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
Objective： The aim of this study was to evaluate L-J （Lo＂wenstein-Jensen） medium culture, MGIT 960 culture anddifferent specimen types in diagnosis of BJTB （bone and joint tuberculosis）. Methods：： Specimens of...Objective： The aim of this study was to evaluate L-J （Lo＂wenstein-Jensen） medium culture, MGIT 960 culture anddifferent specimen types in diagnosis of BJTB （bone and joint tuberculosis）. Methods：： Specimens of pus, caseous necrosis,tuberculous granuloma and sequestrum were collected from 52 BJTB patients. All specimens were cultured using both MGIT 960system and L-J medium; and all pus were amplified using real-time PCR to detect the presence of M. tuberculosis DNA. KeyFindings： A total of 191 specimens were collected. Granuloma had better chance to produce positive outcomes by L-J mediumculture, while for sequestrum MGIT 960 culture had higher yield, but there was no significant difference in the recovery rates amongdifferent types of specimen either by L-J culture （Z2 = 0.638, P = 0.888） or by MGIT960 culture （Z2 = 1.399, P = 0.706）. MGIT960culture had significantly higher recovery rate than L-J culture, With a combined culture and PCR-based test, the recovery rate of pusspecimen was significantly higher than that of either method alone （P 〈 0.05）. Conclusion： MGIT 960 culture is superior to L-Jculture in BJTB diagnosis; pus, sequestrum, granuloma and caseous necrosis are usable specimen for mycobacterial culture;combination of culture and molecular techniques can provide a better diagnostic significance.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.
文摘Objective： The aim of this study was to evaluate L-J （Lo＂wenstein-Jensen） medium culture, MGIT 960 culture anddifferent specimen types in diagnosis of BJTB （bone and joint tuberculosis）. Methods：： Specimens of pus, caseous necrosis,tuberculous granuloma and sequestrum were collected from 52 BJTB patients. All specimens were cultured using both MGIT 960system and L-J medium; and all pus were amplified using real-time PCR to detect the presence of M. tuberculosis DNA. KeyFindings： A total of 191 specimens were collected. Granuloma had better chance to produce positive outcomes by L-J mediumculture, while for sequestrum MGIT 960 culture had higher yield, but there was no significant difference in the recovery rates amongdifferent types of specimen either by L-J culture （Z2 = 0.638, P = 0.888） or by MGIT960 culture （Z2 = 1.399, P = 0.706）. MGIT960culture had significantly higher recovery rate than L-J culture, With a combined culture and PCR-based test, the recovery rate of pusspecimen was significantly higher than that of either method alone （P 〈 0.05）. Conclusion： MGIT 960 culture is superior to L-Jculture in BJTB diagnosis; pus, sequestrum, granuloma and caseous necrosis are usable specimen for mycobacterial culture;combination of culture and molecular techniques can provide a better diagnostic significance.
