Estimation of continuous valence and arousal levels from faces in naturalistic conditions, Nature Machine Intelligence 2021

Nature Machine Intelligence 2021

Antoine Toisoul, Jean Kossaifi, Adrian Bulat, Georgios Tzimiropoulos and Maja Pantic

Samsung AI Center
Imperial College London

We present a novel neural network architecture to estimate categorical emotions (e.g., happiness, sadness, anger…) and continuous emotions in terms of valence (how positive or negative the state of mind is) and arousal (how calming or exciting the experience is) with a very high level of accuracy. In addition, our network is able to estimate facial landmarks at no additional cost and is suitable for real-time applications. For full details please read our article available on the Nature Machine Intelligence website.

---

Code : The testing code and models trained on the AffectNet dataset are available here.