693 citations · 2.2k across the 82 of their papers we have counts for
16 papers · 1 filter
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…
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…
Dynamic Differential-Privacy Preserving SGD
Jian Du, Song Li, Xiangyi Chen +2
The vanilla Differentially-Private Stochastic Gradient Descent (DP-SGD), including DP-Adam and other variants, ensures the privacy of training data by uniformly distributing privac…
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…
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…
Detecting Backdoor Attacks Against Point Cloud Classifiers
Zhen Xiang, David J. Miller, Siheng Chen +2
Backdoor attacks (BA) are an emerging threat to deep neural network classifiers. A classifier being attacked will predict to the attacker's target class when a test sample from a s…
Learning to Learn Graph Topologies
Xingyue Pu, Tianyue Cao, Xiaoyun Zhang +2
Learning a graph topology to reveal the underlying relationship between data entities plays an important role in various machine learning and data analysis tasks. Under the assumpt…
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…
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…
Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Prediction
Maosen Li, Siheng Chen, Yangheng Zhao +3
We propose a multiscale spatio-temporal graph neural network (MST-GNN) to predict the future 3D skeleton-based human poses in an action-category-agnostic manner. The core of MST-GN…
CaT: Weakly Supervised Object Detection with Category Transfer
Tianyue Cao, Lianyu Du, Xiaoyun Zhang +3
A large gap exists between fully-supervised object detection and weakly-supervised object detection. To narrow this gap, some methods consider knowledge transfer from additional fu…
Semi-supervised 3D Hand-Object Pose Estimation via Pose Dictionary Learning
Zida Cheng, Siheng Chen, Ya Zhang
3D hand-object pose estimation is an important issue to understand the interaction between human and environment. Current hand-object pose estimation methods require detailed 3D la…
Online Multi-Agent Forecasting with Interpretable Collaborative Graph Neural Network
Maosen Li, Siheng Chen, Yanning Shen +3
This paper considers predicting future statuses of multiple agents in an online fashion by exploiting dynamic interactions in the system. We propose a novel collaborative predictio…
A Backdoor Attack against 3D Point Cloud Classifiers
Zhen Xiang, David J. Miller, Siheng Chen +2
Vulnerability of 3D point cloud (PC) classifiers has become a grave concern due to the popularity of 3D sensors in safety-critical applications. Existing adversarial attacks agains…
Adaptive Mutual Supervision for Weakly-Supervised Temporal Action Localization
Chen Ju, Peisen Zhao, Siheng Chen +3
Weakly-supervised temporal action localization aims to localize actions in untrimmed videos with only video-level action category labels. Most of previous methods ignore the incomp…
MPED: Quantifying Point Cloud Distortion based on Multiscale Potential Energy Discrepancy
Qi Yang, Yujie Zhang, Siheng Chen +3
In this paper, we propose a new distortion quantification method for point clouds, the multiscale potential energy discrepancy (MPED). Currently, there is a lack of effective disto…