Accurately localizing and identifying vertebrae from CT images is crucia...
Qini curves have emerged as an attractive and popular approach for evalu...
The conventional summarization model often fails to capture critical
inf...
Humans learn language via multi-modal knowledge. However, due to the
tex...
Compared to news and chat summarization, the development of meeting
summ...
Cone Beam Computed Tomography (CBCT) is the most widely used imaging met...
Generative Adversarial Networks (GANs) have achieved state-of-the-art re...
The combination of transformers and masked image modeling (MIM) pre-trai...
In the past decade, the technology industry has adopted online randomize...
Black-box adversarial attacks can fool image classifiers into misclassif...
Federated Learning (FL) has emerged as a potentially powerful
privacy-pr...
Intelligent robots rely on object detection models to perceive the
envir...
Knowledge graphs (KGs) are known for their large scale and knowledge
inf...
We consider a basic joint communication and sensing setup comprising a
t...
Is deep learning secure for robots? As embedded systems have access to m...
While Identity Document Verification (IDV) technology on mobile devices
...
Existing dialogue modeling methods have achieved promising performance o...
Siamese tracking paradigm has achieved great success, providing effectiv...
While conversational semantic role labeling (CSRL) has shown its usefuln...
Contrastive learning has shown great potential in unsupervised sentence
...
Blockchain has attracted much attention from both academia and industry ...
We consider the problem of deciding how best to target and prioritize
ex...
In many medical and business applications, researchers are interested in...
We investigate properties of Thompson Sampling in the stochastic multi-a...
We consider a basic communication and sensing setup comprising a transmi...
Financial inclusion depends on providing adjusted services for citizens ...
Internet companies are increasingly using machine learning models to cre...
Conversational semantic role labeling (CSRL) is believed to be a crucial...
This paper presents Hire-MLP, a simple yet competitive vision MLP
archit...
In this paper, we study the privacy-preserving task assignment in spatia...
Vision transformers have been successfully applied to image recognition ...
Language models like BERT and SpanBERT pretrained on open-domain data ha...
Semantic role labeling (SRL) aims to extract the arguments for each pred...
Knowledge distillation is a widely used paradigm for inheriting informat...
As the research in deep neural networks advances, deep convolutional net...
For multi-turn dialogue rewriting, the capacity of effectively modeling ...
Black-box nature hinders the deployment of many high-accuracy models in
...
Last two decades, the problem of robotic mapping has made a lot of progr...
Regression discontinuity designs are used to estimate causal effects in
...
Neural Architecture Search (NAS) has achieved great success in image
cla...
By allowing users to obscure their transactions via including "mixins" (...
Recently, the traffic congestion in modern cities has become a growing w...
Object tracking has been studied for decades, but most of the existing w...
Recently, the Network Representation Learning (NRL) techniques, which
re...