Spatial-Temporal Knowledge Integration: Robust Self-Supervised Facial Landmark Tracking
MM '20: The 28th ACM International Conference on Multimedia Seattle WA USA October, 2020, pp. 4135-4143, 2020.
Diversity of training data significantly affects tracking robustness of model under unconstrained environments. However, existing labeled datasets for facial landmark tracking tend to be large but not diverse, and manually annotating the massive clips of new diverse videos is extremely expensive. To address these problems, we propose a Sp...More
PPT (Upload PPT)