TAL EmotioNet Challenge 2020 Rethinking the Model Chosen Problem in Multi-Task Learning

CVPR Workshops(2020)

引用 6|浏览51
暂无评分
摘要
This paper introduces our approach to the EmotioNet Challenge 2020. We pose the AU recognition problem as a multi-task learning problem, where the non-rigid facial muscle motion (mainly the first 17 AUs) and the rigid head motion (the last 6 AUs) are modeled separately. The co-occurrence of the expression features and the head pose features are explored. We observe that different AUs converge at various speed. By choosing the optimal checkpoint for each AU, the recognition results are improved. We are able to obtain a final score of 0.746 in validation set and 0.7306 in the test set of the challenge.
更多
查看译文
关键词
expression features,rigid head motion,nonrigid facial muscle motion,multitask learning problem,AU recognition problem,model chosen problem,TAL EmotioNet Challenge 2020
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要