Ethanol extract of Merr. ameliorates cognitive impairment through inhibiting NLRP3 inflammasome in scopolamine-treated mice.

Merr. (Evodia lepta) is a well-known traditional Chinese medicine, which has been widely used in herbal tea. We previously reported that the coumarin compounds from the root of Evodia lepta exhibited neuroprotective effects.

Phloroglucinol derivatives, coumarins and an alkaloid from the roots of Evodia lepta Merr.

Two previously undescribed phloroglucinol derivatives [(±) evolephloroglucinols A and B], five unusual coumarins [evolecoumarins A and B and (±) evolecoumarins C-E], and one novel enantiomeric quinoline-type alkaloid [(±) evolealkaloid A], along with 20 known compounds, were isolated from the EtOH extract of the roots of Evodia lepta Merr. Their structures were elucidated by extensive spectroscopic analyses. The absolute configurations of the undescribed compounds were determined by X-ray diffraction or computational calculations.

Huang-Lian-Jie-Du decoction alleviates depressive-like behaviors in dextran sulfate sodium-induced colitis mice via Trem2/Dap12 pathway.

Ethnopharmacological Relevance: Huang-Lian-Jie-Du decoction (HLJD), a traditional Chinese medicine prescription, has been implicated as effective in treating colitis, depression and inflammation-related diseases. Whether HLJD decoction could ameliorate colitis-induced depression was still unknown and the underlying mechanism was needed to be clarified.

Aim Of The Study: Our study aimed to explore the effect and the underlying mechanism of HLJD treatment on colitis-induced depression and the involvement of the inflammatory factors and microglial-activated related genes.

Class-Aware Sounding Objects Localization via Audiovisual Correspondence.

Audiovisual scenes are pervasive in our daily life. It is commonplace for humans to discriminatively localize different sounding objects but quite challenging for machines to achieve class-aware sounding objects localization without category annotations, i.e.

Spatio-Temporal Point Process for Multiple Object Tracking.

Multiple object tracking (MOT) focuses on modeling the relationship of detected objects among consecutive frames and merge them into different trajectories. MOT remains a challenging task as noisy and confusing detection results often hinder the final performance. Furthermore, most existing research are focusing on improving detection algorithms and association strategies.

AP-Loss for Accurate One-Stage Object Detection.

One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This paper alleviates this issue by proposing a novel framework to replace the classification task in one-stage detectors with a ranking task, and adopting the average-precision loss (AP-loss) for the ranking problem. Due to its non-differentiability and non-convexity, the AP-loss cannot be optimized directly.

Group Reidentification with Multigrained Matching and Integration.

The task of reidentifying groups of people under different camera views is an important yet less-studied problem. Group reidentification (Re-ID) is a very challenging task since it is not only adversely affected by common issues in traditional single-object Re-ID problems, such as viewpoint and human pose variations, but also suffers from changes in group layout and group membership. In this paper, we propose a novel concept of group granularity by characterizing a group image by multigrained objects: individual people and subgroups of two and three people within a group.

Deep Color Guided Coarse-to-Fine Convolutional Network Cascade for Depth Image Super-Resolution.

Depth image super-resolution is a significant yet challenging task. In this paper, we introduce a novel deep color guided coarse-to-fine convolutional neural network (CNN) framework to address this problem. First, we present a datadriven filter method to approximate the ideal filter for depth image super-resolution instead of hand-designed filters.

ThiNet: Pruning CNN Filters for a Thinner Net.

This paper aims at accelerating and compressing deep neural networks to deploy CNN models into small devices like mobile phones or embedded gadgets. We focus on filter level pruning, i.e.

Learning Correspondence Structures for Person Re-Identification.

This paper addresses the problem of handling spatial misalignments due to camera-view changes or human-pose variations in person re-identification. We first introduce a boosting-based approach to learn a correspondence structure, which indicates the patchwise matching probabilities between images from a target camera pair. The learned correspondence structure can not only capture the spatial correspondence pattern between cameras but also handle the viewpoint or human-pose variation in individual images.

A Tube-and-Droplet-Based Approach for Representing and Analyzing Motion Trajectories.

Trajectory analysis is essential in many applications. In this paper, we address the problem of representing motion trajectories in a highly informative way, and consequently utilize it for analyzing trajectories. Our approach first leverages the complete information from given trajectories to construct a thermal transfer field which provides a context-rich way to describe the global motion pattern in a scene.

Multitask Learning of Compact Semantic Codebooks for Context-Aware Scene Modeling.

In the past few decades, we have witnessed the success of bag-of-features (BoF) models in scene classification, object detection, and image segmentation. Whereas it is also well acknowledged that the limitation of BoF-based methods lies in the low-level feature encoding and coarse feature pooling. This paper proposes a novel scene classification method, which leverages several semantic codebooks learned in a multitask fashion for robust feature encoding, and designs a context-aware image representation for efficient feature pooling.

A Diffusion and Clustering-Based Approach for Finding Coherent Motions and Understanding Crowd Scenes.

This paper addresses the problem of detecting coherent motions in crowd scenes and presents its two applications in crowd scene understanding: semantic region detection and recurrent activity mining. It processes input motion fields (e.g.

Good Practices for Learning to Recognize Actions Using FV and VLAD.

High dimensional representations such as Fisher vectors (FV) and vectors of locally aggregated descriptors (VLAD) have shown state-of-the-art accuracy for action recognition in videos. The high dimensionality, on the other hand, also causes computational difficulties when scaling up to large-scale video data. This paper makes three lines of contributions to learning to recognize actions using high dimensional representations.

Tree-Based Visualization and Optimization for Image Collection.

The visualization of an image collection is the process of displaying a collection of images on a screen under some specific layout requirements. This paper focuses on an important problem that is not well addressed by the previous methods: visualizing image collections into arbitrary layout shapes while arranging images according to user-defined semantic or visual correlations (e.g.

Flexible Image Similarity Computation Using Hyper-Spatial Matching.

Spatial pyramid matching (SPM) has been widely used to compute the similarity of two images in computer vision and image processing. While comparing images, SPM implicitly assumes that: in two images from the same category, similar objects will appear in similar locations. However, this is not always the case.

Multiscale semilocal interpolation with antialiasing.

Aliasing is a common artifact in low-resolution (LR) images generated by a downsampling process. Recovering the original high-resolution image from its LR counterpart while at the same time removing the aliasing artifacts is a challenging image interpolation problem. Since a natural image normally contains redundant similar patches, the values of missing pixels can be available at texture-relevant LR pixels.