Deep graph neural network-based spammer detection under the perspective of heterogeneous cyberspace
Due to the severe threat to cyberspace security, detection of online spammers has been a
universal concern of academia. Nowadays, prevailing literature of this field almost leveraged …
universal concern of academia. Nowadays, prevailing literature of this field almost leveraged …
Efficient and effective training of sparse recurrent neural networks
Recurrent neural networks (RNNs) have achieved state-of-the-art performances on various
applications. However, RNNs are prone to be memory-bandwidth limited in practical …
applications. However, RNNs are prone to be memory-bandwidth limited in practical …
Multi-threshold deep metric learning for facial expression recognition
W Yang, J Yu, T Chen, Z Liu, X Wang, J Shen - Pattern Recognition, 2024 - Elsevier
Feature representations generated through triplet-based deep metric learning offer
significant advantages for facial expression recognition (FER). Each threshold in triplet loss …
significant advantages for facial expression recognition (FER). Each threshold in triplet loss …