Whilst contrastive learning yields powerful representations by matching
...
Predicting the future behavior of agents is a fundamental task in autono...
We propose Concavity-induced Distance (CID) as a novel way to measure th...
Object detection and multiple object tracking (MOT) are essential compon...
Deep learning has achieved great success in recent years with the aid of...
Multiple robots could perceive a scene (e.g., detect objects) collaborat...
We propose DeepExplorer, a simple and lightweight metric-free exploratio...
Pneumatic soft robots present many advantages in manipulation tasks. Not...
Humans can easily imagine the complete 3D geometry of occluded objects a...
Autonomous UAV path planning for 3D reconstruction has been actively stu...
For medical image segmentation, contrastive learning is the dominant pra...
A private information retrieval (PIR) scheme allows a client to retrieve...
LiDAR mapping is important yet challenging in self-driving and mobile
ro...
In fifth generation (5G) new radio (NR), the demodulation reference sign...
Collaborative 3D object detection exploits information exchange among
mu...
Vision-based localization approaches now underpin newly emerging navigat...
Sharing information between connected and autonomous vehicles (CAVs)
fun...
Visual place recognition (VPR) using deep networks has achieved
state-of...
Self-supervised learning has recently achieved great success in
represen...
This technical report presents an effective method for motion prediction...
Unlike classical routing algorithms, quantum routing algorithms make use...
We introduce a novel tree coloring problem in which each node of a roote...
We are interested in anticipating as early as possible the target locati...
Class-agnostic counting (CAC) aims to count all instances in a query ima...
Particle robots are novel biologically-inspired robotic systems where
lo...
Tiny machine learning (tinyML) has emerged during the past few years aim...
There is a resurgence of interest in Byzantine fault-tolerant (BFT) syst...
Vehicle-to-everything (V2X), which denotes the collaboration between a
v...
As adoption of blockchain-based systems grows, more attention is being g...
Full nodes in a blockchain network store and verify a copy of the whole
...
Neural networks (NN) for single-view 3D reconstruction (SVR) have gained...
Despite the large progress in supervised learning with Neural Networks, ...
To promote better performance-bandwidth trade-off for multi-agent percep...
Distributed energy resources (DERs), such as rooftop solar panels, are
g...
Visual place recognition (VPR) is critical in not only localization and
...
The system design and algorithm development of mobile 3D printing robots...
Compute-forward is a coding technique that enables receiver(s) in a netw...
Low latency is one of the desired properties for partially synchronous
B...
Short-packet communication is a key technology to support two emerging
a...
HotStuff is a state-of-the-art Byzantine fault-tolerant consensus protoc...
Fused deposition modeling (FDM) using mobile robots instead of the
gantr...
Exploiting short packets for communications is one of the key technologi...
Spatial reasoning on multi-view line drawings by state-of-the-art superv...
PoseNet can map a photo to the position where it is taken, which is appe...
We need intelligent robots for mobile construction, the process of navig...
LiDAR point clouds collected from a moving vehicle are functions of its
...
Permissioned blockchains employ Byzantine fault-tolerant (BFT) state mac...
In the domain of visual tracking, most deep learning-based trackers high...
Byzantine fault tolerant (BFT) consensus has recently gained much attent...
The HotStuff protocol is a recent breakthrough inByzantine Fault Toleran...