Jie Zou

Prof. Jie Zou

University of Electronic Science and Technology of China, Chengdu, Sichuan, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications

23 February 2025 in WIREs Data Mining and Knowledge Discovery
Verified
Journal Article
Closed access
LKLazarus Kwao
Lazarus Kwao
YYYang Yang
Yang Yang
JZJie Zou
Jie Zou
JMJing MA
Jing MA


5 June 2024 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
KLKe Liu
Ke Liu
JWJiwei Wei
Jiwei Wei
JZJie Zou
Jie Zou
PWPeng Wang
Peng Wang
YYYang Yang
Yang Yang
HSHeng Tao Shen
Heng Tao Shen
Multi-view speech emotion recognition (SER) based on the pre-trained model has gained attention in the last two years, which shows great potential in improving the model performance in speaker-independent scenarios. However, the existing work either relies on various fine-tuning methods or uses excessive feature views with complex fusion strategies, causing the increase of complexity with limited performance benefit. In this paper, we improve multi-view SER based on the pre-trained model from the perspective of a low-level speech feature. Specifically, we forgo fine-tuning the pre-trained model and instead focus on learning effective features hidden in the low-level speech feature mel-scale frequency cepstral coefficient (MFCC). We propose a t wo- s tream p ooling c hannel a ttention ( TsPCA ) module to discriminatively weight the channel dimensions of the features derived from MFCC. This module enables inter-channel interaction and learning of emotion sequence information across channels. Furthermore, we design a simple but effective feature view fusion strategy to learn robust representations. In the comparison experiments, our method achieves the WA and UA of 73.97%/74.69% and 74.61%/75.66% on the IEMOCAP dataset, 97.21% and 97.11% on the Emo-DB dataset, 77.08% and 77.34% on the RAVDESS dataset, and 74.38% and 71.43% on the SAVEE dataset. Extensive experiments on the four datasets demonstrate that our method consistently surpasses existing methods and achieves a new state-of-the-art result.


1 January 2025 in Kidney Diseases
Verified
Journal Article
Open access
CLCheng Li
Cheng Li
JLJing Liu
Jing Liu
PFPing Fu
Ping Fu
JZJie Zou
Jie Zou
Background: Artificial intelligence (AI) has made significant advances in nephrology, revolutionizing the diagnosis, prognosis, and treatment of kidney diseases. Summary: This review provides an overview of AI applications in nephrology, introducing the basic structures of each model, highlighting both traditional machine-learning approaches and neural networks, and providing model application comparisons along with selection recommendations. It discussed key challenges in deciding appropriate AI models for specific tasks and evaluated their advantages, limitations, and optimal use cases. Current applications of AI in nephrology mainly include diagnosis and disease outcome prediction, medical image analysis, treatment recommendations, and personalized health management, supported by massive electronic health records and multimodal data integration. Traditional machine learning models perform well on datasets of varying sizes and structures, while neural networks excel at handling complex and imaging data. Emerging hardware innovations are expected to improve the performance of neural network models, enabling more accurate diagnosis and automated analysis in clinical practice. In the future, AI will have great potential to advance individualized patient care and enable real-time data processing in nephrology. Key Messages: An overview of AI applications in nephrology is provided in this review.