From a cross-cultural pragmatic perspective, this paper makes a comparative study on American and Chinese ways of address, and finds that due to different cultural values, languages differ in the actual realization of...From a cross-cultural pragmatic perspective, this paper makes a comparative study on American and Chinese ways of address, and finds that due to different cultural values, languages differ in the actual realization of address strategies and modifications, which leads to varied interactional styles, and thus holds that there exist distinctive cultural differences in the interactional styles of verbal behaviors, which challenges the universality of pragmatic rules among different languages and cultures.展开更多
Vision Transformer has shown impressive performance on the image classification tasks.Observing that most existing visual style transfer(VST)algorithms are based on the texture-biased convolution neural network(CNN),h...Vision Transformer has shown impressive performance on the image classification tasks.Observing that most existing visual style transfer(VST)algorithms are based on the texture-biased convolution neural network(CNN),here raises the question of whether the shape-biased Vision Transformer can perform style transfer as CNN.In this work,we focus on comparing and analyzing the shape bias between CNN-and transformer-based models from the view of VST tasks.For comprehensive comparisons,we propose three kinds of transformer-based visual style transfer(Tr-VST)methods(Tr-NST for optimization-based VST,Tr-WCT for reconstruction-based VST and Tr-AdaIN for perceptual-based VST).By engaging three mainstream VST methods in the transformer pipeline,we show that transformer-based models pre-trained on ImageNet are not proper for style transfer methods.Due to the strong shape bias of the transformer-based models,these Tr-VST methods cannot render style patterns.We further analyze the shape bias by considering the influence of the learned parameters and the structure design.Results prove that with proper style supervision,the transformer can learn similar texture-biased features as CNN does.With the reduced shape bias in the transformer encoder,Tr-VST methods can generate higher-quality results compared with state-of-the-art VST methods.展开更多
文摘From a cross-cultural pragmatic perspective, this paper makes a comparative study on American and Chinese ways of address, and finds that due to different cultural values, languages differ in the actual realization of address strategies and modifications, which leads to varied interactional styles, and thus holds that there exist distinctive cultural differences in the interactional styles of verbal behaviors, which challenges the universality of pragmatic rules among different languages and cultures.
基金the National Key Research and Development Program of China under Grant No.2020AAA0106200the National Natural Science Foundation of China under Grant Nos.62102162,61832016,U20B2070,and 6210070958+1 种基金the CASIA-Tencent Youtu Joint Research Projectthe Open Projects Program of the National Laboratory of Pattern Recognition.
文摘Vision Transformer has shown impressive performance on the image classification tasks.Observing that most existing visual style transfer(VST)algorithms are based on the texture-biased convolution neural network(CNN),here raises the question of whether the shape-biased Vision Transformer can perform style transfer as CNN.In this work,we focus on comparing and analyzing the shape bias between CNN-and transformer-based models from the view of VST tasks.For comprehensive comparisons,we propose three kinds of transformer-based visual style transfer(Tr-VST)methods(Tr-NST for optimization-based VST,Tr-WCT for reconstruction-based VST and Tr-AdaIN for perceptual-based VST).By engaging three mainstream VST methods in the transformer pipeline,we show that transformer-based models pre-trained on ImageNet are not proper for style transfer methods.Due to the strong shape bias of the transformer-based models,these Tr-VST methods cannot render style patterns.We further analyze the shape bias by considering the influence of the learned parameters and the structure design.Results prove that with proper style supervision,the transformer can learn similar texture-biased features as CNN does.With the reduced shape bias in the transformer encoder,Tr-VST methods can generate higher-quality results compared with state-of-the-art VST methods.
