Hui Yu

Intelligence Extraction Method of Domain Terms for Chinese Web Documents Based on Hierarchical Combination Strategy

2016

Domain terms extraction based on Chinese Web document is an important step in the field of Chinese text information into machine recognition, and it is also the technical basis of intelligence information processing in domain …

The Review of Discourse-Based Machine Translation Evaluation

2018 · Proceedings of the 2018 International Conference on Network, Communication, Computer Engineering (NCCE 2018)

This article reviews the discourse-based machine translation evaluation metrics. According to different methods of using, machine translation evaluation based on discourse is divided into two categories: evaluation based on discourse structure and evaluation based on …

Deep Learning-Based Fully Automated Detection and Segmentation of Breast Mass

2020

In the field of breast mass detection, there are many of small-scale masses in the image. However, most of the existing target detection models have low accuracy in detecting small-scale masses, which is prone to …

GIDN: A Lightweight Graph Inception Diffusion Network for High-efficient Link Prediction

2022 · arXiv (Cornell University)

In this paper, we propose a Graph Inception Diffusion Networks(GIDN) model. This model generalizes graph diffusion in different feature spaces, and uses the inception module to avoid the large amount of computations caused by complex …

Privacy-Preserving Range Query Quantum Scheme With Single Photons in Edge-Based Internet of Things

2023 · IEEE Transactions on Network and Service Management

Range query in cloud-based outsourcing applications is an important data search service, but it can suffer from privacy disclosure. In this paper, we generalize and redefine privacy-preserving range query in edge-based Internet of Things (IoT). …

HG-SFDA: HyperGraph Learning Meets Source-Free Unsupervised Domain Adaptation

2025 · IEEE Transactions on Image Processing

Source-Free unsupervised Domain Adaptation (SFDA) aims to classify target samples by only accessing a pre-trained source model and unlabelled target samples. Since no source data is available, transferring the knowledge from the source domain to …