Mixup is a well-established data augmentation technique, which can exten...
Recently, efficient fine-tuning of large-scale pre-trained models has
at...
The inherent challenge of multimodal fusion is to precisely capture the
...
Multimodal machine learning has achieved remarkable progress in a wide r...
Classifying incomplete multi-view data is inevitable since arbitrary vie...
Subpopulation shift exists widely in many real-world applications, which...
Large language models have demonstrated surprising ability to perform
in...
Infrared and visible image fusion can compensate for the incompleteness ...
Image-based head swapping task aims to stitch a source head to another s...
Multi-view learning has progressed rapidly in recent years. Although man...
Open set recognition enables deep neural networks (DNNs) to identify sam...
Deep learning models suffer from catastrophic forgetting when learning n...
Semantic segmentation with limited annotations, such as weakly supervise...
Learning from different data views by exploring the underlying complemen...
The abductive natural language inference task (αNLI) is proposed to
infe...
Multimodal regression is a fundamental task, which integrates the inform...
For video recognition task, a global representation summarizing the whol...
Most existing domain adaptation methods focus on adaptation from only on...
Crowd counting on the drone platform is an interesting topic in computer...
To promote the developments of object detection, tracking and counting
a...
Although multi-view learning has made signifificant progress over the pa...
Although significant progress achieved, multi-label classification is st...
Deep neural networks are highly effective when a large number of labeled...
Deep learning-based object detection and instance segmentation have achi...
Smart city has been consider the wave of the future and the route
recomm...
Recent works have demonstrated that global covariance pooling (GCP) has ...
Drone equipped with cameras can dynamically track the target in the air ...
Drones, or general UAVs, equipped with cameras have been fast deployed w...
This paper proposes a space-time multi-scale attention network (STANet) ...
Channel attention has recently demonstrated to offer great potential in
...
Blind deconvolution is a classical yet challenging low-level vision prob...
Multi-view subspace clustering aims to discover the inherent structure b...
Along with the deraining performance improvement of deep networks, their...
Question answering (QA) is an important natural language processing (NLP...
Deep Convolution Neural Networks (CNN) have achieved significant perform...
Data-driven saliency detection has attracted strong interest as a result...
Though deep neural networks have achieved state-of-the-art performance i...
In this paper we present a large-scale visual object detection and track...
Background modeling is a critical component for various vision-based
app...
Feature selection is an important preprocessing step in machine learning...