A5053041234- Emotion and Mood Recognition
- Face recognition and analysis
- Speech and Audio Processing
- Anomaly Detection Techniques and Applications
- Protein Hydrolysis and Bioactive Peptides
- vaccines and immunoinformatics approaches
- Machine Learning in Bioinformatics
- Time Series Analysis and Forecasting
- Music and Audio Processing
- Gaze Tracking and Assistive Technology
- Antimicrobial Peptides and Activities
- Face and Expression Recognition
- Aquatic life and conservation
Baidu (China)
2024
Guangzhou Academy of Fine Arts
2024
Hefei University of Technology
2020-2022
When using neural networks to recognize facial expressions, determining which features help identify different expressions is essential, and there a massive information transmission loss between layers of network with multiple layers. This paper proposes robust vectorized convolutional (CNN) model that introduces an attention mechanism for extracting in the region interests(ROIs) face. The ROIs image are marked before input into network. In particular, concept adopted first layer proposed...
Due to the broad-spectrum and high-efficiency antibacterial activity, antimicrobial peptides (AMPs) their functions have been studied in field of drug discovery. Using biological experiments detect AMPs corresponding activities require a high cost, whereas computational technologies do so for much less. Currently, most methods solve identification as two independent tasks, which ignore relationship between them. Therefore, combination sharing patterns tasks is crucial problem that needs be...
Personality analysis is widely used in occupational aptitude tests and entrance psychological tests. However, answering hundreds of questions at once seems to be a burden. Inspired by personality psychology, we propose multimodal attention network with Category-based mean square error (CBMSE) for assessment. With this method, can obtain information about one's behaviour from his or her daily videos, including gaze distribution, speech features, facial expression changes, accurately determine...
Microexpression recognition from short video sequences is a challenging problem in computer vision and multimedia research. This article proposes dual expression fusion (DEF) microexpression framework, which performs better on more general videos. framework uses deep learning models to extract the facial features single frame while directly predicting action units (AUs) states of that frame. Then, long short-term memory network (LSTM) predicts category sequence features. To perform across...
Current deep learning models for time series often face challenges with generalizability in scenarios characterized by limited samples or inadequately labeled data. By tapping into the robust generative capabilities of diffusion models, which have shown success computer vision and natural language processing, we see potential improving adaptability models. However, specific application generating classification tasks remains underexplored. To bridge this gap, introduce MDGPS model,...