activity
20152023
most citedMultivariate Time Series Forecasting with Dynamic Graph Neural ODEs

182 citations · 683 across the 61 of their papers we have counts for

collaborators
Showing 2021 · cs.CVShow all

11 papers · 2 filters

cs.CV2021★ 5 cited

No-Reference Point Cloud Quality Assessment via Domain Adaptation

Qi Yang, Yipeng Liu, Siheng Chen +2

We present a novel no-reference quality assessment metric, the image transferred point cloud quality assessment (IT-PCQA), for 3D point clouds. For quality assessment, deep neural…

cs.CV2021★ 17 cited

Learning Distilled Collaboration Graph for Multi-Agent Perception

Yiming Li, Shunli Ren, Pengxiang Wu +3

To promote better performance-bandwidth trade-off for multi-agent perception, we propose a novel distilled collaboration graph (DiscoGraph) to model trainable, pose-aware, and adap…

cs.CV2021★ 1 cited

Collaborative Uncertainty in Multi-Agent Trajectory Forecasting

Bohan Tang, Yiqi Zhong, Ulrich Neumann +3

Uncertainty modeling is critical in trajectory forecasting systems for both interpretation and safety reasons. To better predict the future trajectories of multiple agents, recent…

cs.CV2021★ 1 cited

Spatio-Temporal Graph Complementary Scattering Networks

Zida Cheng, Siheng Chen, Ya Zhang

Spatio-temporal graph signal analysis has a significant impact on a wide range of applications, including hand/body pose action recognition. To achieve effective analysis, spatio-t…

cs.CV2021

Joint 3D Human Shape Recovery and Pose Estimation from a Single Image with Bilayer Graph

Xin Yu, Jeroen van Baar, Siheng Chen

The ability to estimate the 3D human shape and pose from images can be useful in many contexts. Recent approaches have explored using graph convolutional networks and achieved prom…

cs.CV2021★ 1 cited

A 3D Mesh-based Lifting-and-Projection Network for Human Pose Transfer

Jinxiang Liu, Yangheng Zhao, Siheng Chen +1

Human pose transfer has typically been modeled as a 2D image-to-image translation problem. This formulation ignores the human body shape prior in 3D space and inevitably causes imp…