TAL EmotioNet Challenge 2020 Rethinking the Model Chosen Problem in Multi-Task Learning
This work addresses facial expression analysis for computer vision applications, but it is incremental as it focuses on optimizing checkpoint selection in an existing multi-task learning setup.
The paper tackled Action Unit (AU) recognition in facial expressions by modeling non-rigid facial muscle motion and rigid head motion separately in a multi-task learning framework, achieving a final score of 0.7306 on the test set of the EmotioNet Challenge 2020.
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.