activity
20212023
most citedInvestigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction

88 citations · 144 across the 12 of their papers we have counts for

collaborators
Showing 2022Show all

6 papers · 1 filter

astro-ph.GA2022★ 3 cited

Analytical Equation of Three-point Correlation Function of Galaxies: to Third Order of Density Perturbation

Shu-Guang Wu, Yang Zhang

Applying functional differentiation to the density field with Newtonian gravity, we obtain the static, nonlinear equation of the three-point correlation function of galaxies, t…

cs.CV2022

Copy Motion From One to Another: Fake Motion Video Generation

Zhenguang Liu, Sifan Wu, Chejian Xu +4

One compelling application of artificial intelligence is to generate a video of a target person performing arbitrary desired motion (from a source person). While the state-of-the-a…

math-ph2022★ 3 cited

SYK model with an extra diagonal perturbation: phase transition in the eigenvalue spectrum

Shuang Wu

We study the SYK model with an extra constant source, i.e. a constant matrix or equivalently a diagonal matrix with only one non-zero entry . By using methods from analytic co…

cs.CV2022★ 4 cited

Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation

Zhenguang Liu, Runyang Feng, Haoming Chen +4

Multi-frame human pose estimation has long been a compelling and fundamental problem in computer vision. This task is challenging due to fast motion and pose occlusion that frequen…

cs.SD2022★ 11 cited

Dual Learning Music Composition and Dance Choreography

Shuang Wu, Zhenguang Li, Shijian Lu +1

Music and dance have always co-existed as pillars of human activities, contributing immensely to the cultural, social, and entertainment functions in virtually all societies. Notwi…

cs.CV2022

Motion Prediction via Joint Dependency Modeling in Phase Space

Pengxiang Su, Zhenguang Liu, Shuang Wu +3

Motion prediction is a classic problem in computer vision, which aims at forecasting future motion given the observed pose sequence. Various deep learning models have been proposed…