用双方向注意力网络提升面部表情识别准确率
Enhancing Facial Expression Recognition through Dual-Direction Attention Mixed Feature Networks and CLIP: Application to 8th ABAW Challenge
- 采用双方向注意力混合特征网络统一处理三类表情任务
- 在8届ABAW挑战赛中超越基线模型表现
- 验证CLIP对情感识别的增益，提供可复现架构设计
我们提交了2025年CVPR会议第8届ABAW挑战赛的参赛作品，针对唤醒度-效价估计、情绪识别和面部动作单元检测三个独立任务提出解决方案。方法统一采用成熟的双方向注意力混合特征网络（DDAMFN），在三项任务上均优于基准模型。此外，我们在情绪识别任务中额外引入CLIP进行实验性探索。论文深入分析了模型架构选择对性能提升的关键作用，为后续研究提供可参考的技术路径。
原文摘要 · Abstract (English)
We present our contribution to the 8th ABAW challenge at CVPR 2025, where we tackle valence-arousal estimation, emotion recognition, and facial action unit detection as three independent challenges. Our approach leverages the well-known Dual-Direction Attention Mixed Feature Network (DDAMFN) for all three tasks, achieving results that surpass the proposed baselines. Additionally, we explore the use of CLIP for the emotion recognition challenge as an additional experiment. We provide insights into the architectural choices that contribute to the strong performance of our methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。