Generating realistic and synthetic video from text is a highly challenging task due to the multitude of issues involved,including digit deformation,noise interference between frames,blurred output,and the need for tem...Generating realistic and synthetic video from text is a highly challenging task due to the multitude of issues involved,including digit deformation,noise interference between frames,blurred output,and the need for temporal coherence across frames.In this paper,we propose a novel approach for generating coherent videos of moving digits from textual input using a Deep Deconvolutional Generative Adversarial Network(DD-GAN).The DDGAN comprises a Deep Deconvolutional Neural Network(DDNN)as a Generator(G)and a modified Deep Convolutional Neural Network(DCNN)as a Discriminator(D)to ensure temporal coherence between adjacent frames.The proposed research involves several steps.First,the input text is fed into a Long Short Term Memory(LSTM)based text encoder and then smoothed using Conditioning Augmentation(CA)techniques to enhance the effectiveness of the Generator(G).Next,using a DDNN to generate video frames by incorporating enhanced text and random noise and modifying a DCNN to act as a Discriminator(D),effectively distinguishing between generated and real videos.This research evaluates the quality of the generated videos using standard metrics like Inception Score(IS),Fréchet Inception Distance(FID),Fréchet Inception Distance for video(FID2vid),and Generative Adversarial Metric(GAM),along with a human study based on realism,coherence,and relevance.By conducting experiments on Single-Digit Bouncing MNIST GIFs(SBMG),Two-Digit Bouncing MNIST GIFs(TBMG),and a custom dataset of essential mathematics videos with related text,this research demonstrates significant improvements in both metrics and human study results,confirming the effectiveness of DD-GAN.This research also took the exciting challenge of generating preschool math videos from text,handling complex structures,digits,and symbols,and achieving successful results.The proposed research demonstrates promising results for generating coherent videos from textual input.展开更多
The challenging task of handwriting style synthesis requires capturing the individuality and diversity of human handwriting.The majority of currently available methods use either a generative adversarial network(GAN)o...The challenging task of handwriting style synthesis requires capturing the individuality and diversity of human handwriting.The majority of currently available methods use either a generative adversarial network(GAN)or a recurrent neural network(RNN)to generate new handwriting styles.This is why these techniques frequently fall short of producing diverse and realistic text pictures,particularly for terms that are not commonly used.To resolve that,this research proposes a novel deep learning model that consists of a style encoder and a text generator to synthesize different handwriting styles.This network excels in generating conditional text by extracting style vectors from a series of style images.The model performs admirably on a range of handwriting synthesis tasks,including the production of text that is out-of-vocabulary.It works more effectively than previous approaches by displaying lower values on key Generative Adversarial Network evaluation metrics,such Geometric Score(GS)(3.21×10^(-5))and Fréchet Inception Distance(FID)(8.75),as well as text recognition metrics,like Character Error Rate(CER)and Word Error Rate(WER).A thorough component analysis revealed the steady improvement in image production quality,highlighting the importance of specific handwriting styles.Applicable fields include digital forensics,creative writing,and document security.展开更多
This study utilized continuous observational data from a PARSIVEL2 disdrometer collected during winter from 2019 to 2021 in the southwest mountainous areas of China.Based on the diameter and terminal fall velocity of ...This study utilized continuous observational data from a PARSIVEL2 disdrometer collected during winter from 2019 to 2021 in the southwest mountainous areas of China.Based on the diameter and terminal fall velocity of the precipitation particles,combined with the discrete Fréchet distance method,the precipitation particles were classified into five categories:freezing raindrops,freezing raindrops-graupel mixed(F-G Mixed),graupel,graupel-snow mixed(G-S Mixed),and snow.The characteristics of their particle size distributions(PSDs)were analyzed,and the results indicated that during freezing weather,the dominant precipitation type was G-S Mixed,accounting for 44.80%of total precipitation.The total number concentration(Nt),mass-weighted mean diameter(Dm),and spectrum dispersion(σ)of all precipitation particles exhibit a positive correlation with precipitation intensity(PI),while the normalized intercept parameter in logarithmic form(log_(10)N_(w))shows minimal correlation with PI.Particles with diameters smaller than 2 mm contributed significantly to Nt,with freezing raindrops,F-G Mixed,and graupel particles between 1 mm and 2 mm,and G-S Mixed and snow particles larger than 4 mm contributing the most to PI.The mean PSD width followed the order of snow>G-S Mixed>graupel>freezing raindrops>F-G Mixed.Furthermore,this study derives the shape(μ)and slope(Λ)parameters of the Gamma distribution for different precipitation types,as well as the relationships between radar reflectivity(Z)and PI,and between kinetic energy(KE)and PI.These findings are expected to enhance the accuracy of PSD retrieval and the quantitative estimation of winter precipitation in this area.展开更多
Boundary equilibrium generative adversarial networks(BEGANs)are the improved version of generative adversarial networks(GANs).In this paper,an improved BEGAN with a skip-connection technique in the generator and the d...Boundary equilibrium generative adversarial networks(BEGANs)are the improved version of generative adversarial networks(GANs).In this paper,an improved BEGAN with a skip-connection technique in the generator and the discriminator is proposed.Moreover,an alternative time-scale update rule is adopted to balance the learning rate of the generator and the discriminator.Finally,the performance of the proposed method is quantitatively evaluated by Fréchet inception distance(FID)and inception score(IS).The test results show that the performance of the proposed method is better than that of the original BEGAN.展开更多
基金supported by the General Program of the National Natural Science Foundation of China(Grant No.61977029).
文摘Generating realistic and synthetic video from text is a highly challenging task due to the multitude of issues involved,including digit deformation,noise interference between frames,blurred output,and the need for temporal coherence across frames.In this paper,we propose a novel approach for generating coherent videos of moving digits from textual input using a Deep Deconvolutional Generative Adversarial Network(DD-GAN).The DDGAN comprises a Deep Deconvolutional Neural Network(DDNN)as a Generator(G)and a modified Deep Convolutional Neural Network(DCNN)as a Discriminator(D)to ensure temporal coherence between adjacent frames.The proposed research involves several steps.First,the input text is fed into a Long Short Term Memory(LSTM)based text encoder and then smoothed using Conditioning Augmentation(CA)techniques to enhance the effectiveness of the Generator(G).Next,using a DDNN to generate video frames by incorporating enhanced text and random noise and modifying a DCNN to act as a Discriminator(D),effectively distinguishing between generated and real videos.This research evaluates the quality of the generated videos using standard metrics like Inception Score(IS),Fréchet Inception Distance(FID),Fréchet Inception Distance for video(FID2vid),and Generative Adversarial Metric(GAM),along with a human study based on realism,coherence,and relevance.By conducting experiments on Single-Digit Bouncing MNIST GIFs(SBMG),Two-Digit Bouncing MNIST GIFs(TBMG),and a custom dataset of essential mathematics videos with related text,this research demonstrates significant improvements in both metrics and human study results,confirming the effectiveness of DD-GAN.This research also took the exciting challenge of generating preschool math videos from text,handling complex structures,digits,and symbols,and achieving successful results.The proposed research demonstrates promising results for generating coherent videos from textual input.
基金supported by the National Research Foundation of Korea(NRF)Grant funded by the Korean government(MSIT)(NRF-2023R1A2C1005950).
文摘The challenging task of handwriting style synthesis requires capturing the individuality and diversity of human handwriting.The majority of currently available methods use either a generative adversarial network(GAN)or a recurrent neural network(RNN)to generate new handwriting styles.This is why these techniques frequently fall short of producing diverse and realistic text pictures,particularly for terms that are not commonly used.To resolve that,this research proposes a novel deep learning model that consists of a style encoder and a text generator to synthesize different handwriting styles.This network excels in generating conditional text by extracting style vectors from a series of style images.The model performs admirably on a range of handwriting synthesis tasks,including the production of text that is out-of-vocabulary.It works more effectively than previous approaches by displaying lower values on key Generative Adversarial Network evaluation metrics,such Geometric Score(GS)(3.21×10^(-5))and Fréchet Inception Distance(FID)(8.75),as well as text recognition metrics,like Character Error Rate(CER)and Word Error Rate(WER).A thorough component analysis revealed the steady improvement in image production quality,highlighting the importance of specific handwriting styles.Applicable fields include digital forensics,creative writing,and document security.
基金supported by the National Natural Science Foundation of China(Grant Nos.42075063,42075066)the Jiangsu Graduate Scientific Research Innovation Project(Grant No.KYCX23_1316)+2 种基金the China Scholarship Council(CSC)(Grant No.202309040027)the CMA Meteorological Observation Center Field Experimental Project in 2024(Grant No.GCSYJH24-30)the Project of China Meteorological Administration Training Center(Grant No.2024CMATCPY06)。
文摘This study utilized continuous observational data from a PARSIVEL2 disdrometer collected during winter from 2019 to 2021 in the southwest mountainous areas of China.Based on the diameter and terminal fall velocity of the precipitation particles,combined with the discrete Fréchet distance method,the precipitation particles were classified into five categories:freezing raindrops,freezing raindrops-graupel mixed(F-G Mixed),graupel,graupel-snow mixed(G-S Mixed),and snow.The characteristics of their particle size distributions(PSDs)were analyzed,and the results indicated that during freezing weather,the dominant precipitation type was G-S Mixed,accounting for 44.80%of total precipitation.The total number concentration(Nt),mass-weighted mean diameter(Dm),and spectrum dispersion(σ)of all precipitation particles exhibit a positive correlation with precipitation intensity(PI),while the normalized intercept parameter in logarithmic form(log_(10)N_(w))shows minimal correlation with PI.Particles with diameters smaller than 2 mm contributed significantly to Nt,with freezing raindrops,F-G Mixed,and graupel particles between 1 mm and 2 mm,and G-S Mixed and snow particles larger than 4 mm contributing the most to PI.The mean PSD width followed the order of snow>G-S Mixed>graupel>freezing raindrops>F-G Mixed.Furthermore,this study derives the shape(μ)and slope(Λ)parameters of the Gamma distribution for different precipitation types,as well as the relationships between radar reflectivity(Z)and PI,and between kinetic energy(KE)and PI.These findings are expected to enhance the accuracy of PSD retrieval and the quantitative estimation of winter precipitation in this area.
基金National Natural Science Foundation of China(Nos.61602398,U19A2083)Science and Technology Department of Hunan Province,China(No.2019GK4007)。
文摘Boundary equilibrium generative adversarial networks(BEGANs)are the improved version of generative adversarial networks(GANs).In this paper,an improved BEGAN with a skip-connection technique in the generator and the discriminator is proposed.Moreover,an alternative time-scale update rule is adopted to balance the learning rate of the generator and the discriminator.Finally,the performance of the proposed method is quantitatively evaluated by Fréchet inception distance(FID)and inception score(IS).The test results show that the performance of the proposed method is better than that of the original BEGAN.
