Network embedding, a graph representation learning method illustrating
n...
Iris presentation attack detection (PAD) has achieved great success unde...
Taxonomy completion, a task aimed at automatically enriching an existing...
Most existing approaches for point cloud normal estimation aim to locall...
OOD-CV challenge is an out-of-distribution generalization task. To solve...
OOD-CV challenge is an out-of-distribution generalization task. In this
...
Gaze estimation is the fundamental basis for many visual tasks. Yet, the...
Convolutional neural networks (CNNs) have demonstrated gratifying result...
The rapid development of point cloud learning has driven point cloud
com...
Point cloud upsampling focuses on generating a dense, uniform and
proxim...
Currently, many face forgery detection methods aggregate spatial and
fre...
Video Object Grounding (VOG) is the problem of associating spatial objec...
Solid results from Transformers have made them prevailing architectures ...
Expandable networks have demonstrated their advantages in dealing with
c...
End-to-end text spotting has attached great attention recently due to it...
Assessing the blurriness of an object image is fundamentally important t...
Universal domain adaptive object detection (UniDAOD)is more challenging ...
Vanilla unsupervised domain adaptation methods tend to optimize the mode...
Semi-supervised object detection has made significant progress with the
...
Self-training for unsupervised domain adaptive object detection is a
cha...
Inspired by the remarkable zero-shot generalization capacity of
vision-l...
Convolutional neural networks (CNNs) have achieved significant success i...
The knowledge replay technique has been widely used in many tasks such a...
Exemplar-free incremental learning is extremely challenging due to
inacc...
Automatic facial action unit (AU) recognition is a challenging task due ...
Iris presentation attack detection (PAD) has achieved remarkable success...
Learning from a label distribution has achieved promising results on ord...
Natural language spatial video grounding aims to detect the relevant obj...
Novel classes frequently arise in our dynamically changing world, e.g., ...
Knowledge graphs store a large number of factual triples while they are ...
Although previous CNN based face anti-spoofing methods have achieved
pro...
This paper introduces a post-training quantization (PTQ) method achievin...
Although modern automatic speech recognition (ASR) systems can achieve h...
Knowledge Graph (KG) inference is the vital technique to address the nat...
Few-shot learning (FSL) aims to learn models that generalize to novel cl...
Designing optimal reward functions has been desired but extremely diffic...
Nowadays advanced image editing tools and technical skills produce tampe...
Automatic facial action unit (AU) recognition is a challenging task due ...
Reconstruction-based methods play an important role in unsupervised anom...
Multi-person pose estimation is an attractive and challenging task. Exis...
Few-shot relation extraction (FSRE) is of great importance in long-tail
...
Text recognition is a popular topic for its broad applications. In this ...
Table structure recognition is a challenging task due to the various
str...
Document layout analysis is crucial for understanding document structure...
Point clouds can be represented in many forms (views), typically, point-...
Object detection involves two sub-tasks, i.e. localizing objects in an i...
This paper proposes a 3D LiDAR SLAM algorithm named Ground-SLAM, which
e...
In facial action unit (AU) recognition tasks, regional feature learning ...
Although current face anti-spoofing methods achieve promising results un...
It is a strong prerequisite to access source data freely in many existin...