22 citations · 38 across the 8 of their papers we have counts for
8 papers
Attention-Based Depth Distillation with 3D-Aware Positional Encoding for Monocular 3D Object Detection
Zizhang Wu, Yunzhe Wu, Jian Pu +2
Monocular 3D object detection is a low-cost but challenging task, as it requires generating accurate 3D localization solely from a single image input. Recent developed depth-assist…
From Node Interaction to Hop Interaction: New Effective and Scalable Graph Learning Paradigm
Jie Chen, Zilong Li, Yin Zhu +2
Existing Graph Neural Networks (GNNs) follow the message-passing mechanism that conducts information interaction among nodes iteratively. While considerable progress has been made,…
SA-MLP: Distilling Graph Knowledge from GNNs into Structure-Aware MLP
Jie Chen, Shouzhen Chen, Mingyuan Bai +3
The message-passing mechanism helps Graph Neural Networks (GNNs) achieve remarkable results on various node classification tasks. Nevertheless, the recursive nodes fetching and agg…
Universal Deep GNNs: Rethinking Residual Connection in GNNs from a Path Decomposition Perspective for Preventing the Over-smoothing
Jie Chen, Weiqi Liu, Zhizhong Huang +3
The performance of GNNs degrades as they become deeper due to the over-smoothing. Among all the attempts to prevent over-smoothing, residual connection is one of the promising meth…
Exploiting Neighbor Effect: Conv-Agnostic GNNs Framework for Graphs with Heterophily
Jie Chen, Shouzhen Chen, Junbin Gao +3
Due to the homophily assumption in graph convolution networks (GNNs), a common consensus in the graph node classification task is that GNNs perform well on homophilic graphs but ma…
Graph Decoupling Attention Markov Networks for Semi-supervised Graph Node Classification
Jie Chen, Shouzhen Chen, Mingyuan Bai +3
Graph neural networks (GNN) have been ubiquitous in graph node classification tasks. Most of GNN methods update the node embedding iteratively by aggregating its neighbors' informa…
SelfGait: A Spatiotemporal Representation Learning Method for Self-supervised Gait Recognition
Yiqun Liu, Yi Zeng, Jian Pu +3
Gait recognition plays a vital role in human identification since gait is a unique biometric feature that can be perceived at a distance. Although existing gait recognition methods…
Exploration-efficient Deep Reinforcement Learning with Demonstration Guidance for Robot Control
Ke Lin, Liang Gong, Xudong Li +6
Although deep reinforcement learning (DRL) algorithms have made important achievements in many control tasks, they still suffer from the problems of sample inefficiency and unstabl…