Ph.D. Computer Science, Queen Mary, University of London, 2004-2007

M.Phil. Electrical and Computer Engineering, National University of Singapore, 2001-2004

B.Eng. Electronics Engineering, Northwestern Polytechnic University, 1997-2001

Kui JIA is currently a full Professor with tenure at the School of Data Science, The Chinese University of Hong Kong, Shenzhen. He was previously affiliated with South China University of Technology, University of Macau, and UIUC Advanced Digital Science Center. His primary research interests are in machine learning and computer vision. He is recently focusing on deep learning and generalization, generative 3D modeling, and Sim2Real 3D semantic learning. His has been regularly publishing in top AI journals and conferences, such as TPAMI/CVPR/ICCV/NeurIPS/ICML. His research has been supported by grants from NSFC, Guangdong Government, Huawei, MSRA, etc. Some of his research outputs have been used in the products of Orbbec for intelligent 3D sensing, and in the self-driving system from Samsung America for 3D pedestrian and car detection. He is serving as Associate Editors for a few journals such as Trans. on Machine Learning Research and IEEE Trans. on Image Processing, and served or has been serving as Area Chairs for ICCV, NeurIPS, ICML, etc. He is the founder of the DexForce Technology. 

1.     Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation, Rui Chen, Yongwei Chen, Ningxin Jiao, and Kui Jia, IEEE International Conference on Computer Vision (ICCV), 2023.

2.     On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion, Yushu Li, Xun Xu, Yongyi Su, and Kui Jia, IEEE International Conference on Computer Vision (ICCV), 2023. Oral Presentation

3.     VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representations, Jiehong Lin, Zewei Wei, Yabin Zhang, and Kui Jia, IEEE International Conference on Computer Vision (ICCV), 2023.

4.     Generative Scene Synthesis via Incremental View Inpainting using RGBD Diffusion Models, Jiabao Lei, Jiapeng Tang, and Kui Jia, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.

5.     A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain Adaptation, Hui Tang and Kui Jia, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.

6.     HelixSurf: A Robust and Efficient Neural Implicit Surface Learning of Indoor Scenes with Iterative Intertwined Regularization, Zhihao Liang, Zhangjin Huang, Changxing Ding, and Kui Jia, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.

7.     TANGO: Text-driven Photorealistic and Robust 3D Stylization via Lighting Decomposition, Yongwei Chen, Rui Chen, Jiabao Lei, Yabin Zhang, and Kui Jia, Neural Information Processing Systems (NeurIPS), 2022.

8.     Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering, Yongyi Su, Xun Xu, and Kui Jia, Neural Information Processing Systems (NeurIPS), 2022.

9.     Towards Discovering the Effectiveness of Moderately Confident Samples for Semi-Supervised Learning, Hui Tang and Kui Jia, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.

10.  Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization, Yabin Zhang, Minghan Li, Ruihuang Li, Kui Jia, and Lei Zhang, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022. Oral Presentation

11.  VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attention, Shengheng Deng, Zhihao Liang, Lin Sun, and Kui Jia,  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.

12.  Learning and Meshing from Deep Implicit Surface Networks Using an Efficient Implementation of Analytic Marching, Jiabao Lei, Kui Jia, and Yi Ma, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Accepted, 2021.

13.  Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space, Jiehong Lin, Hongyang Li, Ke Chen, Jiangbo Lu, and Kui Jia, Neural Information Processing Systems (NeurIPS), 2021.

14.  Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering, Hui Tang, Xiatian Zhu, Ke Chen, Kui Jia, and C. L. Philip Chen, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Accepted, 2021.

15.  SkeletonNet: A Topology-Preserving Solution for Learning Mesh Reconstruction of Object Surfaces from RGB Images, Jiapeng Tang, Xiaoguang Han, Mingkui Tan, Xin Tong, and Kui Jia, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Accepted, 2021.

16.  3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding, Shengheng Deng, Xun Xu, Chaozheng Wu, Ke Chen, and Kui Jia, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.

17.  Geometry-Aware Generation of Adversarial Point Clouds, Yuxin Wen, Jiehong Lin, Ke Chen, C. L. Philip Chen, and Kui Jia, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Accepted, 2020.

18.  Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practice, Yabin Zhang, Bin Deng, Hui Tang, Lei Zhang, and Kui Jia, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Accepted, 2020.

19.  Grasp Proposal Networks: An End-to-End Solution for Visual Learning of Robotic Grasps, Chaozheng Wu, Jian Chen, Qiaoyu Cao, Jianchi Zhang, Yunxin Tai, Lin Sun, and Kui Jia, Neural Information Processing Systems (NeurIPS), 2020.

20.  Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering, Hui Tang, Ke Chen, and Kui Jia, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020. Oral Presentation

21.  Orthogonal Deep Neural Networks, Shuai Li, Kui Jia, Yuxin Wen, Tongliang Liu, and Dacheng Tao, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Accepted, 2019.

22.  A Skeleton-bridged Deep Learning Approach for Generating Meshes of Complex Topologies from Single RGB Images, Jiapeng Tang, Xiaoguang Han, Junyi Pan, Kui Jia, and Xin Tong, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019. Oral Presentation, Best Paper Finalists

More publications can be found at http://kuijia.site/