The sixth-generation (6G) network is envisioned to shift its focus from ...
Deep neural networks are vulnerable to adversarial examples crafted by
a...
With a growing interest in outer space, space robots have become a focus...
Product image segmentation is vital in e-commerce. Most existing methods...
Poster layout is a crucial aspect of poster design. Prior methods primar...
Structure-based drug design powered by deep generative models have attra...
In longitudinal studies, it is not uncommon to make multiple attempts to...
The challenges faced by text classification with large tag systems in na...
Semi-supervised learning (SSL) has attracted much attention since it red...
To benefit the complementary information between heterogeneous data, we
...
We tackle a new problem of multi-view camera and subject registration in...
Recently, segmentation-based methods are quite popular in scene text
det...
Multi-Label Continual Learning (MLCL) builds a class-incremental framewo...
Person re-identification (Re-ID) is a classical computer vision task and...
Gait recognition is an important AI task, which has been progressed rapi...
Usually, lesions are not isolated but are associated with the surroundin...
Benefiting from the fusion of communication and intelligent technologies...
Continual Learning (CL) sequentially learns new tasks like human beings,...
Skeleton-based human action recognition has been drawing more interest
r...
Three-dimensional (3D) images, such as CT, MRI, and PET, are common in
m...
Event extraction is an important work of medical text processing. Accord...
It's common for current methods in skeleton-based action recognition to
...
Pooling methods are necessities for modern neural networks for increasin...
Existing unsupervised domain adaptation methods based on adversarial lea...
The sixth-generation (6G) network is envisioned to integrate communicati...
Active camera relocalization (ACR) is a new problem in computer vision t...
The upcoming sixth generation (6G) network is envisioned to be more open...
The Lifelong Multi-Label (LML) image recognition builds an online
class-...
Human group detection, which splits crowd of people into groups, is an
i...
To obtain a more comprehensive activity understanding for a crowded scen...
Modal regression, a widely used regression protocol, has been extensivel...
Lane detection plays a key role in autonomous driving. While car cameras...
Deep face recognition (FR) has achieved significantly high accuracy on
s...
Single image dehazing is a challenging task, for which the domain shift
...
Retinal vessel segmentation plays a key role in computer-aided screening...
In the coming smart ocean era, reliable and efficient communications are...
Current fifth-generation (5G) networks do not cover the maritime area,
c...
In the upcoming sixth-generation (6G) era, the demand for constructing a...
There is an approximately one-year observation gap of terrestrial water
...
In recent years, hyperspectral anomaly detection (HAD) has become an act...
Rehearsal, seeking to remind the model by storing old knowledge in lifel...
Arbitrary-shaped text detection is an important and challenging task in
...
Terrestrial communication networks can provide high-speed and ultra-reli...
In recent years, co-saliency object detection (CoSOD) has achieved
signi...
Single-image deraining is rather challenging due to the unknown rain mod...
Rain is a common phenomenon in nature and an essential factor for many d...
Image denoising techniques have been widely employed in multimedia devic...
As the GAN-based face image and video generation techniques, widely know...
Current fifth generation (5G) cellular networks mainly focus on the
terr...
Due to the rapid development of Internet of Things (IoT), a massive numb...