Ju He
Junior Student @ PKU


Ju He is a junior student majoring in Computer Science at Peking University. His research interests focus on Computer Vision and Artificial Intelligence.


[May. 2019] Our paper POINT CLOUD ATTRIBUTE INPAINTING IN GRAPH SPECTRAL DOMAIN is accepted to ICIP2019 in Taipei, Taiwan!
[Nov. 2018]Our paper Exploring Hypergraph Representation on Face Anti-spoofing Beyond 2D Attacks is now on arXiv!


2019.6 - Present
Research Intern @ JHU CCVL
Computer Vision
Supervisor: Prof. Alan
2018.9 - Present
Research Intern @ PKU ICST GLAB
Computer Vision
Supervisor: Prof. Wei Hu
2019.02 - 2019.05
Research Intern @ ByteDance
Video Augmentation
Mentor: Shenyi Song
2018.06 - 2018.10
Research Intern @ Momenta
Object Detection
Mentor: Shaoqing Ren and Yunfei Jiang
2016 - Present
Undergraduate student @ PKU
Computer Science

Selected Publications


With the prevalence of depth sensors and 3D scanning de- vices, point clouds have attracted increasing attention as a format for 3D object representation, with applications in var- ious fields such as tele-presence, navigation for autonomous driving and heritage reconstruction. However, point clouds usually exhibit holes of missing data, mainly due to the lim- itation of acquisition techniques and complicated structure. Hence, we propose an efficient inpainting method for the at- tribute (e.g., color) of point clouds, exploiting non-local self- similarity in graph spectral domain. Specifically, we represent irregular point clouds naturally on graphs, and split a point cloud into fixed-sized cubes as the processing unit. We then globally search for the most similar cubes to the target cube with holes inside, and compute the graph Fourier transform (GFT) basis from the similar cubes, which will be leveraged for the GFT representation of the target patch. We then for- mulate attribute inpainting as a sparse coding problem, im- posing sparsity on the GFT representation of the attribute for hole filling. Experimental results demonstrate the superiority of our method.

ICIP 2019 in Taipei, Taiwan
Exploring Hypergraph Representation on Face Anti-spoofing Beyond 2D Attacks

Face anti-spoofing plays a crucial role in protecting face recognition systems from various attacks. Previous modelbased and deep learning approaches achieve satisfactory performance for 2D face spoofs, but remain limited for more advanced 3D attacks such as vivid masks. In this paper, we address 3D face anti-spoofing via the proposed Hypergraph Convolutional Neural Networks (HGCNN). Firstly, we construct a computation-efficient and posture-invariant face representation with only a few key points on hypergraphs. The hypergraph representation is then fed into the designed HGCNN with hypergraph convolution for feature extraction, while the depth auxiliary is also exploited for 3D mask anti-spoofing. Further, we build a 3D face attack database with color, depth and infrared light information to overcome the deficiency of 3D face anti-spoofing data. Experiments show that our method achieves the state-of-theart performance over widely used 3D and 2D databases as well as the proposed one under various tests.

Under Review