Shihong Xia is a professor at the Institute of Computing Technology, CAS. He is leading a research group working on human motion modeling in computer graphics, computer vision and VR/AR.
Contact Info
Email：xsh@ict.ac.cn
Tel：86 10 62600852
For more details, please refer to http://humanmotion.ict.ac.cn/en/index.html
Research Areas
Computer Graphics, Virtual Reality, Artificial Intelligence
Selected Publications
1. Chongyang Zhong, Lei Hu, Zihao Zhang, Yongjing Ye, Shihong Xia. Spatio-Temporal Gating-Adjacency GCN for Human Motion Prediction. CVPR 2022. in press.
2. Yuhui Wen, Lin Gao, Hongbo Fu, FangLue Zhang, Shihong Xia, YongJin Liu. Motif-GCNs with Local and Non-Local Temporal Blocks for Skeleton-Based Action Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 2022. in press.
3. Shuyu Chen, Jia-Qi Zhang, Lin Gao, Yue He, Shihong Xia, Min Shi, Fanglue Zhang. Active Colorization for Cartoon Line Drawings. IEEE TVCG 28(2): 1198-1208 (2022)
4. Zihao Zhang, Lei Hu, Xiaoming Deng, Shihong Xia. Sequential 3D Human Pose Estimation Using Adaptive Point Cloud Sampling Strategy. IJCAI 2021: 1330-1337.
5. Zhiyong Wang, Jinxiang Chai, Shihong Xia. Combining Recurrent Neural Networks and Adversarial Training for Human Motion Synthesis and Control. IEEE TVCG 27(1): 14-28 (2021)
6. Zhiyong Wang, Jinxiang Chai, Shihong Xia. Realtime and Accurate 3D Eye Gaze Capture with DCNN-Based Iris and Pupil Segmentation. IEEE TVCG 27(1): 190-203 (2021)
7. Lin Gao, Yu-Kun Lai, Jie Yang, Ling-Xiao Zhang, Shihong Xia, Leif Kobbelt. Sparse Data Driven Mesh Deformation. IEEE TVCG 27(3): 2085-2100 (2021)
8. Shu-Yu Chen, Wanchao Su, Lin Gao, Shihong Xia, Hongbo Fu. DeepFaceDrawing: Deep Generation of Face Images from Sketches. ACM TOG / SIGGRAPH, 2020，39 (4), 72: 1-72: 16
9. Zihao Zhang, Lei Hu, Xiaoming Deng, Shihong Xia. Weakly Supervised Adversarial Learning for 3D Human Pose Estimation from Point Clouds. IEEE TVCG/VR 26 (5), 1851-1859, 2020.
10. Mingze Yuan, Lin Gao, Hongbo Fu, Shihong Xia. Temporal Upsampling of Depth Maps Using a Hybrid Camera. IEEE TVCG 25(3): 1591-1602 (2019)
11. Yuhui Wen, Lin Gao, Hongbo Fu, Fang-Lue Zhang, Shihong Xia. Graph CNNs with Motif and Variable Temporal Block for Skeleton-based Action Recognition. AAAI 2019: 8989-8996.
12. Yuhui Wen, Hongshi Huang, Yuanyuan Yu, Si Zhang, Jie Yang, Yingfang Ao, Shihong Xia. Effect of tibia marker placement on knee joint kinematic analysis. Gait & Posture 60 (2018) 99-103.
13. Lin Gao, Jie Yang, Yiling Qiao, Yukun Lai, Paul Rosin, Weiwei Xu, Shihong Xia. Automatic unpaired shape deformation transfer. ACM TOG / SIGGRAPH Asia 2018, 37 (6), 237: 1-237: 15
14. Qingyang Tan, Lin Gao, Yu-Kun Lai, Shihong Xia. Variational Autoencoders for Deforming 3D Mesh Models. CVPR 2018: 5841-5850
15. Shuyu Chen, Lin Gao, Yu-Kun Lai, Paul L. Rosin, Shihong Xia. Real-time 3D Face Reconstruction and Gaze Tracking for Virtual Reality. IEEE VR 2018: 525-526
16. Shihong Xia, Zihao Zhang, Le Su. Cascaded 3D Full-body Pose Regression from Single Depth Image at 100 FPS. IEEE VR 2018: 431-438
17. Qingyang Tan, Lin Gao, Yu-Kun Lai, Jie Yang, Shihong Xia. Mesh-based Autoencoders for Localized Deformation Component Analysis. AAAI 2018: 2452-2459.
18. Kangkan Wang, Guofeng Zhang, Shihong Xia. Templateless Non-rigid Reconstruction and Motion Tracking with a Single RGB-D Camera. IEEE TIP 26(12): 5966-5979 (2017)
19. Shihong Xia, Lin Gao, Yu-Kun Lai, Ming-Ze Yuan, Jinxiang Chai. A Survey on Human Performance Capture and Animation. JCST 32(3): 536-554 (2017)
20. Xiaolei Lv, Jinxiang Chai, Shihong Xia. Data-driven Inverse Dynamics for Human Motion. ACM TOG / SIGGRAPH Asia 2016: 35(6), 163:1-163:12.
21. Lin Gao, Yu-Kun Lai, Dun Liang, Shu-Yu Chen, Shihong Xia. Efficient and Flexible Deformation Representation for Data-Driven Surface Modeling. ACM TOG, vol. 35(5), 158:1-17, 2016
22. Congyi Wang, Fuhao Shi, Shihong Xia, Jinxiang Chai. Realtime 3D eye gaze animation using a single RGB camera. ACM TOG / SIGGRAPH 2016: 35(4), 118:1-118:14
23. Shihong Xia, Congyi Wang, Jinxiang Chai, Jessica Hodgins. Realtime Style Transfer for Unlabeled Heterogeneous Human Motion. ACM TOG / SIGGRAPH 2015. 34(4), 119:1-119:10