With the rapid expansion of social media,analyzing emotions and their causes in texts has gained significant importance.Emotion-cause pair extraction enables the identification of causal relationships between emotions...With the rapid expansion of social media,analyzing emotions and their causes in texts has gained significant importance.Emotion-cause pair extraction enables the identification of causal relationships between emotions and their triggers within a text,facilitating a deeper understanding of expressed sentiments and their underlying reasons.This comprehension is crucial for making informed strategic decisions in various business and societal contexts.However,recent research approaches employing multi-task learning frameworks for modeling often face challenges such as the inability to simultaneouslymodel extracted features and their interactions,or inconsistencies in label prediction between emotion-cause pair extraction and independent assistant tasks like emotion and cause extraction.To address these issues,this study proposes an emotion-cause pair extraction methodology that incorporates joint feature encoding and task alignment mechanisms.The model consists of two primary components:First,joint feature encoding simultaneously generates features for emotion-cause pairs and clauses,enhancing feature interactions between emotion clauses,cause clauses,and emotion-cause pairs.Second,the task alignment technique is applied to reduce the labeling distance between emotion-cause pair extraction and the two assistant tasks,capturing deep semantic information interactions among tasks.The proposed method is evaluated on a Chinese benchmark corpus using 10-fold cross-validation,assessing key performance metrics such as precision,recall,and F1 score.Experimental results demonstrate that the model achieves an F1 score of 76.05%,surpassing the state-of-the-art by 1.03%.The proposed model exhibits significant improvements in emotion-cause pair extraction(ECPE)and cause extraction(CE)compared to existing methods,validating its effectiveness.This research introduces a novel approach based on joint feature encoding and task alignment mechanisms,contributing to advancements in emotion-cause pair extraction.However,the study’s limitation lies in the data sources,potentially restricting the generalizability of the findings.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
In order to support the future digital society,sixth generation(6G)network faces the challenge to work efficiently and flexibly in a wider range of scenarios.The traditional way of system design is to sequentially get...In order to support the future digital society,sixth generation(6G)network faces the challenge to work efficiently and flexibly in a wider range of scenarios.The traditional way of system design is to sequentially get the electromagnetic wave propagation model of typical scenarios firstly and then do the network design by simulation offline,which obviously leads to a 6G network lacking of adaptation to dynamic environments.Recently,with the aid of sensing enhancement,more environment information can be obtained.Based on this,from radio wave propagation perspective,we propose a predictive 6G network with environment sensing enhancement,the electromagnetic wave propagation characteristics prediction enabled network(EWave Net),to further release the potential of 6G.To this end,a prediction plane is created to sense,predict and utilize the physical environment information in EWave Net to realize the electromagnetic wave propagation characteristics prediction timely.A two-level closed feedback workflow is also designed to enhance the sensing and prediction ability for EWave Net.Several promising application cases of EWave Net are analyzed and the open issues to achieve this goal are addressed finally.展开更多
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
Light-field displays typically consist of a two-dimensional(2D)display panel and a light modulation device.The 2D panel presents synthesized parallax images,with the total information content of the three-dimensional(...Light-field displays typically consist of a two-dimensional(2D)display panel and a light modulation device.The 2D panel presents synthesized parallax images,with the total information content of the three-dimensional(3D)light feld dictated by the panel's total resolution.Angular resolution serves as a critical metric for light-field displays,where higher angular resolution correlates with a more realistic 3D visual experience.However,the improvement of angular resolution is typically accompanied by a reduction in spatial resolution,due to the limitations of the 2D display panel's total resolution.To address this challenge,a light-feld display method with enhanced information utilization is introduced,achieved through the independent modulation of chrominance and luminance.A static light-field image display system is proposed to verify the feasibility of this method.The system employs a bidirectional angular modulation grating(BAMG)and a collimated light source(CLS)to create uniformly distributed viewpoints in space.A luminance modulation film(LMF)and a chrominance modulation film(CMF)are utilized to modulate the light-field information,with chrominance and luminance synthesized images printed at pixel densities of 720 pixels per inch(PPl)and 8000 dots per inch(DPl),respectively,to align with the differential sensitivities of the human visual system.In the experiment,the proposed display system achieves a full-parallax,high-fidelity color display with a 98.2°horizontal and 97.7°vertical field of view(FOV).So,the light-feld display method of modulating chrominance and luminance separately has been proven to achieve high-fidelity display effects.展开更多
The rapid globalization of the digital ecosystem has elevated information security to a critical concern in modern society. Optical encryption offers an effective approach for enhancing information protection;however,...The rapid globalization of the digital ecosystem has elevated information security to a critical concern in modern society. Optical encryption offers an effective approach for enhancing information protection;however, existing optical encryption strategies are unable to reliably recover encrypted information following free-space transmission. To address this challenge, we propose a novel protocol named the optical coherence engineering encryption protocol(OCE-Encryption Protocol). By jointly manipulating the optical coherence structure and introducing astigmatic phase modulation, the protocol generates a spectral intensity ciphertext capable of secure free-space transmission. At the receiver, the original information can be accurately reconstructed by measuring the optical coherence structure of the received ciphertext and applying the correct decryption key. Furthermore, the proposed protocol demonstrates strong resilience to transmission channel disturbances. We hope that optical coherence engineering can expand the functional boundaries of existing optical encryption protocols and provide a pathway toward next-generation secure optical communication systems.展开更多
Aiming at the problems such as diverse target scales and large-scale changes in crowds in dense crowd scenarios,a crowd density estimation method based on multi-scale feature fusion and information en-hancement is pro...Aiming at the problems such as diverse target scales and large-scale changes in crowds in dense crowd scenarios,a crowd density estimation method based on multi-scale feature fusion and information en-hancement is proposed.Firstly,considering that small-scale targets account for a relatively large proportion in the image,based on the VGG-16 network,the dilated convolution module is introduced to mine the detailed information of the image.Secondly,in order to make full use of the multi-scale information of the target,a new context-aware module is constructed to extract the contrast features between different scales.Finally,con-sidering the characteristic of continuous changes in the target scale,a multi-scale feature aggregation module is designed to enhance the sampling range of dense scales and multi-scale information interaction,thereby improving the network performance.Experiments on public datasets show that the proposed method in this paper can effectively estimate the population density compared with other advanced methods.展开更多
文摘With the rapid expansion of social media,analyzing emotions and their causes in texts has gained significant importance.Emotion-cause pair extraction enables the identification of causal relationships between emotions and their triggers within a text,facilitating a deeper understanding of expressed sentiments and their underlying reasons.This comprehension is crucial for making informed strategic decisions in various business and societal contexts.However,recent research approaches employing multi-task learning frameworks for modeling often face challenges such as the inability to simultaneouslymodel extracted features and their interactions,or inconsistencies in label prediction between emotion-cause pair extraction and independent assistant tasks like emotion and cause extraction.To address these issues,this study proposes an emotion-cause pair extraction methodology that incorporates joint feature encoding and task alignment mechanisms.The model consists of two primary components:First,joint feature encoding simultaneously generates features for emotion-cause pairs and clauses,enhancing feature interactions between emotion clauses,cause clauses,and emotion-cause pairs.Second,the task alignment technique is applied to reduce the labeling distance between emotion-cause pair extraction and the two assistant tasks,capturing deep semantic information interactions among tasks.The proposed method is evaluated on a Chinese benchmark corpus using 10-fold cross-validation,assessing key performance metrics such as precision,recall,and F1 score.Experimental results demonstrate that the model achieves an F1 score of 76.05%,surpassing the state-of-the-art by 1.03%.The proposed model exhibits significant improvements in emotion-cause pair extraction(ECPE)and cause extraction(CE)compared to existing methods,validating its effectiveness.This research introduces a novel approach based on joint feature encoding and task alignment mechanisms,contributing to advancements in emotion-cause pair extraction.However,the study’s limitation lies in the data sources,potentially restricting the generalizability of the findings.
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 the National Natural Science Foundation of China(No.92167202,61925102,U21B2014,62101069)the National Key R&D Program of China(No.2020YFB1805002)。
文摘In order to support the future digital society,sixth generation(6G)network faces the challenge to work efficiently and flexibly in a wider range of scenarios.The traditional way of system design is to sequentially get the electromagnetic wave propagation model of typical scenarios firstly and then do the network design by simulation offline,which obviously leads to a 6G network lacking of adaptation to dynamic environments.Recently,with the aid of sensing enhancement,more environment information can be obtained.Based on this,from radio wave propagation perspective,we propose a predictive 6G network with environment sensing enhancement,the electromagnetic wave propagation characteristics prediction enabled network(EWave Net),to further release the potential of 6G.To this end,a prediction plane is created to sense,predict and utilize the physical environment information in EWave Net to realize the electromagnetic wave propagation characteristics prediction timely.A two-level closed feedback workflow is also designed to enhance the sensing and prediction ability for EWave Net.Several promising application cases of EWave Net are analyzed and the open issues to achieve this goal are addressed finally.
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 Key Research and Development Program of China(2023YFB3611500)National Natural Science Foundation of China(62175015,62335002,62075016).
文摘Light-field displays typically consist of a two-dimensional(2D)display panel and a light modulation device.The 2D panel presents synthesized parallax images,with the total information content of the three-dimensional(3D)light feld dictated by the panel's total resolution.Angular resolution serves as a critical metric for light-field displays,where higher angular resolution correlates with a more realistic 3D visual experience.However,the improvement of angular resolution is typically accompanied by a reduction in spatial resolution,due to the limitations of the 2D display panel's total resolution.To address this challenge,a light-feld display method with enhanced information utilization is introduced,achieved through the independent modulation of chrominance and luminance.A static light-field image display system is proposed to verify the feasibility of this method.The system employs a bidirectional angular modulation grating(BAMG)and a collimated light source(CLS)to create uniformly distributed viewpoints in space.A luminance modulation film(LMF)and a chrominance modulation film(CMF)are utilized to modulate the light-field information,with chrominance and luminance synthesized images printed at pixel densities of 720 pixels per inch(PPl)and 8000 dots per inch(DPl),respectively,to align with the differential sensitivities of the human visual system.In the experiment,the proposed display system achieves a full-parallax,high-fidelity color display with a 98.2°horizontal and 97.7°vertical field of view(FOV).So,the light-feld display method of modulating chrominance and luminance separately has been proven to achieve high-fidelity display effects.
基金National Natural Science Foundation of China(12192254,12374276,12304326,92250304,W2441005,12474333)National Key Research and Development Program of China(2022YFA1404800)+2 种基金Natural Science Foundation of Shandong Province(ZR2023QA081)Qingchuang Science and Technology Plan of Shandong Province(2023KJ198)Young Talent of Lifting Engineering for Science and Technology in Shandong(SDAST2024QTA047).
文摘The rapid globalization of the digital ecosystem has elevated information security to a critical concern in modern society. Optical encryption offers an effective approach for enhancing information protection;however, existing optical encryption strategies are unable to reliably recover encrypted information following free-space transmission. To address this challenge, we propose a novel protocol named the optical coherence engineering encryption protocol(OCE-Encryption Protocol). By jointly manipulating the optical coherence structure and introducing astigmatic phase modulation, the protocol generates a spectral intensity ciphertext capable of secure free-space transmission. At the receiver, the original information can be accurately reconstructed by measuring the optical coherence structure of the received ciphertext and applying the correct decryption key. Furthermore, the proposed protocol demonstrates strong resilience to transmission channel disturbances. We hope that optical coherence engineering can expand the functional boundaries of existing optical encryption protocols and provide a pathway toward next-generation secure optical communication systems.
文摘Aiming at the problems such as diverse target scales and large-scale changes in crowds in dense crowd scenarios,a crowd density estimation method based on multi-scale feature fusion and information en-hancement is proposed.Firstly,considering that small-scale targets account for a relatively large proportion in the image,based on the VGG-16 network,the dilated convolution module is introduced to mine the detailed information of the image.Secondly,in order to make full use of the multi-scale information of the target,a new context-aware module is constructed to extract the contrast features between different scales.Finally,con-sidering the characteristic of continuous changes in the target scale,a multi-scale feature aggregation module is designed to enhance the sampling range of dense scales and multi-scale information interaction,thereby improving the network performance.Experiments on public datasets show that the proposed method in this paper can effectively estimate the population density compared with other advanced methods.
