A robust automatic micro-expression recognition system would have broad applications in national safety, police interrogation, and clinical diagnosis. Developing such a system requires high quality databases with sufficient training samples which are currently not available. We reviewed the previously developed micro-expression databases and built an improved one (CASME II), with higher temporal resolution (200 fps) and spatial resolution (about 280×340 pixels on facial area). We elicited participants' facial expressions in a well-controlled laboratory environment and proper illumination (such as removing light flickering). Among nearly 3000 facial movements, 247 micro-expressions were selected for the database with action units (AUs) and emotions labeled. For baseline evaluation, LBP-TOP and SVM were employed respectively for feature extraction and classifier with the leave-one-subject-out cross-validation method. The best performance is 63.41% for 5-class classification.

No abstract

The energy-storage capacities of a series of water-stable porous metal-organic frameworks, based on high-valence metal cations (Al , Fe , Cr , Ti , Zr ) and polycarboxylate linkers, were evaluated under the typical conditions of seasonal energy-storage devices. The results showed that the microporous hydrophilic Al-dicarboxylate MIL-160(Al) exhibited one of the best performances. To assess the properties of this material for space-heating applications on a laboratory pilot scale with an open reactor, a new synthetic route involving safer, greener conditions was developed. This led to the production of MIL-160(Al) on a 400 g scale, before the material was shaped into pellets through a wet-granulation method. The material exhibited a very high energy-storage capacity for a physical-sorption material (343 Wh kg ), which is in full agreement with the predicted value.