Industrial and academic interest in how to effectively manage technology resources is increasing as it becomes more and more important.Effective managing of technology resources depends on technology management system...Industrial and academic interest in how to effectively manage technology resources is increasing as it becomes more and more important.Effective managing of technology resources depends on technology management system,and thus understanding how such system evolves becomes an ongoing research topic.Based on the self-organization theory,this paper constructs an evolution model of technology management system.The simulation results show that the evolution of each of the technology management subsystem is affected by the knowledge growth rate of its own,and it is also affected by the coupling and synergy relationship with other subsystems.Moreover,the coupling and synergy relationship can make the speed of evolution higher than the knowledge growth rate of the subsystem itself.展开更多
The attention mechanism can extract salient features in images,which has been proved to be effective in improving the performance of person re-identification(Re-ID).However,most of the existing attention modules have ...The attention mechanism can extract salient features in images,which has been proved to be effective in improving the performance of person re-identification(Re-ID).However,most of the existing attention modules have the following two shortcomings:On the one hand,they mostly use global average pooling to generate context descriptors,without highlighting the guiding role of salient information on descriptor generation,resulting in insufficient ability of the final generated attention mask representation;On the other hand,the design of most attention modules is complicated,which greatly increases the computational cost of the model.To solve these problems,this paper proposes an attention module called self-supervised recalibration(SR)block,which introduces both global and local information through adaptive weighted fusion to generate a more refined attention mask.In particular,a special"Squeeze-Excitation"(SE)unit is designed in the SR block to further process the generated intermediate masks,both for nonlinearizations of the features and for constraint of the resulting computation by controlling the number of channels.Furthermore,we combine the most commonly used Res Net-50 to construct the instantiation model of the SR block,and verify its effectiveness on multiple Re-ID datasets,especially the mean Average Precision(m AP)on the Occluded-Duke dataset exceeds the state-of-the-art(SOTA)algorithm by 4.49%.展开更多
基金supported by the National Natural Science Foundation of China(72072047)the Humanities and Social Sciences Project of Ministry of Education(20YJC630090)+1 种基金Heilongjiang Philosophy and Social Science Research Project(19GLB087)the Science and Technology Program of Hebei Province(20557688D)。
文摘Industrial and academic interest in how to effectively manage technology resources is increasing as it becomes more and more important.Effective managing of technology resources depends on technology management system,and thus understanding how such system evolves becomes an ongoing research topic.Based on the self-organization theory,this paper constructs an evolution model of technology management system.The simulation results show that the evolution of each of the technology management subsystem is affected by the knowledge growth rate of its own,and it is also affected by the coupling and synergy relationship with other subsystems.Moreover,the coupling and synergy relationship can make the speed of evolution higher than the knowledge growth rate of the subsystem itself.
基金supported in part by the Natural Science Foundation of Xinjiang Uygur Autonomous Region(Grant No.2022D01B186 and No.2022D01B05)。
文摘The attention mechanism can extract salient features in images,which has been proved to be effective in improving the performance of person re-identification(Re-ID).However,most of the existing attention modules have the following two shortcomings:On the one hand,they mostly use global average pooling to generate context descriptors,without highlighting the guiding role of salient information on descriptor generation,resulting in insufficient ability of the final generated attention mask representation;On the other hand,the design of most attention modules is complicated,which greatly increases the computational cost of the model.To solve these problems,this paper proposes an attention module called self-supervised recalibration(SR)block,which introduces both global and local information through adaptive weighted fusion to generate a more refined attention mask.In particular,a special"Squeeze-Excitation"(SE)unit is designed in the SR block to further process the generated intermediate masks,both for nonlinearizations of the features and for constraint of the resulting computation by controlling the number of channels.Furthermore,we combine the most commonly used Res Net-50 to construct the instantiation model of the SR block,and verify its effectiveness on multiple Re-ID datasets,especially the mean Average Precision(m AP)on the Occluded-Duke dataset exceeds the state-of-the-art(SOTA)algorithm by 4.49%.
