Junjie Ye

Dr. Junjie Ye

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 March 2022 in Applied Intelligence
Verified
Journal Article
Closed access
PDF file
JYJunjie Ye
Junjie Ye
JGJunjun Guo
Junjun Guo


1 December 2024 in Neural Networks
Verified
Journal Article
Closed access
XZXiaojun Zhou
Xiaojun Zhou
CZChunna Zhao
Chunna Zhao
YHYaqun Huang
Yaqun Huang
ZCZhou Chengli
Zhou Chengli
JYJunjie Ye
Junjie Ye

2 August 2023 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
JGJunjun Guo
Junjun Guo
JYJunjie Ye
Junjie Ye
YXYan Xiang
Yan Xiang
ZYZhengtao Yu
Zhengtao Yu
Multi-modal neural machine translation (MNMT) aims to translate sentences from the source language into the target language with the aid of corresponding images. Unfortunately, there is a considerable modality gap between the semantic-related images and texts in terms of data form and semantic expression. How to fully incorporate visual information into texts to enhance the performance of machine translation is one of the critical issues for MNMT. However, the initial visual and textual features are generally extracted with their modality-specific models; Consequently, there is a considerable representation gap between images and texts. Most previous MNMT works prefer only to adopt the feature-level fusion strategies to learn multi-modal representation, while the modality representation gap is often ignored. To this end, this paper proposes a progressive multi-modal Transformer (ProMul-Trans) with Modality Difference-Aware (MDA) to address the visual-to-textual fusion problem raised in MNMT. We first employ MDA to capture the modality-consistency information by taking visual and textual representations as inputs in each Transformer layer. Then a layer-level progressive fusion (Layer-ProFusion) strategy is adopted to progressively align visual and textual representations layer-by-layer to enhance machine translation performance. Experiment results on the Multi30k dataset are conducted, and the results show that the proposed approach outperforms the compared state-of-the-art (SOTA) methods on English $\rightarrow$ German (En $\rightarrow$ De), English $\rightarrow$ French (En $\rightarrow$ Fr) and English $\rightarrow$ Czech (En $\rightarrow$ Cs) tasks. We release the code at https://github.com/JunjieYe-MMT/HierProMul-Trans .

22 May 2025 in Knowledge-Based Systems
Verified
Journal Article
Closed access
JYJunjie Ye
Junjie Ye
JLJinhong Li
Jinhong Li
RSRui Su
Rui Su
SYSen Yang
Sen Yang
YHYaqun Huang
Yaqun Huang
CZChunna Zhao
Chunna Zhao

22 July 2024 in Fractal and Fractional
Verified
Journal Article
Open access
PDF file
CZChunna Zhao
Chunna Zhao
JYJunjie Ye
Junjie Ye
ZZZhu Zelong
Zhu Zelong
YHYaqun Huang
Yaqun Huang
Time series forecasting has played an important role in different industries, including economics, energy, weather, and healthcare. RNN-based methods have shown promising potential due to their strong ability to model the interaction of time and variables. However, they are prone to gradient issues like gradient explosion and vanishing gradients. And the prediction accuracy is not high. To address the above issues, this paper proposes a Fractional-order Lipschitz Recurrent Neural Network with a Frequency-domain Gated Attention mechanism (FLRNN-FGA). There are three major components: the Fractional-order Lipschitz Recurrent Neural Network (FLRNN), frequency module, and gated attention mechanism. In the FLRNN, fractional-order integration is employed to describe the dynamic systems accurately. It can capture long-term dependencies and improve prediction accuracy. Lipschitz weight matrices are applied to alleviate the gradient issues. In the frequency module, temporal data are transformed into the frequency domain by Fourier transform. Frequency domain processing can reduce the computational complexity of the model. In the gated attention mechanism, the gated structure can regulate attention information transmission to reduce the number of model parameters. Extensive experimental results on five real-world benchmark datasets demonstrate the effectiveness of FLRNN-FGA compared with the state-of-the-art methods.