Graph Neural Networks (GNNs) have become popular in Graph Representation...
The electronic design automation of analog circuits has been a longstand...
3D vision-language grounding (3D-VL) is an emerging field that aims to
c...
Relying on large-scale training data with pixel-level labels, previous e...
Deep learning techniques for medical image analysis usually suffer from ...
Message passing neural networks (MPNNs) have emerged as the most popular...
This paper studies multiparty learning, aiming to learn a model using th...
Medical image segmentation methods normally perform poorly when there is...
Dynamic graph representation learning is growing as a trending yet
chall...
Semantic segmentation is still a challenging task for parsing diverse
co...
Humans constantly contact objects to move and perform tasks. Thus, detec...
Rich Electronic Health Records (EHR), have created opportunities to impr...
Learning to represent free text is a core task in many clinical machine
...
Transformer, originally devised for natural language processing, has als...
This technical report briefly describes our JDExplore d-team's Vega v2
s...
Although prediction models for delirium, a commonly occurring condition
...
Learning to generate diverse scene-aware and goal-oriented human motions...
Recently, Graph Neural Networks (GNNs) have been applied to graph learni...
The synergistic drug combinations provide huge potentials to enhance
the...
An applied problem facing all areas of data science is harmonizing data
...
The development of parallelizable algorithms for monotone, submodular
ma...
The most popular design paradigm for Graph Neural Networks (GNNs) is 1-h...
An automated and accurate fabric defect inspection system is in high dem...
Convolutional neural network (CNN) has achieved impressive success in
co...
By starting with the assumption that motion is fundamentally a decision
...
Optimization of directed acyclic graph (DAG) structures has many
applica...
We revisit the one- and two-stage detector distillation tasks and presen...
For the problem of maximizing a monotone, submodular function with respe...
Recently, the interpretability of deep learning has attracted a lot of
a...
Effectively structuring deep knowledge plays a pivotal role in transfer ...
We study the understanding of embodied reference: One agent uses both
la...
Few-shot classification (FSC) is one of the most concerned hot issues in...
We study the vision transformer structure in the mobile level in this pa...
Data quality is a common problem in machine learning, especially in
high...
Camera scene detection is among the most popular computer vision problem...
Image super-resolution is one of the most popular computer vision proble...
We investigate molecular mechanisms of resistant or sensitive response o...
Fluid simulations are often performed using the incompressible Navier-St...
Discretization of continuous-time diffusion processes is a widely recogn...
With the current ongoing debate about fairness, explainability and
trans...
Understanding and interpreting human actions is a long-standing challeng...
The goal of neural-symbolic computation is to integrate the connectionis...
Exploring the intrinsic interconnections between the knowledge encoded i...
Detecting 3D objects from a single RGB image is intrinsically ambiguous,...
Exploring the transferability between heterogeneous tasks sheds light on...
We propose a new 3D holistic++ scene understanding problem, which jointl...
Logistic regression (LR) is widely used in clinical prediction because i...
In this paper, we will study the dynamic network regression problem, whi...
Identifying statistical dependence between the features and the label is...
Most modern successful recommender systems are based on matrix factoriza...