Dong Huang

Analysis of solar energy potentials at Nansha Guangzhou

2019 · IOP Conference Series Earth and Environmental Science

The increasing energy supply is believed to exceed the capacity of three existing thermal power plants at Nansha Guangzhou for the rapid development. Thus constructing an eco-friendly energy structure will be one of the main …

Vision Transformer for Contrastive Clustering

2022 · arXiv (Cornell University)

Vision Transformer (ViT) has shown its advantages over the convolutional neural network (CNN) with its ability to capture global long-range dependencies for visual representation learning. Besides ViT, contrastive learning is another popular research topic recently. …

Artificial Intelligence-Oriented User Interface Design and Human Behavior Recognition based on Human–Computer Nature Interaction

2022 · International Journal of Humanoid Robotics

This work is to explore the application of intelligent algorithms based on deep learning in human–computer interaction systems, hoping to promote the development of human–computer interaction systems in the field of behavior recognition. Firstly, the …

Heterogeneous Tri-stream Clustering Network

2023 · arXiv (Cornell University)

Contrastive deep clustering has recently gained significant attention with its ability of joint contrastive learning and clustering via deep neural networks. Despite the rapid progress, previous works mostly require both positive and negative sample pairs …

Towards Building More Robust Models with Frequency Bias

2023 · arXiv (Cornell University)

The vulnerability of deep neural networks to adversarial samples has been a major impediment to their broad applications, despite their success in various fields. Recently, some works suggested that adversarially-trained models emphasize the importance of …

Incorporating emoji sentiment information into a pre-trained language model for Chinese and English sentiment analysis

2024 · Intelligent Data Analysis

Emojis in texts provide lots of additional information in sentiment analysis. Previous implicit sentiment analysis models have primarily treated emojis as unique tokens or deleted them directly, and thus have ignored the explicit sentiment information …

Correlation Analysis of Adversarial Attack in Time Series Classification

2024 · arXiv (Cornell University)

This study investigates the vulnerability of time series classification models to adversarial attacks, with a focus on how these models process local versus global information under such conditions. By leveraging the Normalized Auto Correlation Function …

Simple One-Step Multi-View Clustering With Fast Similarity and Cluster Structure Learning

2025 · IEEE Signal Processing Letters

Multi-view clustering (MVC) is essential for integrating heterogeneous data from multiple sources. However, many existing approaches are hindered by high computational complexity and the separate optimization of similarity and cluster structures. In light of these …

Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward

2025 · arXiv (Cornell University)

Reinforcement learning (RL) has been widely adopted to enhance the performance of large language models (LLMs) on Text-to-SQL tasks. However, existing methods often rely on execution-based or LLM-based Bradley-Terry reward models. The former suffers from …