A5107699658- Emotion and Mood Recognition
- Image Processing Techniques and Applications
- Advanced Vision and Imaging
- Cognitive Abilities and Testing
- Vehicle Noise and Vibration Control
- Brain Tumor Detection and Classification
- Traffic control and management
- Natural Language Processing Techniques
- Engineering Applied Research
- Real-time simulation and control systems
- EEG and Brain-Computer Interfaces
- Transportation Planning and Optimization
- Action Observation and Synchronization
- Advanced Image Processing Techniques
- Traffic Prediction and Management Techniques
- Face recognition and analysis
- Face and Expression Recognition
- Topic Modeling
Fudan University
2024
Dalian University of Technology
2024
Dynamic Facial Expression Recognition (DFER) is crucial for affective computing but often overlooks the impact of scene context. We have identified a significant issue in current DFER tasks: human annotators typically integrate emotions from various angles, including environmental cues and body language, whereas existing methods tend to consider as noise that needs be filtered out, focusing solely on facial information. refer this Rigid Cognitive Problem. The Problem can lead discrepancies...
Although text-based large language models exhibit human-level writing ability and remarkable intelligence, speech (SLMs) still struggle to generate semantically coherent outputs. There are several potential reasons for this performance degradation: (A) tokens mainly provide phonetic information rather than semantic information, (B) the length of sequences is much longer that text sequences, (C) paralinguistic such as prosody, introduces additional complexity variability. In paper, we explore...
In the field of affective computing, fully leveraging information from a variety sensory modalities is essential for comprehensive understanding and processing human emotions. Inspired by process through which brain handles emotions theory cross-modal plasticity, we propose UMBEnet, brain-like unified modal network. The primary design UMBEnet includes Dual-Stream (DS) structure that fuses inherent prompts with Prompt Pool Sparse Feature Fusion (SFF) module. aimed at integrating different...