Recent work has shown that depth estimation from a stereo pair of images can be formulated as a supervised learning task to be resolved with convolutional neural networks (CNNs). However, current architectures rely on patch-based Siamese networks, lacking the means to exploit context information for finding correspondence in ill-posed regions. To tackle this problem, we propose PSMNet, a pyramid stereo matching network consisting of two main modules: spatial pyramid pooling and 3D CNN. The spatial pyramid pooling module takes advantage of the capacity of global context information by aggregating context in different scales and locations to form a cost volume. The 3D CNN learns to regularize cost volume using stacked multiple hourglass networks in conjunction with intermediate supervision. The proposed approach was evaluated on several benchmark datasets. Our method ranked first in the KITTI 2012 and 2015 leaderboards before March 18, 2018. The codes of PSMNet are available at: https://github.com/JiaRenChang/PSMNet.

Primary dysmenorrhea (PDM) is the most prevalent gynecological disorder for women in the reproductive age. PDM patients suffer from lower abdominal pain that starts with the onset of the menstrual flow. Prolonged nociceptive input to the central nervous system can induce functional and structural alterations throughout the nervous system. In PDM, a chronic viscero-nociceptive drive of cyclic nature, indications of central sensitization and altered brain metabolism suggest a substantial central reorganization. Previously, we hypothesized that disinhibition of orbitofrontal networks could be responsible for increased pain and negative affect in PDM. Here, we further tested this hypothesis. We used an optimized voxel-based morphometry (VBM) approach to compare total and regional gray matter (GM) increases and decreases in 32 PDM patients with 32 healthy age and menstrual cycle matched (peri-ovulatory phase) controls. Abnormal decreases were found in regions involved in pain transmission, higher level sensory processing, and affected regulation while increases were found in regions involved in pain modulation and in regulation of endocrine function. Moreover, GM changes in regions involved in top-down pain modulation and in generation of negative affect were related to the severity of the experienced PDM pain. Our results demonstrate that abnormal GM volume changes are present in PDM patients even in the absence of pain. These changes may underpin a combination of impaired pain inhibition, increased pain facilitation and increased affect. Our findings highlight that longer lasting central changes may occur not only in sustained chronic pain conditions but also in cyclic occurring pain conditions.

This paper proposes the Parallel Residual Bi-Fusion Feature Pyramid Network (PRB-FPN) for fast and accurate single-shot object detection. Feature Pyramid (FP) is widely used in recent visual detection, however the top-down pathway of FP cannot preserve accurate localization due to pooling shifting. The advantage of FP is weakened as deeper backbones with more layers are used. In addition, it cannot keep up accurate detection of both small and large objects at the same time. To address these issues, we propose a new parallel FP structure with bi-directional (top-down and bottom-up) fusion and associated improvements to retain high-quality features for accurate localization. We provide the following design improvements: 1) parallel bifusion FP structure with a bottom-up fusion module (BFM) to detect both small and large objects at once with high accuracy; 2) concatenation and re-organization (CORE) module provides a bottom-up pathway for feature fusion, which leads to the bi-directional fusion FP that can recover lost information from lower-layer feature maps; 3) CORE feature is further purified to retain richer contextual information. Such CORE purification in both top-down and bottom-up pathways can be finished in only a few iterations; 4) adding of a residual design to CORE leads to a new Re-CORE module that enables easy training and integration with a wide range of deeper or lighter backbones. The proposed network achieves state-of-the-art performance on the UAVDT17 and MS COCO datasets.

The emergence of the digital world has greatly increased the number of accounts and passwords that users must remember. It has also increased the need for secure access to personal information in the cloud. Biometrics is one approach to person recognition, which can be used in identification as well as authentication. Among the various modalities that have been developed, EEG-based biometrics features unparalleled universality, distinctiveness, and collectability, while minimizing the risk of circumvention. However, commercializing EEG-based person recognition poses a number of challenges. This paper reviews the various systems proposed over the past few years with a focus on the shortcomings that have prevented wide-scale implementation, including issues pertaining to temporal stability, psychological and physiological changes, protocol design, equipment, and performance evaluation. We also examine several directions for the further development of usable EEG-based recognition systems as well as the niche markets to which they could be applied. It is expected that rapid advancements in EEG instrumentation, on-device processing, and machine learning techniques will lead to the emergence of commercialized person recognition systems in the near future.