In real-world applications, perfect labels are rarely available, making ...
Modern neural networks are known to give overconfident prediction for
ou...
As more and more artificial intelligence (AI) technologies move from the...
As an important part of intelligent transportation systems, traffic
fore...
With the rapid development of eXplainable Artificial Intelligence (XAI),...
Detecting out-of-distribution (OOD) samples is crucial to the safe deplo...
Most existing point cloud completion methods are only applicable to part...
Multi-modal Multi-label Emotion Recognition (MMER) aims to identify vari...
Noisy labels damage the performance of deep networks. For robust learnin...
Conventional unsupervised domain adaptation (UDA) methods need to access...
Time series has wide applications in the real world and is known to be
d...
Co-training, extended from self-training, is one of the frameworks for
s...
Unsupervised domain adaptation aims to transfer knowledge from a labeled...
Unsupervised domain adaptation aims at transferring knowledge from the
l...
Unsupervised domain adaptation aims at transferring knowledge from the
l...
Transfer learning has been demonstrated to be successful and essential i...
With the emergence of diverse data collection techniques, objects in rea...