In this study, we address the challenge of 3D scene structure recovery f...
Stance detection aims to identify the attitude expressed in a document
t...
Text-to-image person re-identification (TIReID) is a compelling topic in...
The inherent challenge of multimodal fusion is to precisely capture the
...
Cutting out an object and estimating its opacity mask, known as image
ma...
Multimodal machine learning has achieved remarkable progress in a wide r...
Obtaining sufficient labelled data for model training is impractical for...
3D interacting hand pose estimation from a single RGB image is a challen...
Real-time eyeblink detection in the wild can widely serve for fatigue
de...
Ensemble learning serves as a straightforward way to improve the perform...
Model-based deep learning has achieved astounding successes due in part ...
Optical Intra-oral Scanners (IOS) are widely used in digital dentistry,
...
Modern deep neural networks (DNNs) have achieved state-of-the-art
perfor...
Existing multi-view classification algorithms focus on promoting accurac...
Multimodal regression is a fundamental task, which integrates the inform...
Overparametrized Deep Neural Networks (DNNs) often achieve astounding
pe...
Current one-stage methods for visual grounding encode the language query...
Convolutional neural networks may perform poorly when the test and train...
Spiking neural networks (SNNs) have advantages in latency and energy
eff...
Neural networks training on edge terminals is essential for edge AI
comp...
Multi-view classification (MVC) generally focuses on improving classific...
Learn in-situ is a growing trend for Edge AI. Training deep neural netwo...
Although multi-view learning has made signifificant progress over the pa...
We study reinforcement learning (RL) for text-based games, which are
int...
Deep neural networks have achieved great success both in computer vision...
In this paper, we propose a one-stage online clustering method called
Co...
In this paper, the Point Adversarial Self Mining (PASM) approach, a simp...
Graph Neural Networks (GNN) has demonstrated the superior performance in...
Face verification can be regarded as a 2-class fine-grained visual
recog...
In this paper, we study two challenging and less-touched problems in sin...
Edge devices demand low energy consumption, cost and small form factor. ...
In this paper, we target on advancing the performance in facial expressi...
Recent works that utilized deep models have achieved superior results in...
To facilitate depth-based 3D action recognition, 3D dynamic voxel (3DV) ...
The real-world data usually exhibits heterogeneous properties such as
mo...
Along with the extensive applications of CNN models for classification, ...
Current summarization systems only produce plain, factual headlines, but...
State-of-the-art neural machine translation (NMT) systems are data-hungr...
Is recurrent network really necessary for learning a good visual
represe...
Reading comprehension (RC) has been studied in a variety of datasets wit...
A panoply of multi-view clustering algorithms has been developed to deal...
For 3D hand and body pose estimation task in depth image, a novel
anchor...
Nonlinear regression has been extensively employed in many computer visi...
Machine learning algorithms are often vulnerable to adversarial examples...
Recently, several adversarial attack methods to black-box deep neural
ne...
Effective and real-time eyeblink detection is of wide-range applications...
In this paper, we study how to make clustering benefiting from different...
Person re-identification is indeed a challenging visual recognition task...
Dynamic image is the recently emerged action representation paradigm abl...
Multi-instance multi-label (MIML) learning has many interesting applicat...