End-to-end region-based object detectors like Sparse R-CNN usually have
...
Loop-closure detection, also known as place recognition, aiming to ident...
Current state-of-the-art models for natural language understanding requi...
Sequential interaction networks (SIN) have been commonly adopted in many...
Graph clustering is a longstanding research topic, and has achieved
rema...
The rapid development of advanced computing technologies such as quantum...
The widespread emergence of smart devices for ECG has sparked demand for...
We study tail risk dynamics in high-frequency financial markets and thei...
Automatic font generation without human experts is a practical and
signi...
In the future, service robots are expected to be able to operate autonom...
Continual graph learning routinely finds its role in a variety of real-w...
Pre-trained vision-language models like CLIP have recently shown superio...
Without densely tiled anchor boxes or grid points in the image, sparse R...
Representation learning on temporal graphs has drawn considerable resear...
Controllable person image synthesis task enables a wide range of applica...
In this paper, we explore a new knowledge-amalgamation problem, termed
F...
Unpaired image-to-image (I2I) translation often requires to maximize the...
Existing GAN inversion methods fail to provide latent codes for reliable...
In the past ten years, the use of 3D Time-of-Flight (ToF) LiDARs in mobi...
Graph representation learning received increasing attentions in recent y...
Recently, vision Transformers (ViTs) are developing rapidly and starting...
The image-to-image translation (I2IT) model takes a target label or a
re...
Image-to-image (I2I) translation is usually carried out among discrete
d...
Font generation is a challenging problem especially for some writing sys...
Learning representations for graphs plays a critical role in a wide spec...
End-to-end visuomotor control is emerging as a compelling solution for r...
View synthesis is usually done by an autoencoder, in which the encoder m...
This paper investigates the size performance of Wald tests for CAViaR mo...
Short-form video social media shifts away from the traditional media par...
Graph Neural Networks (GNNs) have been widely applied to fraud detection...
Novel view synthesis often needs the paired data from both the source an...
Data uncertainty in practical person reID is ubiquitous, hence it requir...
Image features from a small local region often give strong evidence in t...
This paper proposes a novel approach for global localisation of mobile r...
The dominant graph neural networks (GNNs) over-rely on the graph links,
...
This paper aims to disentangle the latent space in cVAE into the spatial...
In this paper we investigate an artificial agent's ability to perform
ta...
The field of autonomous driving has grown tremendously over the past few...
This paper presents the research focus and ideas incorporated in the EPA...
A massive number of well-trained deep networks have been released by
dev...
Electrocardiography plays an essential role in diagnosing and screening
...
The majority of contemporary object-tracking approaches used in autonomo...
VAE requires the standard Gaussian distribution as a prior in the latent...
With the rapid development of deep learning, there have been an
unpreced...
Gliomas are the most common primary brain malignancies, with different
d...
Estimating multiple attributes from a single facial image gives comprehe...
While most security projects have focused on fending off attacks coming ...
This paper presents a novel semantic mapping approach, Recurrent-OctoMap...
This paper introduces a fully deep learning approach to monocular SLAM, ...
Human detection and tracking is an essential task for service robots, wh...