An action recognition network that combines multi-level spatiotemporal feature fusion with an attention mechanism is proposed as a solution to the issues of single spatiotemporal feature scale extraction,information r...An action recognition network that combines multi-level spatiotemporal feature fusion with an attention mechanism is proposed as a solution to the issues of single spatiotemporal feature scale extraction,information redundancy,and insufficient extraction of frequency domain information in channels in 3D convolutional neural networks.Firstly,based on 3D CNN,this paper designs a new multilevel spatiotemporal feature fusion(MSF)structure,which is embedded in the network model,mainly through multilevel spatiotemporal feature separation,splicing and fusion,to achieve the fusion of spatial perceptual fields and short-medium-long time series information at different scales with reduced network parameters;In the second step,a multi-frequency channel and spatiotemporal attention module(FSAM)is introduced to assign different frequency features and spatiotemporal features in the channels are assigned corresponding weights to reduce the information redundancy of the feature maps.Finally,we embed the proposed method into the R3D model,which replaced the 2D convolutional filters in the 2D Resnet with 3D convolutional filters and conduct extensive experimental validation on the small and medium-sized dataset UCF101 and the largesized dataset Kinetics-400.The findings revealed that our model increased the recognition accuracy on both datasets.Results on the UCF101 dataset,in particular,demonstrate that our model outperforms R3D in terms of a maximum recognition accuracy improvement of 7.2%while using 34.2%fewer parameters.The MSF and FSAM are migrated to another traditional 3D action recognition model named C3D for application testing.The test results based on UCF101 show that the recognition accuracy is improved by 8.9%,proving the strong generalization ability and universality of the method in this paper.展开更多
The application of nanotechnology for antimicrobial delivery has capacity to improve anti-bacterial efficacy.Currently,the usage of various inorganic and organic carriers,such as metal ions,nano-silicon and surfactant...The application of nanotechnology for antimicrobial delivery has capacity to improve anti-bacterial efficacy.Currently,the usage of various inorganic and organic carriers,such as metal ions,nano-silicon and surfactants,might increase the potential toxicity of nanoparticles and make their clinical transformation more difficult.Herein,a nano-delivery system was constructed by direct self-assembly of antibacterial phytochemicals(berberine and rhein)originated from traditional Chinese medicine Coptis chinensis Franch.and Rheum palmatum L.,respectively.Combining X-ray single crystal diffraction,nuclear magnetic resonance and other spectra characterizations,the stacked structure of nanoparticles was profoundly demonstrated.Briefly,rhein acted as the layered backbone and berberine embedded in it.In vitro bacteriostasis experiment showed the minimum bactericidal concentration of nanoparticles was 0.1μmol/mL,which was lower than that of berberine and rhein.The results of confocal laser scanning microscope,biofilm quantitive assay and scanning electron microscopy indicated that nanoparticles had strong inhibitory effects on Staphylococcus aureus biofilm.More importantly,transmission electron microscopy and mass spectra indicated the further bacteriostatic mechanism of nanoparticles.Meanwhile,the nanoparticles had well biocompatibility and safety.Current study will open up new prospect that the design of self-assemblies between active phytochemicals can be originated from traditional Chinese medicine combination.展开更多
基金supported by the General Program of the National Natural Science Foundation of China (62272234)the Enterprise Cooperation Project (2022h160)the Priority Academic Program Development of Jiangsu Higher Education Institutions Project.
文摘An action recognition network that combines multi-level spatiotemporal feature fusion with an attention mechanism is proposed as a solution to the issues of single spatiotemporal feature scale extraction,information redundancy,and insufficient extraction of frequency domain information in channels in 3D convolutional neural networks.Firstly,based on 3D CNN,this paper designs a new multilevel spatiotemporal feature fusion(MSF)structure,which is embedded in the network model,mainly through multilevel spatiotemporal feature separation,splicing and fusion,to achieve the fusion of spatial perceptual fields and short-medium-long time series information at different scales with reduced network parameters;In the second step,a multi-frequency channel and spatiotemporal attention module(FSAM)is introduced to assign different frequency features and spatiotemporal features in the channels are assigned corresponding weights to reduce the information redundancy of the feature maps.Finally,we embed the proposed method into the R3D model,which replaced the 2D convolutional filters in the 2D Resnet with 3D convolutional filters and conduct extensive experimental validation on the small and medium-sized dataset UCF101 and the largesized dataset Kinetics-400.The findings revealed that our model increased the recognition accuracy on both datasets.Results on the UCF101 dataset,in particular,demonstrate that our model outperforms R3D in terms of a maximum recognition accuracy improvement of 7.2%while using 34.2%fewer parameters.The MSF and FSAM are migrated to another traditional 3D action recognition model named C3D for application testing.The test results based on UCF101 show that the recognition accuracy is improved by 8.9%,proving the strong generalization ability and universality of the method in this paper.
基金funded by the Beijing Municipal Natural Science Foundation(No.7202116,China)National Natural Science Foundation of China(No.81603256)+2 种基金project of China Association of Chinese Medicine(CACM-2018-QNRC2-B08)the Fundamental Research Funds for the Central Universities(BUCM-2019-JCRC002,BUCM-2018-2020 and 2019-JYBTD005,China)Beijing Key Laboratory for Basic and Development Research on Chinese Medicine(Beijing,China)
文摘The application of nanotechnology for antimicrobial delivery has capacity to improve anti-bacterial efficacy.Currently,the usage of various inorganic and organic carriers,such as metal ions,nano-silicon and surfactants,might increase the potential toxicity of nanoparticles and make their clinical transformation more difficult.Herein,a nano-delivery system was constructed by direct self-assembly of antibacterial phytochemicals(berberine and rhein)originated from traditional Chinese medicine Coptis chinensis Franch.and Rheum palmatum L.,respectively.Combining X-ray single crystal diffraction,nuclear magnetic resonance and other spectra characterizations,the stacked structure of nanoparticles was profoundly demonstrated.Briefly,rhein acted as the layered backbone and berberine embedded in it.In vitro bacteriostasis experiment showed the minimum bactericidal concentration of nanoparticles was 0.1μmol/mL,which was lower than that of berberine and rhein.The results of confocal laser scanning microscope,biofilm quantitive assay and scanning electron microscopy indicated that nanoparticles had strong inhibitory effects on Staphylococcus aureus biofilm.More importantly,transmission electron microscopy and mass spectra indicated the further bacteriostatic mechanism of nanoparticles.Meanwhile,the nanoparticles had well biocompatibility and safety.Current study will open up new prospect that the design of self-assemblies between active phytochemicals can be originated from traditional Chinese medicine combination.