The investigation of the similarity between artists and music is crucial...
Data augmentation has been widely used in low-resource NER tasks to tack...
Graph contrastive learning (GCL) shows great potential in unsupervised g...
Image manipulation on the latent space of the pre-trained StyleGAN can
c...
Data augmentation is a widely used technique for enhancing the generaliz...
Deep neural networks are powerful, but they also have shortcomings such ...
Face recognition has achieved considerable progress in recent years than...
Image transformation, a class of vision and graphics problems whose goal...
Data augmentation is a very practical technique that can be used to impr...
Deep learning has achieved remarkable results in many computer vision ta...
Deep neural networks (DNNs) have been proven to be vulnerable to adversa...
One of the most effective methods of channel pruning is to trim on the b...
Subtext is a kind of deep semantics which can be acquired after one or m...
Single object tracking (SOT) is currently one of the most important task...
Convolutional neural network (CNN) is a class of artificial neural netwo...
As a popular machine learning method, neural networks can be used to sol...
With the development of feed-forward models, the default model for seque...
Deeper neural networks are hard to train. Inspired by the elastic collis...
Context-aware recommender systems (CARS), which consider rich side
infor...
Recent studies have demonstrated that the convolutional networks heavily...
Class incremental learning refers to a special multi-class classificatio...
User response prediction makes a crucial contribution to the rapid
devel...