The ability to detect objects in all lighting (i.e., normal-, over-, and...
Efficiently optimizing multi-model inference pipelines for fast, accurat...
Omnidirectional images (ODIs) have become increasingly popular, as their...
Endeavors have been recently made to transfer knowledge from the labeled...
Contrasting Language-image pertaining (CLIP) has recently shown promisin...
Deep Neural Networks (DNNs) for 3D point cloud recognition are vulnerabl...
The explicit neural radiance field (NeRF) has gained considerable intere...
In this paper, we strive to answer the question "how to collaboratively ...
The ability to scene understanding in adverse visual conditions, e.g.,
n...
This paper makes the first attempt to tackle the challenging task of
rec...
Segment Anything Model (SAM) has revolutionized the way of segmentation....
The widespread adoption of edge computing has emerged as a prominent tre...
Achieving seamless global coverage is one of the ultimate goals of
space...
In this paper, we introduce FMapping, an efficient neural field mapping
...
Generating and editing a 3D scene guided by natural language poses a
cha...
Images captured by rolling shutter (RS) cameras under fast camera motion...
Recently, intermittent computing (IC) has received tremendous attention ...
Cloud native technology has revolutionized 5G beyond and 6G communicatio...
Recently, omnidirectional images (ODIs) have become increasingly popular...
Semi-supervised learning (SSL) has attracted much attention since it red...
The ability of scene understanding has sparked active research for panor...
Recent research endeavors have shown that combining neural radiance fiel...
Event cameras sense the intensity changes asynchronously and produce eve...
Endeavors have been recently made to leverage the vision transformer (Vi...
One major challenge of disentanglement learning with variational autoenc...
Depth estimation from a monocular 360 image is a burgeoning problem
owin...
The additive model is a popular nonparametric regression method due to i...
Event cameras are bio-inspired sensors that capture the per-pixel intens...
Estimating causal effects from large experimental and observational data...
Motivation: This study aims to develop a novel model called DNA Pretrain...
The metaverse has recently gained increasing attention from the public. ...
A micro-expression is a spontaneous unconscious facial muscle movement t...
The use and analysis of massive data are challenging due to the high sto...
Although weakly-supervised techniques can reduce the labeling effort, it...
Recently, the self-supervised pre-training paradigm has shown great pote...
Revealing the continuous dynamics on the networks is essential for
under...
Thanks to the advantages of flexible deployment and high mobility, unman...
In this paper, a convolution sparse coding method based on global struct...
Since 2021, the term "Metaverse" has been the most popular one, garnerin...
Although deep salient object detection (SOD) has achieved remarkable
pro...
Usually, lesions are not isolated but are associated with the surroundin...
As one of the most successful AI-powered applications, recommender syste...
Three-dimensional (3D) images, such as CT, MRI, and PET, are common in
m...
The popular methods for semi-supervised semantic segmentation mostly ado...
Video deblurring is a highly under-constrained problem due to the spatia...
Existing unsupervised domain adaptation methods based on adversarial lea...
Image restoration and enhancement is a process of improving the image qu...
Federated learning (FL) is a distributed machine learning paradigm that
...
Our modern society and competitive economy depend on a strong digital
fo...
Omnidirectional image (ODI) data is captured with a 360x180 field-of-vie...