In this paper, we propose a novel image recompression frame- work and image quality assessment （IQA） method to efficiently recompress Internet images. With this framework image size is significantly reduced without ...In this paper, we propose a novel image recompression frame- work and image quality assessment （IQA） method to efficiently recompress Internet images. With this framework image size is significantly reduced without affecting spatial resolution or perceptible quality of the image. With the help of IQA, the relationship between image quality and image evaluation scores can be quickly established, and the optimal quality factor can be obtained quickly and accurately within a pre - determined perceptual quality range. This process ensures the image＇s perceptual quality, which is applied to each input image. The test results show that, using the proposed method, the file size of images can be reduced by about 45%-60% without affecting their visual quality. Moreover, our new image -reeompression framework can be used in to many different application scenarios.展开更多
The technique of facial attribute manipulation has found increasing application,but it remains challenging to restrict editing of attributes so that a face’s unique details are preserved.In this paper,we introduce ou...The technique of facial attribute manipulation has found increasing application,but it remains challenging to restrict editing of attributes so that a face’s unique details are preserved.In this paper,we introduce our method,which we call a mask-adversarial autoencoder(M-AAE).It combines a variational autoencoder(VAE)and a generative adversarial network(GAN)for photorealistic image generation.We use partial dilated layers to modify a few pixels in the feature maps of an encoder,changing the attribute strength continuously without hindering global information.Our training objectives for the VAE and GAN are reinforced by supervision of face recognition loss and cycle consistency loss,to faithfully preserve facial details.Moreover,we generate facial masks to enforce background consistency,which allows our training to focus on the foreground face rather than the background.Experimental results demonstrate that our method can generate high-quality images with varying attributes,and outperforms existing methods in detail preservation.展开更多
Background:Many studies have confirmed that ileal transposition can improve type 2 diabetes mellitus(T2DM),accompanied by increased glucagon-like peptide-1(GLP-1).We performed the experiment on diabetic rats to evalua...Background:Many studies have confirmed that ileal transposition can improve type 2 diabetes mellitus(T2DM),accompanied by increased glucagon-like peptide-1(GLP-1).We performed the experiment on diabetic rats to evaluate the effects and mechanisms of ileal transposition on the glycemic metabolism.Methods:Twenty Goto-Kakizaki(GK)rats were randomly divided into the ileal transposition group(IT group)and the sham operation group(Shamgroup).Weight,food intake,fasting plasma glucose(FPG),fasting insulin(F-ins),oral glucose tolerance test(OGTT)and GLP-1 were determined at baseline and 1,4,8,16 and 24weeks post-operatively.The homeostasis model assessment-insulin resistance(HOMA-IR)index and the area under the curve(AUC)during OGTT were measured.Histological determination of the GLP-1 receptor(GLP-1R)was performed on the pancreas and ileum24weeks post-operatively.Results:In comparison with the Sham group,the IT group showed a higher GLP-1 level and lower AUC at 4,8,16 and 24 weeks post-operatively(all P<0.05)and a lower FPG,F-ins levels and HOMA-IR at 8,16 and 24 weeks post-operatively(all P<0.05).Compared with baseline levels,the plasma GLP-1,AUC and FPG levels decreased significantly at each postoperative time point in the IT group(all P<0.05),but not in the Sham group(all P>0.05);F-ins and HOMA-IR significantly decreased at 8,16 and 24 weeks post-operatively in the IT group(all P<0.05).GLP-1R expression in the IT group was significantly higher than that of the Sham group in both the pancreas and the ileum at 24 weeks post-operatively(P<0.05).Conclusions:Ileal transposition ameliorated glucose metabolism without reduction in weight or food intake in GK rats,which may be induced by the increased GLP-1 expression.However,the delayed improvement of insulin resistance,accompanied by decreased plasma insulin levels,might not directly result from the increased GLP-1.展开更多
Despite the efficiency of trajectory piecewise-linear(TPWL)model order re-duction(MOR)for nonlinear circuits,it needs large amount of expansion points forlarge-scale nonlinear circuits.This will inevitably increase th...Despite the efficiency of trajectory piecewise-linear(TPWL)model order re-duction(MOR)for nonlinear circuits,it needs large amount of expansion points forlarge-scale nonlinear circuits.This will inevitably increase the model size as well as the simulation time of the resulting reduced macromodels.In this paper,subspaceTPWL-MOR approach is developed for the model order reduction of nonlinear cir-cuits.By breaking the high-dimensional state space into several subspaces with much lower dimensions,the subspace TPWL-MOR has very promising advantages of re-ducing the number of expansion points as well as increasing the effective region of thereduced-order model in the state space.As a result,the model size and the accuracy of the TWPL model can be greatly improved.The numerical results have shown dra-matic reduction in the model size as well as the improvement in accuracy by using the subspace TPWL-MOR compared with the conventional TPWL-MOR approach.展开更多
基金supported in part by China"973"Program under Grant No.2014CB340303
文摘In this paper, we propose a novel image recompression frame- work and image quality assessment （IQA） method to efficiently recompress Internet images. With this framework image size is significantly reduced without affecting spatial resolution or perceptible quality of the image. With the help of IQA, the relationship between image quality and image evaluation scores can be quickly established, and the optimal quality factor can be obtained quickly and accurately within a pre - determined perceptual quality range. This process ensures the image＇s perceptual quality, which is applied to each input image. The test results show that, using the proposed method, the file size of images can be reduced by about 45%-60% without affecting their visual quality. Moreover, our new image -reeompression framework can be used in to many different application scenarios.
基金partially funded by the National Natural Science Foundation of China(No.61972157)the National Social Science Foundation of China(No.18ZD22)+3 种基金the Science and Technology Commission of Shanghai Municipality Program(No.18D1205903)the Science and Technology Commission of Pudong Municipality Program(No.PKJ2018-Y46)the Multidisciplinary Project of Shanghai Jiao Tong University(No.ZH2018ZDA25)partially supported by a joint project of SenseTime and Shanghai Jiao Tong University。
文摘The technique of facial attribute manipulation has found increasing application,but it remains challenging to restrict editing of attributes so that a face’s unique details are preserved.In this paper,we introduce our method,which we call a mask-adversarial autoencoder(M-AAE).It combines a variational autoencoder(VAE)and a generative adversarial network(GAN)for photorealistic image generation.We use partial dilated layers to modify a few pixels in the feature maps of an encoder,changing the attribute strength continuously without hindering global information.Our training objectives for the VAE and GAN are reinforced by supervision of face recognition loss and cycle consistency loss,to faithfully preserve facial details.Moreover,we generate facial masks to enforce background consistency,which allows our training to focus on the foreground face rather than the background.Experimental results demonstrate that our method can generate high-quality images with varying attributes,and outperforms existing methods in detail preservation.
文摘Background:Many studies have confirmed that ileal transposition can improve type 2 diabetes mellitus(T2DM),accompanied by increased glucagon-like peptide-1(GLP-1).We performed the experiment on diabetic rats to evaluate the effects and mechanisms of ileal transposition on the glycemic metabolism.Methods:Twenty Goto-Kakizaki(GK)rats were randomly divided into the ileal transposition group(IT group)and the sham operation group(Shamgroup).Weight,food intake,fasting plasma glucose(FPG),fasting insulin(F-ins),oral glucose tolerance test(OGTT)and GLP-1 were determined at baseline and 1,4,8,16 and 24weeks post-operatively.The homeostasis model assessment-insulin resistance(HOMA-IR)index and the area under the curve(AUC)during OGTT were measured.Histological determination of the GLP-1 receptor(GLP-1R)was performed on the pancreas and ileum24weeks post-operatively.Results:In comparison with the Sham group,the IT group showed a higher GLP-1 level and lower AUC at 4,8,16 and 24 weeks post-operatively(all P<0.05)and a lower FPG,F-ins levels and HOMA-IR at 8,16 and 24 weeks post-operatively(all P<0.05).Compared with baseline levels,the plasma GLP-1,AUC and FPG levels decreased significantly at each postoperative time point in the IT group(all P<0.05),but not in the Sham group(all P>0.05);F-ins and HOMA-IR significantly decreased at 8,16 and 24 weeks post-operatively in the IT group(all P<0.05).GLP-1R expression in the IT group was significantly higher than that of the Sham group in both the pancreas and the ileum at 24 weeks post-operatively(P<0.05).Conclusions:Ileal transposition ameliorated glucose metabolism without reduction in weight or food intake in GK rats,which may be induced by the increased GLP-1 expression.However,the delayed improvement of insulin resistance,accompanied by decreased plasma insulin levels,might not directly result from the increased GLP-1.
文摘Despite the efficiency of trajectory piecewise-linear(TPWL)model order re-duction(MOR)for nonlinear circuits,it needs large amount of expansion points forlarge-scale nonlinear circuits.This will inevitably increase the model size as well as the simulation time of the resulting reduced macromodels.In this paper,subspaceTPWL-MOR approach is developed for the model order reduction of nonlinear cir-cuits.By breaking the high-dimensional state space into several subspaces with much lower dimensions,the subspace TPWL-MOR has very promising advantages of re-ducing the number of expansion points as well as increasing the effective region of thereduced-order model in the state space.As a result,the model size and the accuracy of the TWPL model can be greatly improved.The numerical results have shown dra-matic reduction in the model size as well as the improvement in accuracy by using the subspace TPWL-MOR compared with the conventional TPWL-MOR approach.
