Dense captioning aims to simultaneously localize and describe regions-of-interest(RoIs)in images in natural language.Specifically,we identify three key problems:1)dense and highly overlapping RoIs,making accurate loca...Dense captioning aims to simultaneously localize and describe regions-of-interest(RoIs)in images in natural language.Specifically,we identify three key problems:1)dense and highly overlapping RoIs,making accurate localization of each target region challenging;2)some visually ambiguous target regions which are hard to recognize each of them just by appearance;3)an extremely deep image representation which is of central importance for visual recognition.To tackle these three challenges,we propose a novel end-to-end dense captioning framework consisting of a joint localization module,a contextual reasoning module and a deep convolutional neural network(CNN).We also evaluate five deep CNN structures to explore the benefits of each.Extensive experiments on visual genome(VG)dataset demonstrate the effectiveness of our approach,which compares favorably with the state-of-the-art methods.展开更多
It has been shown in recent economic and statistical studies that combining forecasts may produce more accurate forecasts than individual ones. However, the literature on combining forecasts has almost exclusively foc...It has been shown in recent economic and statistical studies that combining forecasts may produce more accurate forecasts than individual ones. However, the literature on combining forecasts has almost exclusively focused on linear combining forecasts. In this paper, a new nonlinear combination forecasting method based on fuzzy inference system is present to overcome the difficulties and drawbacks in linear combination modeling of non-stationary time series. Furthermore, the optimization algorithm based on a hierarchical structure of learning automata is used to identify the parameters of the fuzzy system. Experiment results related to numerical examples demonstrate that the new technique has excellent identification performances and forecasting accuracy superior to other existing linear combining forecasts.展开更多
The formation and growth of cracks in concrete dams are mainly induced by hydrostatic and temperature loads.As cracks es-pecially unstable cracks are of great danger to the safety of dams,it is critical to avoid extre...The formation and growth of cracks in concrete dams are mainly induced by hydrostatic and temperature loads.As cracks es-pecially unstable cracks are of great danger to the safety of dams,it is critical to avoid extremely adverse load combinations during the dam operations to achieve the stability of cracks.Conventionally,the adverse load combinations have to be deter-mined empirically by experts based on specific dam site conditions.Therefore,it is attractive to apply quantitative instead of empirical methods to identify the adverse loading conditions.In this study,we employ an adaptive neuro-fuzzy inference sys-tem(ANFIS) to Chencun concrete dam.The ANFIS is able to help us build a relationship between the model inputs(reservoir water level and air temperature) and the model output(crack opening displacement).Based on this relationship,the rules of the adverse load combinations to the crack are generated directly from the monitoring data.The accuracy of the trained ANFIS is proved by comparing the modeling results and the monitoring data.Our work demonstrates that the ANFIS is a useful ap-proach for accurately recognizing the rules of the adverse load combinations that can be used in the knowledge base of dam safety expert system.展开更多
基金Project(2020A1515010718)supported by the Basic and Applied Basic Research Foundation of Guangdong Province,China。
文摘Dense captioning aims to simultaneously localize and describe regions-of-interest(RoIs)in images in natural language.Specifically,we identify three key problems:1)dense and highly overlapping RoIs,making accurate localization of each target region challenging;2)some visually ambiguous target regions which are hard to recognize each of them just by appearance;3)an extremely deep image representation which is of central importance for visual recognition.To tackle these three challenges,we propose a novel end-to-end dense captioning framework consisting of a joint localization module,a contextual reasoning module and a deep convolutional neural network(CNN).We also evaluate five deep CNN structures to explore the benefits of each.Extensive experiments on visual genome(VG)dataset demonstrate the effectiveness of our approach,which compares favorably with the state-of-the-art methods.
基金Funded by the Excellent Young Teachers of MOE (350) and Chongqing Education Committee Foundation
文摘It has been shown in recent economic and statistical studies that combining forecasts may produce more accurate forecasts than individual ones. However, the literature on combining forecasts has almost exclusively focused on linear combining forecasts. In this paper, a new nonlinear combination forecasting method based on fuzzy inference system is present to overcome the difficulties and drawbacks in linear combination modeling of non-stationary time series. Furthermore, the optimization algorithm based on a hierarchical structure of learning automata is used to identify the parameters of the fuzzy system. Experiment results related to numerical examples demonstrate that the new technique has excellent identification performances and forecasting accuracy superior to other existing linear combining forecasts.
基金supported by the National Natural Science Foundation of China (Grant Nos.50909041 and 41072217)
文摘The formation and growth of cracks in concrete dams are mainly induced by hydrostatic and temperature loads.As cracks es-pecially unstable cracks are of great danger to the safety of dams,it is critical to avoid extremely adverse load combinations during the dam operations to achieve the stability of cracks.Conventionally,the adverse load combinations have to be deter-mined empirically by experts based on specific dam site conditions.Therefore,it is attractive to apply quantitative instead of empirical methods to identify the adverse loading conditions.In this study,we employ an adaptive neuro-fuzzy inference sys-tem(ANFIS) to Chencun concrete dam.The ANFIS is able to help us build a relationship between the model inputs(reservoir water level and air temperature) and the model output(crack opening displacement).Based on this relationship,the rules of the adverse load combinations to the crack are generated directly from the monitoring data.The accuracy of the trained ANFIS is proved by comparing the modeling results and the monitoring data.Our work demonstrates that the ANFIS is a useful ap-proach for accurately recognizing the rules of the adverse load combinations that can be used in the knowledge base of dam safety expert system.
