Cognition-Inspired Dual-Stream Semantic Enhancement for Vision-Based Dynamic Emotion Modeling
启发认知的双流语义增强用于基于视觉的动态情绪建模
机构 * College of Intelligent Robotics and Advanced Manufacturing, Fudan University(复旦大学智能机器人与先进制造学院) ; Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University(上海智能信息处理重点实验室,复旦大学计算机科学与人工智能学院) ; School of Data Science and Engineering, East China Normal University(华东师范大学数据科学与工程学院)
AI总结 本文提出DuSE模型,通过双流架构模拟认知过程,提升动态面部表情识别的鲁棒性和可解释性。
Comments Accepted by IEEE ICRA 2026