Zhigang Zeng

Improved black-box attack based on query and perturbation distribution

2021

Adversarial examples cause the deep neural network prediction error, which is a great threat to the deep neural network. How to generate more natural adversarial examples and improve the robustness of deep neural networks has …

GraphCFC: A Directed Graph Based Cross-Modal Feature Complementation Approach for Multimodal Conversational Emotion Recognition

2022 · arXiv (Cornell University)

Emotion Recognition in Conversation (ERC) plays a significant part in Human-Computer Interaction (HCI) systems since it can provide empathetic services. Multimodal ERC can mitigate the drawbacks of uni-modal approaches. Recently, Graph Neural Networks (GNNs) have …

Harnessing Neural Unit Dynamics for Effective and Scalable Class-Incremental Learning

2024 · arXiv (Cornell University)

Class-incremental learning (CIL) aims to train a model to learn new classes from non-stationary data streams without forgetting old ones. In this paper, we propose a new kind of connectionist model by tailoring neural unit …