ma, Zhenjiang Miao, Xiao-Ping Zhang, Min Li. A Saliency Prior Context Model for Real-Time Object Tracking. IEEE Transactions on Multimedia, vol. 19, no. 11, pp. 2415-2424, November 2017 (一区)
9. Wanru Xu; Zhenjiang Miao; Zhang X P, et al. A Hierarchical Spatio-Temporal Model for Human Activity Recognition. IEEE Transactions on Multimedia, 2017, 19(7): 1494-1509. (一区)
10. Jie Geng, Zhenjiang Miao, Xiao-Ping Zhang. Efficient Heuristic Methods for Multimodal Fusion and Concept Fusion in Video Concept Detection. IEEE Transaction on Multimedia,Volume 17, Number 4, April 2015,pp.498 – 511. (一区)
11. Shu Wang, Jian Zhang, Tony X. Han, Zhenjiang Miao. Sketch-based Image Retrieval through Hypothesis Driven Object Boundary Selection with HLR Descriptor. IEEE Transaction on Multimedia,Vol.17, No.7, July 2015, pp.1045-1057. (一区)
12. Yanli Wan, Zhenjiang Miao et al, A Quasi-dense Matching Approach and Its Calibration Application with Internet Photos, IEEE Transactions on Cybernetics, Vol. 45, No. 3, March 2015 (一区)
13. Yuan Shen,Zhenjiang Miao, Multi-Human Tracking Based on Spatial-Temporal Appearance Match, IEEE Transactions on Circuits and Systems for Video Technology, VOL. 24, NO. 3, MARCH 2014 (一区)
14. Yanli Wan, Zhenjiang Miao, Xiao-Ping Zhang, Zhen Tang, Illumination Robust Video Foreground Prediction Based on Color Recovering, IEEE Transaction On Multimedia, VOL. 16, NO. 3, APRIL 2014 (一区)
15. Ping Guo, Zhenjiang Miao,Xiao-Ping Zhang,Coupled Observation Decomposed Hidden Markov Model for Multi-person Activity Recognition,IEEE Transactions on Circuits and Systems for Video Technology, Vol.22, No.9,2012,pp.1306-1320 (一区)
代表性授权发明专利:
(1)苗振江,郭萍,基于分层观测向量分解的隐马尔科夫模型的行为识别方法,ZL 2009 1 0236898.1
(2)苗振江,唐振,一种自动式的图像颜色协调化方法和系统,ZL 2009 1 0236097.5
(3)苗振江,万艳丽,适用于宽基线图像密集匹配的描述符的构建方法, ZL 2011 1 0185779.5
(4)苗振江,钟岑岑,多模态数据的融合概率潜在语义分析方法,ZL2011 1 0180025.0
(5)苗振江,耿杰,一种光照自适应的人体肤色检测方法,ZL2011 1 0185739.0