Search

Abstract When a person attempts to conceal an emotion, the genuine emotion is manifest as a micro-expression. Exploration of automatic facial micro-expression recognition systems is relatively new in the computer vision domain. This is due to the difficulty in implementing optimal feature extraction methods to cope with the subtlety and brief motion characteristics of the expression. Most of the existing approaches extract the subtle facial movements based on hand-crafted features. In this paper, we address the micro-expression recognition task with a convolutional neural network (CNN) architecture, which well integrates the features extracted from each video. We introduce the Optical Flow Features from Apex frame Network (OFF-ApexNet). This is a new feature descriptor that combines the optical flow guided context with the CNN. Firstly, we obtain the location of the apex frame from each video sequence as it portrays the highest intensity of facial motion among all frames. Then, the optical flow information are attained from the apex frame and a reference frame (i.e., onset frame). Finally, the optical flow features are fed into a pre-designed CNN model for further feature enhancement as well as to carry out the expression classification. To evaluate the effectiveness of OFF-ApexNet method, comprehensive evaluations are conducted on three public spontaneous micro-expression datasets (i.e., SMIC, CASME II and SAMM). The promising recognition result suggests that the proposed method can optimally describe the significant micro-expression details. In particular, we report that, in a multi-database with leave-one-subject-out cross-validation (LOSOCV) experimental protocol, the recognition performance reaches 74.60% of recognition accuracy and F-measure of 71.04%. We also note that this is the first work that performs cross-dataset validation on three databases in this domain. Highlights • Only two frames from each video were utilized to represent significant motion features. • A feature extractor that incorporates both the handcrafted and data-drive features were proposed. • Promising performances were obtained in three micro-expression databases. • A comparison of the proposed method with the state-of-the-arts was reported. [ABSTRACT FROM AUTHOR]

Abstract One of the tenets of mammalian auditory physiology is that the frequency selectivity at the cochlear base decreases as a function of stimulus level. Changes in frequency selectivity have been shown to be accompanied by changes in response phases as a function of stimulus level. The existence of such nonlinear properties has been revealed by the analysis of either direct or indirect recordings of mechanical vibrations of the cochlea. Direct measurements of cochlear mechanical vibrations, however, have been carried out with success primarily in cochlear regions that are tuned to frequencies >7 kHz, but not in regions sensitive to lower frequencies. In this paper we continue to analyze recently published data from measurements of sound-induced vibrations at four locations near the apex of the intact guinea pig cochlea, in a region encompassing approximately 25% of its total length. Analysis of the responses at all locations reveal level-dependent phase properties that are rather different from those usually reported at the base of the cochlea of laboratory animals such as the chinchilla. Cochlear group delays, for example, increase or remain constant with increasing stimulus. Similarly, frequency selectivity at all the regions increases as a function of stimulus level. Highlights • The base and the apex of the cochlea process sounds in a different fashion. • Nonlinear amplification of vibrations at the apex is smaller than at the base. • Nonlinear phase changes at the apex and at the base are different. • Group delays increase or remain constant with stimulus level at the apex. • Frequency selectivity increases with stimulus level at the apex. [ABSTRACT FROM AUTHOR]

Despite recent interest and advances in facial micro-expression research, there is still plenty of room for improvement in terms of micro-expression recognition. Conventional feature extraction approaches for micro-expression video consider either the whole video sequence or a part of it, for representation. However, with the high-speed video capture of micro-expressions (100–200 fps), are all frames necessary to provide a sufficiently meaningful representation? Is the luxury of data a bane to accurate recognition? A novel proposition is presented in this paper, whereby we utilize only two images per video, namely, the apex frame and the onset frame. The apex frame of a video contains the highest intensity of expression changes among all frames, while the onset is the perfect choice of a reference frame with neutral expression. A new feature extractor, Bi-Weighted Oriented Optical Flow (Bi-WOOF) is proposed to encode essential expressiveness of the apex frame. We evaluated the proposed method on five micro-expression databases—CAS(ME) 2 , CASME II, SMIC-HS, SMIC-NIR and SMIC-VIS. Our experiments lend credence to our hypothesis, with our proposed technique achieving a state-of-the-art F1-score recognition performance of 0.61 and 0.62 in the high frame rate CASME II and SMIC-HS databases respectively. [ABSTRACT FROM AUTHOR]

APEX (A gricultural P olicy/ E nvironmental e X tender) is an oft-used agroecosystem model but has limited use in groundwater-driven watersheds due to a simplistic representation of groundwater processes. This paper presents the linkage of APEX and the groundwater flow model MODFLOW into a single modeling code. The mapping of recharge, groundwater head, and groundwater-surface water interactions are handled internally via subroutines. The APEX-MODFLOW model is applied to three watersheds in the United States for testing code accuracy and hydrologic state variables and fluxes: the Animas River Watershed, Colorado and New Mexico (3543 km2); the Price River Watershed, Utah (4886 km2); and the Middle Bosque River Watershed, Texas (470 km2). Whereas the hydrology of the Animas River and Price River watersheds is driven by snowmelt and spring runoff, the hydrology of the Middle Bosque River Watershed is driven by summer thunderstorms. The model can be used for scenario analysis in groundwater-driven watersheds. • New integrated hydrologic model links APEX model to MODFLOW model. • Model passes recharge, water table elevation, and gw-sw flux rates internally. • APEX-MODFLOW applied to three watersheds in Utah, Colorado, and Texas, USA. • Model results show importance of including physically based groundwater flow. [ABSTRACT FROM AUTHOR]

In recent years, numerous facial expression recognition related applications had been commercialized in the market. Many of them achieved promising and reliable performance results in real-world applications. In contrast, the automated micro-expression recognition system relevant research analysis is still greatly lacking. This is because of the nature of the micro-expression that is usually appeared with relatively lesser duration and lower intensity. However, due to its uncontrollable, subtlety, and spontaneity properties, it is capable to reveal one's concealed genuine feelings. Therefore, this paper attempts to improve the performance of current micro-expression recognition systems by introducing an efficient and effective algorithm. Particularly, we employ genetic algorithms (GA) to discover an optimal solution in order to facilitate the computational process in producing better recognition results. Prior to the GA implementation, the benchmark preprocessing method and feature extractors are directly adopted herein. Succinctly, the complete proposed framework composes three main steps: the apex frame acquisition, optical flow approximation, and feature extraction with CNN architecture. Experiments are conducted on the composite dataset that is made up of three publicly available databases, viz, CASME II, SMIC, and SAMM. The recognition performance tends to prevail the state-of-the-art methods by attaining an accuracy of 85.9% and F1-score of 83.7%. • A novel approach for micro-expression recognition was proposed. • A genetic algorithm was implemented on one of the state-of-the-art ME algorithms for feature integration. • Promising performances were obtained in three micro-expression databases. • A comparison of the proposed method with the benchmark and recent methods was reported. [ABSTRACT FROM AUTHOR]