At present,knowledge embedding methods are widely used in the field of knowledge graph(KG)reasoning,and have been successfully applied to those with large entities and relationships.However,in research and production ...At present,knowledge embedding methods are widely used in the field of knowledge graph(KG)reasoning,and have been successfully applied to those with large entities and relationships.However,in research and production environments,there are a large number of KGs with a small number of entities and relations,which are called sparse KGs.Limited by the performance of knowledge extraction methods or some other reasons(some common-sense information does not appear in the natural corpus),the relation between entities is often incomplete.To solve this problem,a method of the graph neural network and information enhancement is proposed.The improved method increases the mean reciprocal rank(MRR)and Hit@3 by 1.6%and 1.7%,respectively,when the sparsity of the FB15K-237 dataset is 10%.When the sparsity is 50%,the evaluation indexes MRR and Hit@10 are increased by 0.8%and 1.8%,respectively.展开更多
The femtosecond pulse shaping technique has been shown to be an effective method to control the multi-photon absorption by the light–matter interaction. Previous studies mainly focused on the quantum coherent control...The femtosecond pulse shaping technique has been shown to be an effective method to control the multi-photon absorption by the light–matter interaction. Previous studies mainly focused on the quantum coherent control of the multi-photon absorption by the phase, amplitude and polarization modulation, but the coherent features of the multi-photon absorption depending on the energy level structure, the laser spectrum bandwidth and laser central frequency still lack in-depth systematic research. In this work, we further explore the coherent features of the resonance-mediated two-photon absorption in a rubidium atom by varying the energy level structure, spectrum bandwidth and central frequency of the femtosecond laser field. The theoretical results show that the change of the intermediate state detuning can effectively influence the enhancement of the near-resonant part, which further affects the transform-limited （TL）-normalized final state population maximum. Moreover, as the laser spectrum bandwidth increases, the TL-normalized final state population maximum can be effectively enhanced due to the increase of the enhancement in the near-resonant part, but the TL-normalized final state population maximum is constant by varying the laser central frequency. These studies can provide a clear physical picture for understanding the coherent features of the resonance-mediated two-photon absorption, and can also provide a theoretical guidance for the future applications.展开更多
Single-photon sensors are novel devices with extremely high single-photon sensitivity and temporal resolution.However,these advantages also make them highly susceptible to noise.Moreover,single-photon cameras face sev...Single-photon sensors are novel devices with extremely high single-photon sensitivity and temporal resolution.However,these advantages also make them highly susceptible to noise.Moreover,single-photon cameras face severe quantization as low as 1 bit/frame.These factors make it a daunting task to recover high-quality scene information from noisy single-photon data.Most current image reconstruction methods for single-photon data are mathematical approaches,which limits information utilization and algorithm performance.In this work,we propose a hybrid information enhancement model which can significantly enhance the efficiency of information utilization by leveraging attention mechanisms from both spatial and channel branches.Furthermore,we introduce a structural feature enhance module for the FFN of the transformer,which explicitly improves the model's ability to extract and enhance high-frequency structural information through two symmetric convolution branches.Additionally,we propose a single-photon data simulation pipeline based on RAW images to address the challenge of the lack of single-photon datasets.Experimental results show that the proposed method outperforms state-of-the-art methods in various noise levels and exhibits a more efficient capability for recovering high-frequency structures and extracting information.展开更多
Sea cucumber detection is widely recognized as the key to automatic culture.The underwater light environment is complex and easily obscured by mud,sand,reefs,and other underwater organisms.To date,research on sea cucu...Sea cucumber detection is widely recognized as the key to automatic culture.The underwater light environment is complex and easily obscured by mud,sand,reefs,and other underwater organisms.To date,research on sea cucumber detection has mostly concentrated on the distinction between prospective objects and the background.However,the key to proper distinction is the effective extraction of sea cucumber feature information.In this study,the edge-enhanced scaling You Only Look Once-v4(YOLOv4)(ESYv4)was proposed for sea cucumber detection.By emphasizing the target features in a way that reduced the impact of different hues and brightness values underwater on the misjudgment of sea cucumbers,a bidirectional cascade network(BDCN)was used to extract the overall edge greyscale image in the image and add up the original RGB image as the detected input.Meanwhile,the YOLOv4 model for backbone detection is scaled,and the number of parameters is reduced to 48%of the original number of parameters.Validation results of 783images indicated that the detection precision of positive sea cucumber samples reached 0.941.This improvement reflects that the algorithm is more effective to improve the edge feature information of the target.It thus contributes to the automatic multi-objective detection of underwater sea cucumbers.展开更多
基金supported by the Sichuan Science and Technology Program under Grants No.2022YFQ0052 and No.2021YFQ0009.
文摘At present,knowledge embedding methods are widely used in the field of knowledge graph(KG)reasoning,and have been successfully applied to those with large entities and relationships.However,in research and production environments,there are a large number of KGs with a small number of entities and relations,which are called sparse KGs.Limited by the performance of knowledge extraction methods or some other reasons(some common-sense information does not appear in the natural corpus),the relation between entities is often incomplete.To solve this problem,a method of the graph neural network and information enhancement is proposed.The improved method increases the mean reciprocal rank(MRR)and Hit@3 by 1.6%and 1.7%,respectively,when the sparsity of the FB15K-237 dataset is 10%.When the sparsity is 50%,the evaluation indexes MRR and Hit@10 are increased by 0.8%and 1.8%,respectively.
基金Supported by the National Natural Science Foundation of China under Grant Nos 51132004,11474096 and 11604199the Science and Technology Commission of Shanghai Municipality under Grant No 14JC1401500the Higher Education Key Program of He'nan Province under Grant Nos 17A140025 and 16A140030
文摘The femtosecond pulse shaping technique has been shown to be an effective method to control the multi-photon absorption by the light–matter interaction. Previous studies mainly focused on the quantum coherent control of the multi-photon absorption by the phase, amplitude and polarization modulation, but the coherent features of the multi-photon absorption depending on the energy level structure, the laser spectrum bandwidth and laser central frequency still lack in-depth systematic research. In this work, we further explore the coherent features of the resonance-mediated two-photon absorption in a rubidium atom by varying the energy level structure, spectrum bandwidth and central frequency of the femtosecond laser field. The theoretical results show that the change of the intermediate state detuning can effectively influence the enhancement of the near-resonant part, which further affects the transform-limited （TL）-normalized final state population maximum. Moreover, as the laser spectrum bandwidth increases, the TL-normalized final state population maximum can be effectively enhanced due to the increase of the enhancement in the near-resonant part, but the TL-normalized final state population maximum is constant by varying the laser central frequency. These studies can provide a clear physical picture for understanding the coherent features of the resonance-mediated two-photon absorption, and can also provide a theoretical guidance for the future applications.
文摘Single-photon sensors are novel devices with extremely high single-photon sensitivity and temporal resolution.However,these advantages also make them highly susceptible to noise.Moreover,single-photon cameras face severe quantization as low as 1 bit/frame.These factors make it a daunting task to recover high-quality scene information from noisy single-photon data.Most current image reconstruction methods for single-photon data are mathematical approaches,which limits information utilization and algorithm performance.In this work,we propose a hybrid information enhancement model which can significantly enhance the efficiency of information utilization by leveraging attention mechanisms from both spatial and channel branches.Furthermore,we introduce a structural feature enhance module for the FFN of the transformer,which explicitly improves the model's ability to extract and enhance high-frequency structural information through two symmetric convolution branches.Additionally,we propose a single-photon data simulation pipeline based on RAW images to address the challenge of the lack of single-photon datasets.Experimental results show that the proposed method outperforms state-of-the-art methods in various noise levels and exhibits a more efficient capability for recovering high-frequency structures and extracting information.
基金supported by Scientific Research Project of Tianjin Education Commission(Nos.2020KJ091,2018KJ184)National Key Research and Development Program of China(No.2020YFD0900600)+1 种基金the Earmarked Fund for CARS(No.CARS-47)Tianjin Mariculture Industry Technology System Innovation Team Construction Project(No.ITTMRS2021000)。
文摘Sea cucumber detection is widely recognized as the key to automatic culture.The underwater light environment is complex and easily obscured by mud,sand,reefs,and other underwater organisms.To date,research on sea cucumber detection has mostly concentrated on the distinction between prospective objects and the background.However,the key to proper distinction is the effective extraction of sea cucumber feature information.In this study,the edge-enhanced scaling You Only Look Once-v4(YOLOv4)(ESYv4)was proposed for sea cucumber detection.By emphasizing the target features in a way that reduced the impact of different hues and brightness values underwater on the misjudgment of sea cucumbers,a bidirectional cascade network(BDCN)was used to extract the overall edge greyscale image in the image and add up the original RGB image as the detected input.Meanwhile,the YOLOv4 model for backbone detection is scaled,and the number of parameters is reduced to 48%of the original number of parameters.Validation results of 783images indicated that the detection precision of positive sea cucumber samples reached 0.941.This improvement reflects that the algorithm is more effective to improve the edge feature information of the target.It thus contributes to the automatic multi-objective detection of underwater sea cucumbers.
