Basic Information

 

Dr. Wei Ke

Associate Professor

 

My research lies in computer vision and machine learning, especially object/pedestrian detection, low-level image processing, and action recognition. 

 

Contact: wei.ke[at]xjtu.edu.cn

 

I'm sorry that there is no position for international students right now in my team.

Honors

“Young Talent Support Plan” of Xi’an Jiaotong University

“Siyuan Scholar” of Xi’an Jiaotong University

Education

2011.09-2018.06  Ph.D. of Signal and Information Processing, Unversity of Chinese Academy of Sciences. Advised by Prof. Qixiang Ye

2015.10-2016.09  Joint Ph.D. Student, University of Oulu, Finland. Advised by Prof. Guoying Zhao and Prof. Jie Chen

2007.09-2011.06  Bachelor of Electrical Engineering and Automation，Beihang University (BUAA). Advised by Prof. Jing Wu

Positions

2020.04-                 Assoicate Professor, Xi'an Jiaotong University

2018.03-2020.03    Postdoc Fellow, Carnegie Mellon University (CMU), advised by Dr. Dong Huang

2017.11-2018.01    Intern, Microsoft Research Asia (MSRA), advised by Dr. Xun Guo

Publication

Google Scholar 

 

  1. S. Liu, P. Zhang, S. Zhang, W. Ke*. CountSE: Soft Exemplar Open-set Object Counting. International Conference on Computer Vision (ICCV Highlight), 2025.

  2. S. Zhang, Q. Zhou, W. Ke*. Enhancing Zero-shot Object Counting via Text-guided Local Ranking and Number-evoked Global Attention. International Conference on Computer Vision (ICCV), 2025.
  3. Y Wu, H Zhang, T Lin, L Huang, S Luo, R Wu, C Qiu, W. Ke*, T Zhang. Generating Multimodal Driving Scenes via Next-Scene Prediction, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
  4. C. Qiu, Y. Wu, X. Bai, W. Ke, T. Zhang*. Refining CLIP's Spatial Awareness: A Visual-Centric Perspective. International Conference on Learning Representations (ICLR), 2025.
  5. Y. He, J. Chen, J. Zhang, W. Ke*, Y. Gong. A Bayesian Dual-Pathway Network for Unsupervised Domain Adaptation. Pattern Recognition, 2025.
  6. C. Qiu+, T. Zhang+, Y. Wu, W. Ke*, M. Salzmann, S. Süsstrunk. Mind Your Augmentation: The Key to Decoupling Dense Self-supervised Learning. International Conference on Learning Representations (ICLR), 2024
  7. Y. Wu, T. Zhang*, Q. Cong, W. Ke, S. Süsstrunk, M. Salzmann. Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
  8. S. Zhang, W. Ke, S. Liu*, X. Hong, T. Zhang. Boosting Semi-supervised Crowd Counting with Scale-based Active Learning. ACM Multimedia (MM), 2024.
  9. Z. Zhang, W. Ke*, Y. Zhu, X. Liang, J. Liu, Q. Ye, T. Zhang. Language-Driven Visual Consensus for Zero-Shot Semantic Segmentation. IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT). 2024.
  10. S. Zhang, Z. Wang, W. Ke*. One Point is All You Need for Weakly Supervised Object Detection. Pattern Recognition, 2024.

  11. Y. Wu, T. Zhang, W. Ke*,S. Süsstrunk, M. Salzmann. Spatiotemporal Self-supervised Learning for Point Clouds in the Wild. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023. [Poject Page]

  12. Q. Liu#, H. Liu#, W. Ke*, Y. Liang*. Automated Lesion Segmentation in Fundus Images with Many-to-Many Reassembly of Features. Pattern Recognition, 2022.  

  13. Z. Zhang#, Y. Zhu#, J. Liu, X. Liang,  W. Ke*. CoupAlign: Coupling Word-Pixel with Sentence-Mask Alignments for Referring Image Segmentation. Neural Information Processing Systems (NeurIPS Spotlight), 2022.  

  14. T. Zhang, C. Qiu, W. Ke*, S. Süsstrunk, M. Salzmann. Leverage Your Local and Global Representations: A New Self-Supervised Learning Strategy. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.  

  15. Y. He, Z. Ma, X. Wei, X. Hong, W. Ke, Y. Gong. Error-aware density isomorphism reconstruction for unsupervised cross-domain crowd counting. The AAAI Conference on Artificial Intelligence (AAAI), 2021. 

  16. X. Wei, D. Li, X. Hong, W. Ke, Y. Gong. Co-attentive lifting for infrared-visible person re-identification. ACM International Conference on Multimedia, 2020.

  17. Z. Luo, D. Guillory, B Shi, W. Ke, F. Wan, T. Darrell, H. Xu. Weakly-supervised action localization with expectation-maximization multi-instance learning. European Conference on Computer Vision (ECCV), 2020

  18. W. Ke#, T. Zhang#, Z, Huang, Q. Ye*, J. Liu, and D. Huang. Multiple Anchor Learning for Visual Object Detection.  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.  [arXiv] [code]
  19. W. Ke, J, Chen, J. Jiao, G. Zhao, and Q. Ye*. SRN: Side-output Residual Network for Object Reflectional Symmetry Detection and Beyond. IEEE Transactions on Neural Networks and Learning Systems (T-NNLS), 2020. [EarlyAccess pdf]
  20. Q. Ye, T. Zhang, and W. Ke*. Progressive Latent Models for Self-learning Scene-specific Pedestrian Detectors. IEEE Transactions on Intelligent Transportation Systems (T-ITS), vol. 21, no. 4, pp. 1415-1426, 2020. [pdf]
  21. Z. Huang, W. Ke, and D. Huang. Improving Object Detection with Inverted Attention. IEEE Winter Conference on Applications of Computer Vision (WACV), 1294-1302, 2020. [arXiv] [pdf]
  22. W. Ke, J, Chen, and Q. Ye. Deep Contour and Symmetry Scored Object Proposal. Pattern Recognition Letters vol. 119, pp. 172-179, 2019. [pdf]
  23. F. Wan, C. Liu, W. Ke, et al. C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR oral), 2199-2208, 2019. [pdf]
  24. C. Liu, F. Wan, W. Ke, et al. Orthogonal Decomposition Network for Pixel-Wise Binary Classification. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 6064-6073, 2019. [pdf]
  25. C. Liu#, W. Ke#, F. Qin, and Q. Ye. Linear Span Network for Object Skeleton Detection. European Conference on Computer Vision (ECCV), 133-148, 2018. [pdf]
  26. W. Ke, J, Chen, J. Jiao, G. Zhao, and Q. Ye. SRN: Side-output Residual Network for Object Symmetry Detection in the Wild. IEEE Conference on Computer Vision and Pattern Recognition (CVPR Oral), 1068-1076, 2017. [pdf] [code and dataset] [video]
  27. Q. Ye, T. Zhang, W. Ke*, et al. Self-learning Scene-specific Pedestrian Detectors Using a Progressive Latent Model. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 509-518, 2017. [pdf] [poster]
  28. W. Ke, Y. Zhang, P. Wei, Q. Ye and J. Jiao. Pedestrian Detection via PCA Filters Based Convolutional Channel Features. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 1394-1398, 2015. [pdf]