Pedestrian analysis plays a vital role in intelligent video surveillance and is a key component for security-centric computer vision systems. Despite that the convolutional neural networks are remarkable in learning discriminative features from images, the learning of comprehensive features of pedestrians for fine-grained tasks remains an open problem. In this study, we propose a new attentionbased deep neural network, named as HydraPlus-Net (HPnet), that multi-directionally feeds the multi-level attention maps to different feature layers. The attentive deep features learned from the proposed HP-net bring unique advantages: (1) the model is capable of capturing multiple attentions from low-level to semantic-level, and (2) it explores the multi-scale selectiveness of attentive features to enrich the final feature representations for a pedestrian image. We demonstrate the effectiveness and generality of the proposed HP-net for pedestrian analysis on two tasks, i.e. pedestrian attribute recognition and person reidentification. Intensive experimental results have been provided to prove that the HP-net outperforms the state-of-theart methods on various datasets.
Understanding crowd motion dynamics is critical to realworld applications, e.g., surveillance systems and autonomous driving. This is challenging because it requires effectively modeling the socially aware crowd spatial interaction and complex temporal dependencies. We believe attention is the most important factor for trajectory prediction. In this paper, we present STAR, a Spatio-Temporal grAph tRansformer framework, which tackles trajectory prediction by only attention mechanisms. STAR models intra-graph crowd interaction by TGConv, a novel Transformer-based graph convolution mechanism. The inter-graph temporal dependencies are modeled by separate temporal Transformers. STAR captures complex spatio-temporal interactions by interleaving between spatial and temporal Transformers. To calibrate the temporal prediction for the long-lasting effect of disappeared pedestrians, we introduce a read-writable external memory module, consistently being updated by the temporal Transformer. We show STAR outperforms the state-of-the-art models on 4 out of 5 real-world pedestrian trajectory prediction datasets, and achieves comparable performance on the rest.
Real-scanned point clouds are often incomplete due to viewpoint, occlusion, and noise, which hampers 3D geometric modeling and perception. Existing point cloud completion methods tend to generate global shape skeletons and hence lack fine local details. Furthermore, they mostly learn a deterministic partial-to-complete mapping, but overlook structural relations in man-made objects. To tackle these challenges, this paper proposes a variational framework, Variational Relational point Completion network (VRCNet) with two appealing properties: 1) Probabilistic Modeling. In particular, we propose a dual-path architecture to enable principled probabilistic modeling across partial and complete clouds. One path consumes complete point clouds for reconstruction by learning a point VAE. The other path generates complete shapes for partial point clouds, whose embedded distribution is guided by distribution obtained from the reconstruction path during training. 2) Relational Enhancement. Specifically, we carefully design point self-attention kernel and point selective kernel module to exploit relational point features, which refines local shape details conditioned on the coarse completion. In addition, we contribute multi-view partial point cloud datasets (MVP and MVP-40 dataset) containing over 200,000 high-quality scans, which render partial 3D shapes from 26 uniformly distributed camera poses for each 3D CAD model. Extensive experiments demonstrate that VRCNet outperforms state-of-the-art methods on all standard point cloud completion benchmarks. Notably, VRCNet shows great generalizability and robustness on real-world point cloud scans. Moreover, we can achieve robust 3D classification for partial point clouds with the help of VRCNet, which can highly increase classification accuracy. Our project is available at https://paul007pl.github.io/projects/VRCNet.
Lepidium meyenii (Maca), originated from Peru, has been cultivated widely in China as a popular health care food. However, the chemical and effective studies of Maca were less in-depth, which restricted its application seriously. To ensure the quality of Maca, a feasible and accurate strategy was established. One hundred and sixty compounds including 30 reference standards were identified in 6 fractions of methanol extract of Maca by UHPLC-ESI-Orbitrap MS. Among them, 15 representative active compounds were simultaneously determined in 17 samples by UHPLC-ESI-QqQ MS. The results suggested that Maca from Yunnan province was the potential substitute for the one from Peru. Meanwhile, the neuroprotective effects of Maca were investigated. Three fractions and two pure compounds showed strong activities in the 1-methyl-4-phenyl-1, 2, 3, 6-tetrahydropyridine (MPTP)-induced zebrafish model. Among them, 80% methanol elution fraction (Fr5) showed significant neuroprotective activity, followed by 100% part (Fr6). The inhibition of acetylcholinesterase (AChE) and butyrylcholinesterase (BuChE) was a possible mechanism of its neuroprotective effect.
Formononetin and its glycoside ononin are bioactive isoflavones widely present in legumes. The present study investigated the pharmacokinetics, bioavailability, and in vitro absorption of formononetin and ononin. After an oral administration to rats, formononetin showed a higher systemic exposure over ononin. The oral bioavailability of formononetin and ononin were 21.8% and 7.3%, respectively. Ononin was more bioavailable than perceived, and its bioavailability reached 21.7% when its metabolite formononetin was taken into account. Both formononetin and ononin exhibited better absorption in large intestine segments than that in small intestine segments. Formononetin displayed a better permeability in all intestinal segments over ononin. Transport of formononetin across Caco-2 cell monolayer was mainly through passive diffusion, while ononin was actively pumped out by MRP2 but not P-gp. The results provide evidence for better understanding of the pharmacological actions of formononetin and ononin, which advocates more in vivo evaluations or human trials.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.