A major family of sufficient dimension reduction (SDR) methods, called
i...
In this paper, we introduce the novel state-of-the-art Dual-attention
Tr...
As pre-trained models automate many code intelligence tasks, a widely us...
This paper presents a novel framework, named Global-Local Correspondence...
This technical report introduces CyberLoc, an image-based visual localiz...
Due to the extreme imbalance in the number of normal data and abnormal d...
Planning a time-optimal trajectory for aerial robots is critical in many...
In surface defect detection, due to the extreme imbalance in the number ...
Effectively classifying remote sensing scenes is still a challenge due t...
Deep neural networks tend to underestimate uncertainty and produce overl...
Translating e-commercial product descriptions, a.k.a product-oriented ma...
We target at providing a computational cheap yet effective approach for
...
Recognizing objects from subcategories with very subtle differences rema...
Image captioning attempts to generate a sentence composed of several
lin...
Learning long-term dependencies still remains difficult for recurrent ne...
With the rapid development of mobile computing, wearable wrist-worn is
b...
We consider forecasting a single time series using high-dimensional
pred...
Preterm births occur at an alarming rate of 10-15
risk of infant mortali...
It is well known that direct training of deep neural networks will gener...