Deep Structured Prediction for Facial Landmark Detection
This addresses the issue of poor generalization in facial landmark detection for applications like computer vision, though it is incremental as it builds on existing deep learning methods.
The paper tackled the problem of facial landmark detection by embedding structural dependencies among landmark points, achieving superior performance and better generalization on challenging datasets with large pose and occlusion.
Existing deep learning based facial landmark detection methods have achieved excellent performance. These methods, however, do not explicitly embed the structural dependencies among landmark points. They hence cannot preserve the geometric relationships between landmark points or generalize well to challenging conditions or unseen data. This paper proposes a method for deep structured facial landmark detection based on combining a deep Convolutional Network with a Conditional Random Field. We demonstrate its superior performance to existing state-of-the-art techniques in facial landmark detection, especially a better generalization ability on challenging datasets that include large pose and occlusion.