With the increasing penetration of machine learning applications in crit...
We study how to train personalized models for different tasks on
decentr...
Domain generalization (DG) aims to tackle the distribution shift between...
Deep neural networks (DNNs) have shown exciting performance in various t...
The field of deep learning has witnessed significant progress, particula...
Data augmentation is a critical contributing factor to the success of de...
Black-box attacks can generate adversarial examples without accessing th...
Existing few-shot learning (FSL) methods rely on training with a large
l...
The leverage of large volumes of web videos paired with the searched que...
Personalized federated learning is proposed to handle the data heterogen...
We present prompt distribution learning for effectively adapting a
pre-t...
Mainstream state-of-the-art domain generalization algorithms tend to
pri...
Self-supervised learning (SSL) has recently become the favorite among fe...
Knowledge Distillation (KD) is a popular technique to transfer knowledge...
Domain generalization in person re-identification is a highly important
...
The adversarial vulnerability of deep neural networks has attracted
sign...
Skeleton-based human action recognition has attracted much attention wit...
With the knowledge of action moments (i.e., trimmed video clips that eac...
Convolutional neural networks (CNNs) have achieved state-of-the-art resu...
Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art
...
Dropout has been proven to be an effective algorithm for training robust...
Although deep neural networks are highly effective, their high computati...
Temporally localizing actions in a video is a fundamental challenge in v...
Unsupervised image-to-image translation is the task of translating an im...
Convolutional Neural Networks (CNN) have been regarded as a powerful cla...
Rendering synthetic data (e.g., 3D CAD-rendered images) to generate
anno...
Existing methods for single image super-resolution (SR) are typically
ev...
Multitask learning (MTL) aims to learn multiple tasks simultaneously thr...
Recently, Siamese network based trackers have received tremendous intere...
Domain generalization aims to apply knowledge gained from multiple label...
Observing that Semantic features learned in an image classification task...
Visual reranking is effective to improve the performance of the text-bas...