基于多尺度和全局交叉注意力的视听情感识别方法及系统
By combining multi-scale convolutional attention and global cross-attention modules, multi-scale emotional features in audiovisual emotion recognition are extracted and fused, solving the problems of insufficient and redundant modal feature expression in existing technologies and achieving more efficient emotion recognition results.
CN116758451BActive Publication Date: 2026-07-17SHANDONG COMP SCI CENTNAT SUPERCOMP CENT IN JINAN +1
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHANDONG COMP SCI CENTNAT SUPERCOMP CENT IN JINAN
- Filing Date
- 2023-05-24
- Publication Date
- 2026-07-17
Smart Images
Figure CN116758451B_ABST
Abstract
本发明属于情感计算技术领域，提供了基于多尺度和全局交叉注意力的视听情感识别方法及系统，通过多尺度卷积注意力模块，提取不同上下文尺度的模态关键情感特征，弥补了单一尺度特征不足以表达人类复杂情感的缺陷。通过全局交叉注意力模块，同时考虑模态间和模态内的交互，从而学习更丰富的模态交互信息，并且减少了融合特征中的冗余。最后又设计了多尺度特征学习模块，从融合特征中进一步学习对两个模态共同有意义的情感信息。通过以上改进，最终所提出的方法能够实现更好的情感识别准确率和更高效的情感识别效率。
Need to check novelty before this filing date? Find Prior Art