Dan Liu

TL;DR: A novel signal recognition algorithm based on support vector machine (SVM) in cognitive networks is proposed that identifies hostile signals from hostile users and can be successfully recognized in low SNR environment.

TL;DR: This article proposed an improved key sentence extraction algorithm based on features computing, which not only considers word level features, such as keywords attribute, sentiment attribute, verb attribute, conjunction attribute, summary word attribute and viewpoint word attribute, but also includes sentence level features such as position attribute, sentence frequency attribute and title similarity attribute.

TL;DR: WREG-KD as discussed by the authors proposes a target-guided knowledge distillation framework that accounts for region-expression pairs reconstruction and matching, and reactivates the target-related prediction information learned by a pre-trained teacher model to guide the training process and boost the performance of student model.

TL;DR: A deep residual network model Res-HASR with hierarchical attention and event structure representation with significantly improves the performance of event coreference fusion significantly compared with the two basic models.