Video-Based Face Alignment With Local Motion Modeling
| Autor: | Nacim Ihaddadene, Chaabane Djeraba, Pierre Tirilly, Romain Belmonte, Ioan Marius Bilasco |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Hierarchy (mathematics)
Computer science business.industry Pixel connectivity Pattern recognition 02 engineering and technology 010501 environmental sciences 01 natural sciences Motion (physics) Regression Recurrent neural network Robustness (computer science) Face (geometry) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business 0105 earth and related environmental sciences Coherence (physics) |
| Zdroj: | WACV |
| DOI: | 10.1109/wacv.2019.00228 |
| Popis: | Face alignment remains difficult under uncontrolled conditions due to the many variations that may considerably impact facial appearance. Recently, video-based approaches have been proposed, which take advantage of temporal coherence to improve robustness. These new approaches suffer from limited temporal connectivity. We show that early, direct pixel connectivity enables the detection of local motion patterns and the learning of a hierarchy of motion features. We integrate local motion to the two predominant models in the literature, coordinate regression networks and heatmap regression networks, and combine it with late connectivity based on recurrent neural networks. The experimental results on two datasets, 300VW and SNaP-2DFe, show that local motion improves video-based face alignment and is complementary to late temporal information. Despite the simplicity of the proposed architectures, our best model provides competitive performance with more complex models from the literature. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|