activity
20192022
most citedAdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries

12 citations · 12 across the 2 of their papers we have counts for

collaborators

3 papers

cs.CV2022

Dynamic Point Cloud Denoising via Gradient Fields

Qianjiang Hu, Wei Hu

3D dynamic point clouds provide a discrete representation of real-world objects or scenes in motion, which have been widely applied in immersive telepresence, autonomous driving, s…

cs.LG2020★ 12 cited

AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries

Qianjiang Hu, Xiao Wang, Wei Hu +1

Contrastive learning relies on constructing a collection of negative examples that are sufficiently hard to discriminate against positive queries when their representations are sel…

cs.CV2019

3D Dynamic Point Cloud Denoising via Spatial-Temporal Graph Learning

Wei Hu, Qianjiang Hu, Zehua Wang +1

The prevalence of accessible depth sensing and 3D laser scanning techniques has enabled the convenient acquisition of 3D dynamic point clouds, which provide efficient representatio…