Head-related transfer functions (HRTFs) are crucial for spatial soundfie...
Large-scale online recommender system spreads all over the Internet bein...
The SOTA face swap models still suffer the problem of either target iden...
In this paper, we propose a new deep learning method, named finite volum...
Manipulation relationship detection (MRD) aims to guide the robot to gra...
Contrastive learning methods have shown an impressive ability to learn
m...
In this paper, we propose a new adaptive technique, named adaptive
traje...
Generating images with both photorealism and multiview 3D consistency is...
In scenarios involving the grasping of multiple targets, the learning of...
As a crucial infrastructure of intelligent mobile robots, LiDAR-Inertial...
We present HandAvatar, a novel representation for hand animation and
ren...
Neural Radiance Fields (NeRF) have achieved photorealistic novel views
s...
Place recognition is a critical and challenging task for mobile robots,
...
We present two versatile methods to generally enhance self-supervised
mo...
In this paper, we propose a lightweight system, RDS-SLAM, based on ORB-S...
Vision-based localization in a prior map is of crucial importance for
au...
Self-supervised monocular depth estimation (MDE) models universally suff...
Modeling sparse and dense image matching within a unified functional
cor...
Open World Object Detection (OWOD) is a challenging computer vision prob...
Pose estimation is important for robotic perception, path planning, etc....
Task-oriented dialogue (TOD) systems have been widely used by mobile pho...
Recently, the structural reading comprehension (SRC) task on web pages h...
Neural volume rendering has been proven to be a promising method for
eff...
Automatic Time Series Forecasting (TSF) model design which aims to help ...
Due to the representation limitation of the joint Q value function,
mult...
Neural Radiance Fields (NeRF) has recently gained popularity for its
imp...
Point clouds and images could provide complementary information when
rep...
Human motion prediction is an important and challenging topic that has
p...
Robust vision restoration for an underwater image remains a challenging
...
Spoken dialogue systems such as Siri and Alexa provide great convenience...
Recent studies reveal that Convolutional Neural Networks (CNNs) are typi...
In recent years, Face Image Quality Assessment (FIQA) has become an
indi...
Recent years have witnessed significant progress in 3D hand mesh recover...
Web search is an essential way for human to obtain information, but it's...
We propose real-time, six degrees of freedom (6DoF), 3D face pose estima...
Generalized Zero-Shot Learning (GZSL) is a challenging topic that has
pr...
The leximin solution – which selects an allocation that maximizes the
mi...
Underwater robotic perception usually requires visual restoration and ob...
Video object detection (VID) has been vigorously studied for years but a...
We extend the fair machine learning literature by considering the proble...
Object detection methods fall into two categories, i.e., two-stage and
s...
Temporal object detection has attracted significant attention, but most
...
Temporal object detection has attracted significant attention, but most
...
Underwater machine vision attracts more attention, but the terrible qual...
Underwater machine vision attracts more attention, but the terrible qual...