7 citations · 18 across the 7 of their papers we have counts for
7 papers
HGFreNet: Hop-hybrid GraphFomer for 3D Human Pose Estimation with Trajectory Consistency in Frequency Domain
Kai Zhai, Ziyan Huang, Qiang Nie +2
2D-to-3D human pose lifting is a fundamental challenge for 3D human pose estimation in monocular video, where graph convolutional networks (GCNs) and attention mechanisms have prov…
HopFIR: Hop-wise GraphFormer with Intragroup Joint Refinement for 3D Human Pose Estimation
Kai Zhai, Qiang Nie, Bo Ouyang +2
2D-to-3D human pose lifting is fundamental for 3D human pose estimation (HPE), for which graph convolutional networks (GCNs) have proven inherently suitable for modeling the human…
3D Adversarial Attacks Beyond Point Cloud
Jinlai Zhang, Lyujie Chen, Binbin Liu +5
Recently, 3D deep learning models have been shown to be susceptible to adversarial attacks like their 2D counterparts. Most of the state-of-the-art (SOTA) 3D adversarial attacks pe…
Occlusion Guided Self-supervised Scene Flow Estimation on 3D Point Clouds
Bojun Ouyang, Dan Raviv
Understanding the flow in 3D space of sparsely sampled points between two consecutive time frames is the core stone of modern geometric-driven systems such as VR/AR, Robotics, and…
The art of defense: letting networks fool the attacker
Jinlai Zhang, Yinpeng Dong, Binbin Liu +5
Robust environment perception is critical for autonomous cars, and adversarial defenses are the most effective and widely studied ways to improve the robustness of environment perc…
PointCutMix: Regularization Strategy for Point Cloud Classification
Jinlai Zhang, Lyujie Chen, Bo Ouyang +5
As 3D point cloud analysis has received increasing attention, the insufficient scale of point cloud datasets and the weak generalization ability of networks become prominent. In th…
Occlusion Guided Scene Flow Estimation on 3D Point Clouds
Bojun Ouyang, Dan Raviv
3D scene flow estimation is a vital tool in perceiving our environment given depth or range sensors. Unlike optical flow, the data is usually sparse and in most cases partially occ…