Autonomous driving has long grappled with the need for precise absolute
...
Multi-behavior recommendation algorithms aim to leverage the multiplex
i...
Semantic scene completion (SSC) jointly predicts the semantics and geome...
Reliable LiDAR panoptic segmentation (LPS), including both semantic and
...
Deep neural networks often exploit non-predictive features that are
spur...
While deep learning models have shown remarkable performance in various
...
To improve the efficiency and sustainability of learning deep models, we...
Neural networks trained with (stochastic) gradient descent have an induc...
Machine learning models pre-trained on large datasets have achieved
rema...
In practical engineering experiments, the data obtained through detector...
Multimodal contrastive pretraining has been used to train multimodal
rep...
Reliable and automated 3D plant shoot segmentation is a core prerequisit...
Energy consumption in buildings, both residential and commercial, accoun...
Unsupervised foreground-background segmentation aims at extracting salie...
The success of state-of-the-art deep neural networks heavily relies on t...
In recent years, generative adversarial networks (GANs) have been an act...
Multiview self-supervised representation learning roots in exploring sem...
Data poisoning causes misclassification of test time target examples by
...
Doubly intractable models are encountered in a number of fields, e.g. so...
In this article, we propose three kinds of neural networks inspired by p...
In this paper, we propose a sequence-to-set method that can transform an...
Maximizing a monotone submodular function is a fundamental task in machi...
In this paper, we revisit the online non-monotone continuous DR-submodul...
A powerful category of data poisoning attacks modify a subset of trainin...
By coordinating terminal smart devices or microprocessors to engage in
c...
Deep learning-based melanoma classification with dermoscopic images has
...
Dynamic graphs refer to graphs whose structure dynamically changes over ...
High-level synthesis (HLS) has been researched for decades and is still
...
By enabling the nodes or agents to solve small-sized subproblems to achi...
Peer-to-peer (P2P) energy trading is a promising market scheme to accomm...
Interpretability is an important property for visual models as it helps
...
Using solar power in the process industry can reduce greenhouse gas emis...
The semantically disentangled latent subspace in GAN provides rich
inter...
In this paper, we revisit the constrained and stochastic continuous
subm...
It is vital to accurately estimate the value function in Deep Reinforcem...
Sponge city construction is a new concept of urban stormwater management...
For most machine learning (ML) tasks, evaluating learning performance on...
Data-driven approaches have been applied to many problems in urban compu...
We consider the problem of scaling automated suggested replies for Outlo...
The famous three-body problem can be traced back to Newton in 1687, but ...
This paper concerns a convex, stochastic zeroth-order optimization (S-ZO...
We propose an unsupervised foreground-background segmentation method via...
Demand for enterprise data warehouse solutions to support real-time Onli...
Multi-goal reinforcement learning is widely used in planning and robot
m...
This paper proposes a cloud energy storage (CES) model for enabling loca...
The Kolmogorov-Smirnov (KS) test is popularly used in many applications,...
This paper studies an optimal energy storage (ES) sharing model which is...
Early prediction of students at risk (STAR) is an effective and signific...
Decentralized optimization for non-convex problems are now demanding by ...
The Artificial Neural Networks (ANNs) like CNN/DNN and LSTM are not
biol...