Publications by authors named "Zhengkui Weng"

In the field of human action recognition, it is a long-standing challenge to characterize the video-level spatio-temporal features effectively. This is attributable in part to the inability of CNN to model long-range temporal information, especially for actions that consist of multiple staged behaviors. In this paper, a novel attention-based spatio-temporal VLAD network (AST-VLAD) with self-attention model is developed to aggregate the informative deep features across the video according to the adaptive deep feature selected.

View Article and Find Full Text PDF

Misfolded aggregation of the hyperphosphorylated microtubule binding protein Tau in the brain is a pathological hallmark of Alzheimer's disease (AD). Tau aggregation downregulates brain-derived neurotrophic factor (BDNF)/tropomycin receptor kinase B (TRKB) signaling and leads to neurotoxicity. Therefore, enhancement of BDNF/TRKB signaling could be a strategy to alleviate Tau neurotoxicity.

View Article and Find Full Text PDF

Hyperphosphorylation and aggregation of the microtubule binding protein tau is a neuropathological hallmark of Alzheimer's disease/tauopathies. Tau neurotoxicity provokes alterations in brain-derived neurotrophic factor (BDNF)/tropomycin receptor kinase B (TRKB)/cAMP-response-element binding protein (CREB) signaling to contribute to neurodegeneration. Compounds activating TRKB may therefore provide beneficial effects in tauopathies.

View Article and Find Full Text PDF

Glycogen synthase kinase-3β (GSK-3β) is an important serine/threonine kinase that implicates in multiple cellular processes and links with the neurodegenerative diseases including Alzheimer's disease (AD). In this study, structure-based virtual screening was performed to search database for compounds targeting GSK-3β from Enamine's screening collection. Of the top-ranked compounds, 7 primary hits underwent a luminescent kinase assay and a cell assay using human neuroblastoma SH-SY5Y cells expressing Tau repeat domain (Tau) with pro-aggregant mutation ΔK280.

View Article and Find Full Text PDF

Convolutional neural network (CNN) has been leaping forward in recent years. However, the high dimensionality, rich human dynamic characteristics, and various kinds of background interference increase difficulty for traditional CNNs in capturing complicated motion data in videos. A novel framework named the attention-based temporal encoding network (ATEN) with background-independent motion mask (BIMM) is proposed to achieve video action recognition here.

View Article and Find Full Text PDF

As a complex network of many interlinked brain regions, there are some central hub regions which play key roles in the structural human brain network based on T1 and diffusion tensor imaging (DTI) technology. Since most studies about hubs location method in the whole human brain network are mainly concerned with the local properties of each single node but not the global properties of all the directly connected nodes, a novel hubs location method based on global importance contribution evaluation index is proposed in this study. The number of streamlines (NoS) is fused with normalized fractional anisotropy (FA) for more comprehensive brain bioinformation.

View Article and Find Full Text PDF