Dr Pan Ji

Dr Pan Ji
 Org Unit Faculty of Engineering Computer & Math Sciences
 Email pan.ji@adelaide.edu.au
 Telephone +61 8 8313 1855
 Location Ingkarni Wardli ,   North Terrace
  • Biography/ Background


    Feb. 2018 to now                Researcher, NEC Labs America, USA; Research Affiliate, University of Adelaide, Australia

    Jul. 2016 to Jan. 2018         Senior Research Associate, University of Adelaide, Australia 

    Jan. 2013 to Jul. 2016         PhD student,  Australian National University, Australia

    Sep. 2011 to Oct. 2012       Research Assistant, 3DTV Lab, Zhejiang University, China

    Sep. 2007 to Jun. 2011       B.E. & B.A. with Chu Kochen Honours, Zhejiang University, China


    Email: peterji1990 <at> gmail <dot> com


  • Awards & Achievements

    Best Student Paper Award, 2014 International Conference on Image Processing (ICIP 2014)

  • Research Interests

    My current research interests lie in computer vision, especially 3D vision, and unsupervised learning, e.g., clustering, especially with a flavour of deep neural networks (DNN).

  • Publications

    Google Scholar 

    10. Tong Zhang, Pan Ji, Mehrtash Harandi, Richard Hartley, Ian Reid. Scalable deep k-subspace clustering. in Asian Conference on Computer Vision (ACCV), 2018.   


    9. Pan Ji*, Tong Zhang*, Hongdong Li, Mathieu Salzmann, and Ian Reid. Deep subspace clustering networks. in Conference on Neural Information Processing Systems (NIPS), 2017. Code.

    8. Pan Ji, Ian Reid, Ravi Garg, Hongdong Li, and Mathieu Salzmann. Adaptive low-rank kernel subspace clustering. arXiv preprint arXiv:1707.04974. Code.

    7. Pan Ji, Hongdong Li, Yuchao Dai, and Ian Reid. "Maximizing rigidity" revisited: a convex programming approach for generic 3D shape reconstruction from multiple perspective views. In IEEE International Conference on Computer Vision (ICCV), 2017. Code.

    6. Pan Ji, Hongdong Li, Mathieu Salzmann, and Yiran Zhong. Robust multi-body feature tracker: A segmentation-free approach. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. Spotlight (short oral). 

    5. Pan Ji, Mathieu Salzmann, and Hongdong Li. Shape interaction matrix revisited and robustified: Efficient subspace clustering with corrupted and incomplete data. In IEEE International Conference on Computer Vision (ICCV), 2015, OralCodeDataSupplTalk.

    4. Pan Ji, Hongdong Li, Mathieu Salzmann, and Yuchao Dai. Robust motion segmentation with unknown correspondences. In Europian Conference on Computer Vision (ECCV), 2014. Poster. 

    3. Pan Ji, Yiran Zhong, Hongdong Li, and Mathieu Salzmann. Null space clustering with applications to motion segmentation and face clustering. In IEEE International Conference on Image Processing (ICIP), 2014. 
    Best Student Paper AwardCode.

    2. Pan Ji, Mathieu Salzmann, and Hongdong Li. Efficient dense subspace clustering. In IEEE Winter Conference on Applications of Computer Vision (WACV), 2014. Short oral and poster. 

    1. Qingqing Yang, Pan Ji, et al. Fast stereo matching using adaptive guided filtering. Image and Vision Computing (IVC) 32 (3), 202-211, 2014.


  • Professional Associations

    I'm a member of Australian Centre for Vision Technologies (ACVT) and also a research affiliate of Australian Centre for Robotic Vision (ACRV).

    I've been a committee member (reviewer) for various top-tier journals/conferences including TPAMI, TIP, TNNLS, CVPR, ICCV, ECCV, WACV and 3DV.

The information in this directory is provided to support the academic, administrative and business activities of the University of Adelaide. To facilitate these activities, entries in the University Phone Directory are not limited to University employees. The use of information provided here for any other purpose, including the sending of unsolicited commercial material via email or any other electronic format, is strictly prohibited. The University reserves the right to recover all costs incurred in the event of breach of this policy.

Entry last updated: Saturday, 22 Sep 2018

To link to this page, please use the following URL:  https://www.adelaide.edu.au/directory/pan.ji