许万茹
博士、副教授
博士、副教授
办公电话: | 电子邮件: xwanru@bjtu.edu.cn |
通讯地址:土建424 | 邮编:100044 |
研究兴趣包括计算机视觉、深度学习、视频理解、行为识别、视频描述等;
招生信息:欢迎对以上方向感兴趣的同学加入
现招收2025级硕士研究生(包括保研和考研)及博士研究生,
招收专业:计算机科学与技术、计算机技术、 人工智能、控制科学与工程、新一代电子信息技术。
2022/01 -至今, 北京交通大学计算机与信息技术学院,信息科学研究所,副教授
2020/07 - 2021/12, 北京交通大学计算机与信息技术学院,信息科学研究所,讲师
2018/07 - 2020/07,北京交通大学计算机与信息技术学院,博士后,合作导师:于剑
2016/10 - 2017/10,美国伦斯勒理工学院,访问学者,合作导师:Qiang Ji
2011/09 - 2018/07,北京交通大学,信号与信息处理,博士
2007/09 - 2011/07,北京交通大学,生物医学工程,学士
Xu, Wanru, Zhenjiang Miao, Jian Yu, Yigang Cen, Yi Tian, Lili Wan and Qiang Ji. Boosting Semi-Supervised Video Captioning via Learning Candidates Adjusters. ACM Transactions on Multimedia Computing Communications and Applications (2024)
Xu W, Miao Z, Yu J, et al. Bridging Video and Text: A Two-Step Polishing Transformer for Video Captioning[J]. IEEE Transactions on Circuits and Systems for Video Technology(TCSVT), 32 (2022): 6293-6307.Tian, Y., Zhang, Y., Huang, Y., Xu, W., & Ding, Z. (2022). Differential Refinement Network for Zero-Shot Learning. IEEE transactions on neural networks and learning systems.
Xie, N., Miao, Z., Zhang, X., Xu, W., Li, M., & Wang, J. (2022). Sequential Gesture Learning for Continuous Labanotation Generation Based on the Fusion of Graph Neural Networks. IEEE Transactions on Circuits and Systems for Video Technology(TCSVT), 32, 3722-3734.
Li, M., Miao, Z., Zhang, X., Xu, W., Ma, C., & Xie, N. (2022). Rhythm-Aware Sequence-to-Sequence Learning for Labanotation Generation With Gesture-Sensitive Graph Convolutional Encoding. IEEE Transactions on Multimedia(TMM), 24, 1488-1502.
Xu W, Yu J, Miao Z, et al. Deep Reinforcement Polishing Network for Video Captioning[J]. IEEE Transactions on Multimedia(TMM), 2021,23: 1772-1784.
Xu W, Miao Z, Yu J, et al. Deep reinforcement learning for weak human activity localization[J]. IEEE Transactions on Image Processing(TIP), 2020, 29: 1522-1535.
Xu W, Yu J, Miao Z, et al. Spatio-temporal deep Q-networks for human activity localization[J]. IEEE Transactions on Circuits and Systems for Video Technology(TCSVT), 2020,30(9):2984–2999.
Xu W, Yu J, Miao Z, et al. Prediction-CGAN: Human Action Prediction with Conditional Generative Adversarial Networks[C], In Proceedings of the 27th ACM International Conference on Multimedia (ACM MM), 2019, 611–619.
Rui Zhao, Xu W, Hui Su, Qiang Ji, Bayesian Hierarchical Dynamic Model for Human Action Recognition, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, California, USA,2019.6.16-2019.6.20.
Xu W, Miao Z, Yu J, et al. Action recognition and localization with spatial and temporal contexts[J]. Neurocomputing, 2019, 333: 351-363.
Xu W, Miao Z, Zhang X P, et al. A Hierarchical Spatio-Temporal Model for Human Activity Recognition[J]. IEEE Transactions on Multimedia(TMM), 2017, 19(7): 1494-1509.
Xu W, Miao Z, Tian Y. A Novel Mid-Level Distinctive Feature Learning for Action Recognition via Diffusion Map[J]. Neurocomputing, 2016, 218:185-196.
Xu W, Miao Z, Zhang Q. Projection transform on spatio-temporal context for action recognition[J]. Multimedia Tools & Applications, 2015, 74(18):7711-7728.
Xu W, Miao Z, Zhang X P, et al. Learning a hierarchical spatio-temporal model for human activity recognition[C], 24th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), New orleans, USA, 2017.3.05-2017.3.09.
Xu W, Miao Z, Zhang X P. Structured feature-graph model for human activity recognition[C], IEEE International Conference on Image Processing (ICIP), Quebec city, Canada, 2015.9.27-2015.9.30.
Xu W, Miao Z, Zhang J, et al. Learning Spatio-Temporal Features for Action Recognition with Modified Hidden Conditional Random Field[C], 13th European Conference on Computer Vision (ECCV workshop), Zurich, Switzerland, 2014.9.06-2014.9.12.
Xu W,Miao Z, Zhang J, et al. Spatial-Temporal Context for Action Recognition Combined with Confidence and Contribution Weight[C], 2th IAPR Asian Conference on Pattern Recognition (ACPR2013), Okinawa, Japan, 2013.11.05-2013.11.08.
Tian Y, Ruan Q, An G, Xu W. Context and locality constrained linear coding for human action recognition[J]. Neurocomputing, 2015, 167:359-370.
Hao S, Miao Z, Wang J,Xu W, et al. Labanotation generation based on bidirectional gated recurrent units with joint and line features[C]//2019 IEEE International Conference on Image Processing (ICIP). IEEE, 2019: 4265-4269.
Yang J, Wan L, Xu W, et al. 3D human pose estimation from a single image via exemplar augmentation[J]. Journal of Visual Communication and Image Representation, 2019, 59: 371-379.
An R, Miao Z, Li Q, Xu W, et al. Spatiotemporal visual-semantic embedding network for zero-shot action recognition[J]. Journal of Electronic Imaging, 2019, 28(2): 023007.
苗振江,许万茹,张强,刘汝杰,基于结构化的特征图的人体行为识别方法, 2018.08.31,中国, ZL201510126019.5
苗振江,张强,许万茹,一种基于潜在空间平滑自表征的子空间聚类方法,2018.11.13,中国, ZL201410828113.0
苗振江,胡碧莹,张强,许万茹,刘汝杰,一种基于道路监控视频的车辆速度检测方法, 2017.07.18,中国,ZL201310503592.4