- Food Supply Chain Traceability
- Radiomics and Machine Learning in Medical Imaging
- Recommender Systems and Techniques
- Computational Physics and Python Applications
- Gastrointestinal Tumor Research and Treatment
- Tensor decomposition and applications
- Animal Behavior and Welfare Studies
- Ammonia Synthesis and Nitrogen Reduction
- COVID-19 diagnosis using AI
- Lung Cancer Diagnosis and Treatment
- Effects of Environmental Stressors on Livestock
- Catalysts for Methane Reforming
- Sentiment Analysis and Opinion Mining
- Catalytic Processes in Materials Science
- Metastasis and carcinoma case studies
- Image Retrieval and Classification Techniques
Tianjin University of Technology
2025
Wuhan University of Technology
2024
Sichuan University
2024
Lanzhou University
2023
First Hospital of Lanzhou University
2023
Data from multimodalities bring complementary information for deep learning-based medical image classification models. However, data fusion methods simply concatenating features or images barely consider the correlations complementarities among different modalities and easily suffer exponential growth in dimensions computational complexity when modality increases. Consequently, this article proposes a subspace network with tensor decomposition (TD) to heighten multimodal classification. We...
With the continuous development of medical informatics and digital diagnosis, classification tuberculosis cases from computed tomography (CT) images lung based on deep learning is an important guiding aid in clinical diagnosis treatment. Due to its potential application image classification, this task has received extensive research attention. Existing related neural network techniques are still challenging terms feature extraction global contextual information complexity achieving...
Esophageal sarcomatoid carcinoma (ESC) is a rare pathological subtype of esophageal carcinomas, wherein its epithelial component typically demonstrates squamous cell (SCC). However, the clinicopathological features and prognosis ESC remain unclear, alongside unique aspects compared to SCC (ESCC).
Click-through rate (CTR) Prediction is a crucial task in personalized information retrievals, such as industrial recommender systems, online advertising, and web search. Most existing CTR models utilize explicit feature interactions to overcome the performance bottleneck of implicit interactions. Hence, deep based on parallel structures (e.g., DCN, FinalMLP, xDeepFM) have been proposed obtain joint from different semantic spaces. However, these subcomponents lack effective supervisory...