Hypergraphs are important for processing data with higher-order relation...
Exploring spatial-temporal dependencies from observed motions is one of ...
Multi-person motion prediction is a challenging problem due to the depen...
This work considers the category distribution heterogeneity in federated...
Cooperative perception enabled by V2X Communication technologies can
sig...
Camera-only 3D detection provides an economical solution with a simple
c...
To model the indeterminacy of human behaviors, stochastic trajectory
pre...
Learning to predict agent motions with relationship reasoning is importa...
Vision-centric joint perception and prediction (PnP) has become an emerg...
Multiple robots could perceive a scene (e.g., detect objects) collaborat...
Domain adaptation methods reduce domain shift typically by learning
doma...
Collaborative 3D object detection exploits information exchange among
mu...
The construction of a meaningful hypergraph topology is the key to proce...
Multi-agent learning has gained increasing attention to tackle distribut...
3D point cloud semantic segmentation is one of the fundamental tasks for...
One of the key challenges in federated learning (FL) is local data
distr...
Multi-agent collaborative perception could significantly upgrade the
per...
Perception is one of the crucial module of the autonomous driving system...
Drones equipped with cameras can significantly enhance human ability to
...
To make the earlier medical intervention of infants' cerebral palsy (CP)...
Graph convolutional network based methods that model the body-joints'
re...
The historical trajectories previously passing through a location may he...
Collaborative perception has recently shown great potential to improve
p...
In multi-modal multi-agent trajectory forecasting, two major challenges ...
Demystifying the interactions among multiple agents from their past
traj...
Pooling and unpooling are two essential operations in constructing
hiera...
Demystifying the interactions among multiple agents from their past
traj...
To realize trajectory prediction, most previous methods adopt the
parame...
Vehicle-to-everything (V2X), which denotes the collaboration between a
v...
Multivariate time series forecasting has long received significant atten...
Geometric graph models of systems as diverse as proteins, robots, and
me...
Computation offloading is indispensable for mobile edge computing (MEC)....
We present a novel no-reference quality assessment metric, the image
tra...
To promote better performance-bandwidth trade-off for multi-agent percep...
Differentially-Private Stochastic Gradient Descent (DP-SGD) prevents
tra...
Spatio-temporal graph signal analysis has a significant impact on a wide...
Backdoor attacks (BA) are an emerging threat to deep neural network
clas...
Learning a graph topology to reveal the underlying relationship between ...
The ability to estimate the 3D human shape and pose from images can be u...
Human pose transfer has typically been modeled as a 2D image-to-image
tr...
We propose a multiscale spatio-temporal graph neural network (MST-GNN) t...
A large gap exists between fully-supervised object detection and
weakly-...
3D hand-object pose estimation is an important issue to understand the
i...
This paper considers predicting future statuses of multiple agents in an...
Vulnerability of 3D point cloud (PC) classifiers has become a grave conc...
Weakly-supervised temporal action localization aims to localize actions ...
Distortion quantification of point clouds plays a stealth, yet vital rol...
We propose a novel method based on teacher-student learning framework fo...
Although spatio-temporal graph neural networks have achieved great empir...
Graphs with complete node attributes have been widely explored recently....