This paper develops a new vascular respiratory motion compensation algor...
With the rapid advancements of deep learning in recent years, hardware
a...
This article studies the derivatives in models that flexibly characteriz...
Memory-aware network scheduling is becoming increasingly important for d...
Efficient networks, e.g., MobileNetV2, EfficientNet, etc, achieves
state...
Stroke extraction of Chinese characters plays an important role in the f...
Weight-sharing supernet has become a vital component for performance
est...
Most existing RGB-based trackers target low frame rate benchmarks of aro...
In this paper, we consider the problem of long tail scenario modeling wi...
Since the concern of privacy leakage extremely discourages user particip...
While the performance of deep convolutional neural networks for image
su...
Monocular depth estimation is an ambiguous problem, thus global structur...
Current medical image synthetic augmentation techniques rely on intensiv...
Deep learning networks have demonstrated state-of-the-art performance on...
Fusing camera with LiDAR is a promising technique to improve the accurac...
Secure multi-party computation (MPC) enables computation directly on
enc...
This paper deals with the resolutions of fuzzy relation equations with
a...
Derivatives are a key nonparametric functional in wide-ranging applicati...
In this article, we propose a novel spatial global-local spike-and-slab
...
The continual appearance of new objects in the visual world poses
consid...
In recent years, with the development of deep neural networks, end-to-en...
Efficient deep neural network (DNN) models equipped with compact operato...
Modern pre-trained transformers have rapidly advanced the state-of-the-a...
We design deep neural networks (DNNs) and corresponding networks' splitt...
Neural network based end-to-end Text-to-Speech (TTS) has greatly improve...
Federated learning (FL) enables distributed clients to learn a shared mo...
We introduce PyTorchVideo, an open-source deep-learning library that pro...
Low-rank tensor compression has been proposed as a promising approach to...
Vision transformers (ViTs) have attracted much attention for their super...
The big data about music history contains information about time and use...
In the emerging field of materials informatics, a fundamental task is to...
From wearables to powerful smart devices, modern automatic speech recogn...
Automatic speech recognition (ASR) has become increasingly ubiquitous on...
Bloom filter is a compact memory-efficient probabilistic data structure
...
This article is motivated by studying the interaction of magnetic moment...
In this paper, we consider a second-order scalar auxiliary variable (SAV...
Since the mapping relationship between definitized intra-interventional ...
Introducing the transformer structure into computer vision tasks holds t...
There is a wide range of applications where the local extrema of a funct...
Our understanding of the structure of the brain and its relationships wi...
When we use End-to-end automatic speech recognition (E2E-ASR) system for...
Weight-sharing neural architecture search (NAS) is an effective techniqu...
Low-precision deep neural network (DNN) training has gained tremendous
a...
Wav2vec 2.0 is a recently proposed self-supervised framework for speech
...
Scale variance among different sizes of body parts and objects is a
chal...
We study the posterior contraction rates of a Bayesian method with Gauss...
Data augmentation (DA) is an essential technique for training
state-of-t...
Neural architecture search (NAS) has shown great promise designing
state...
The space fractional Cahn-Hilliard phase-field model is more adequate an...
Powerful yet complex deep neural networks (DNNs) have fueled a booming d...