This study looks at the interaction between the process of intersemiosis and resemiosis in multimodality. The importance of both phases is widely acknowledged as part of the meaning making process but many practical s...This study looks at the interaction between the process of intersemiosis and resemiosis in multimodality. The importance of both phases is widely acknowledged as part of the meaning making process but many practical studies focus on the first rather than the second. In particular this study looks at two groups of images about gender relations in Saudi Arabia following the post-2017 reforms of the male guardianship laws. One group are mostly made up of photographs and the second group of cartoons and posters. One important finding is that the latter tend to be less ambiguous in their semiotic structure than the former. In particular, there are instances in the first group where a standard study of intersemiosis indicates low modality but the image may be seen as inherently plausible by many observers. This suggests that while resemiosis can be applied to a single image it may be more appropriate as a tool when applied to an overall news article or set of images. In the same way that not all individual semiotic modes are complementary in how they build meaning, then it is possible for different images to be supportive, contradictory or unclear when studied in isolation.展开更多
The main purpose of our paper is to identify and analyse the underlying stereotype attributes concerning accountant,accounting and users through cartoons.Doing so,we aim to capture insights of how this spectrum of soc...The main purpose of our paper is to identify and analyse the underlying stereotype attributes concerning accountant,accounting and users through cartoons.Doing so,we aim to capture insights of how this spectrum of society perceives actors involved on accounting issues.Our study also differs from others as our period of analysis is long,79 years,from 1925 to 2003.As we have the advantage of a long period and a popular non-professional database,we can work with multiple actors as accountant,accounting and users,instead of focusing on single one.And the richness of database also allowed splitting these main actors in 7 actors.In order to capture stereotype nuances of multiple actors from a cartoon database,we use discourse analysis method that has been used on other studies of identity but not to study accounting issues.As cartoons are composed by images and texts to give a message,it is richer to analyze discourse beyond images and texts.Our results are mainly consistent with previous studies although we found some different results when considering different periods of time as well new findings about tax actors such as taxpayers,tax agent and tax accounting.展开更多
The present paper examines the vocabulary contained in the British animated programme Peppa Pig and investigates whether this vocabulary is highly frequent but also appropriate for beginner learners of English.It also...The present paper examines the vocabulary contained in the British animated programme Peppa Pig and investigates whether this vocabulary is highly frequent but also appropriate for beginner learners of English.It also examines if there is any formulaic language in it.Comparison with the BNC wordlist,the CYLET and EVP wordlists for beginners suggests that one fifth of the English vocabulary contained in the show is highly frequent and that a small amount of it overlaps with the proposed vocabulary lists of CYLET and EVP for A1 level.Therefore,the majority of the vocabulary contained in the show is mainly infrequent but still appropriate while the in-depth analysis of selective episodes showed amplitude of formulaic language in the show and plenty repetition of it.展开更多
Is this sort of thing inevitable,as China opens her doors to the outside?Are these cartoons therefore to be simply filed away under the harmless excuse of"cultural exchange?"To be fair,Japan has its own fear...Is this sort of thing inevitable,as China opens her doors to the outside?Are these cartoons therefore to be simply filed away under the harmless excuse of"cultural exchange?"To be fair,Japan has its own fears about Western cultural imperialism,but a few people in China,more threatened by Astroboy than Sony,feel that measures must be taken to man Chi-na's cultural barricades and resist the invasion.Look at what happened to Peking opera,they warmn.Because children are inheritors of the great cultural tradition and the hope of any country,they must not be sacrificed to the Transformers or the Flower Fairy Lady.展开更多
"And do you,Allison,promise not to share your password with anyone but Roger..."Your X-ray shows a broken arm.You have two choices.I can fix it for$850,or I can just photoshop the X-ray for$8.50.
China＇s booming animation industry reaches a turning point THE success of Pleasant Goat and Big Big Wolf has made Chinese investors realize that producing a moneymaking blockbuster does not require overpriced movie s...China＇s booming animation industry reaches a turning point THE success of Pleasant Goat and Big Big Wolf has made Chinese investors realize that producing a moneymaking blockbuster does not require overpriced movie stars or gorgeous actresses,or even a real person.Since its debut in 2005.the 2D cartoon TV series attracted viewers with stories about clever lambs outwitting clumsy wolves,and was soon made into five films,garnering ticket revenues of over 700 million yuan（$114 million）. A great number of animated characters are now following in the footsteps of these goats and wolves and making their way onto Chinese screens.展开更多
The present paper explores how the issue of the current energy crisis in the wake of the Covid-19 and Ukraine war was constructed by political cartoons.Adopting Critical Multimodal Metaphor Scenario Analysis,this pape...The present paper explores how the issue of the current energy crisis in the wake of the Covid-19 and Ukraine war was constructed by political cartoons.Adopting Critical Multimodal Metaphor Scenario Analysis,this paper focuses on the DISEASE metaphor scenario,one of the most recurring scenarios in political cartoons on this topic,and specifically emphasizes how the METHOD OF TREATMENT,one of the structural elements in the scenario,is represented.The analysis reveals that two predominant scenarios cOnstitute the representations of the METHOD OF TREATMENT:NARCOTIC Scenario and MEDICINE scenario.They differ in entailments:one frames fossil energy as detrimental narcotic while the other frames it as therapeutic medicine.By means of the two scenarios,these cartoons convey strong criticism of the major involvers in the energy crisis,namely,the E.U.,Russia,and the U.S.The cartoons make full use of the dynamic interplay of visual and/or verbal metonymy,metaphor,and narrative to elicit associations,assumptions and evaluations in the viewers,helping facilitate understanding and constructing a view of the crisis reality.The present analysis sheds light on the way cartoonists reshape the public point of view in the framing of specific event(s).展开更多
Until recently,the study of language and meaning of cartoons,the media discourses they generate,and their analysis as a creative means of exploring meaning-making processes as semiotic resources have not received much...Until recently,the study of language and meaning of cartoons,the media discourses they generate,and their analysis as a creative means of exploring meaning-making processes as semiotic resources have not received much scholarly attention in Nigeria.Although cartoons that involve the use of satire and humour as visual representations of reality have gained prominence across many media platforms in Nigeria,only a few scholars have examined this from a social semiotics perspective.This has created a gap in the literature,thus creating room for a para-digm shift in the field of social semiotics.This study explores the semiotics of car-toons in selected Nigerian newspapers to examine the meaning-making resources employed in the visual representation of ASUU strikes in Nigeria.The study,there-fore,examines how cartoonists manipulate symbols,signs,and other semiotic resources to convey specific meanings through visual and textual representations.The study adopts a qualitative research design;data comprising cartoons sourced from selected Vanguard Newspapers and websites are analyzed using Kress and Van Leeuwen's visual semiotics and interpreted from the standpoints of Halliday's Systematic Functional Linguistics(SFL)approach and O'Halloran's position on metaphorical constructions of meaning.Here,metaphorical manipulation and rep-resentation of visual elements in the selected cartoons are interrogated.Findings from the study show the use of semiotic resources in the portrayer of reality in the context of the seemingly intractable ASUU strikes and their consequences on aca-demic activities in Nigeria.This scholarly intervention deserves attention as it significantly contributes to the field of social semiotics through its visual represen-tation in portraying challenges faced by the educational systems in Nigeria vis-a-vis poorgovernment funding.展开更多
Most children have become so addicted to TV, because there is precious little else they do for fun. Part of that enjoyment, in China, is the many cartoon programs available for young viewers, a large number of which a...Most children have become so addicted to TV, because there is precious little else they do for fun. Part of that enjoyment, in China, is the many cartoon programs available for young viewers, a large number of which are foreign productions. But that's all about to change. Foreign cartoons can no longer be screened during prime time viewing. Now millions of upset parents and children are questioning a new展开更多
Do You Know My Woik?One night a hotel caught fire,and the peoplewho were staying in it ran out in their night clothes.Two men stood outside and looked at the fire."Before l came out,"said one,"I ran int...Do You Know My Woik?One night a hotel caught fire,and the peoplewho were staying in it ran out in their night clothes.Two men stood outside and looked at the fire."Before l came out,"said one,"I ran into someof the rooms and found a lot of money.People don’tthink of money when they’re afraid.When anyoneleaves paper money in a fire,the fire burns it.So Itook all the bills that I couht find.No one will bepoorer because I took them.""You don’t know my work,"said the other.展开更多
Begging for DimesSon:Dad,give me a dime.Father:Son,don’t you think you’re getting too big to beforever begging for dimes?Son:I guess you’re right,Dad.Give me a dollar,will you?
The Only ExampleMr.Henry Beecher entered school and found severalletters awaiting him.He opened one and found it containedthe single word"FOOL".Quietly and with seriousness he an-nounced to students the fact...The Only ExampleMr.Henry Beecher entered school and found severalletters awaiting him.He opened one and found it containedthe single word"FOOL".Quietly and with seriousness he an-nounced to students the fact in these words:"I have known many an example of a man writing a let-ter and forgetting to sign his name, but this is the only exam-ple I have ever known of a man signing his name and forget-ting to write the letter."展开更多
The devastating effects of the COVID-19 pandemic have acutely shown the need for maintaining robust international and national systems for biological security and ensuring that life sciences are used only for peaceful...The devastating effects of the COVID-19 pandemic have acutely shown the need for maintaining robust international and national systems for biological security and ensuring that life sciences are used only for peaceful purposes.Life science stakeholders can play an important role in safeguarding scientific and technological advances in biology and related fields against accidental or deliberate misuse,not least because they are on the frontlines of driving innovation.In this paper,we argue that enhancing awareness and understanding of the risk of deliberate disease is essential for effective biological security.We first discuss the issue of‘dual use’in science and technology as it relates to disarmament and non-proliferation of weapons of mass destruction.Second,we review how scientist engagement with dual-use risks has been addressed in the context of the Biological and Toxin Weapons Convention(BTWC).Third,we report on the development of an innovative awarenessraising tool,a cartoon series,that can be used for engaging life science stakeholders with BTWC issues.Finally,we outline a set of practical considerations for promoting sustainable life science engagement with the BTWC.展开更多
Cartoons are a worldwide popular visual entertainment medium with a long history. Nowadays,with the boom of electronic devices, there is an increasing need to digitize old classic cartoons as a basis for further editi...Cartoons are a worldwide popular visual entertainment medium with a long history. Nowadays,with the boom of electronic devices, there is an increasing need to digitize old classic cartoons as a basis for further editing, including deformation,colorization, etc. To perform such editing, it is essential to extract the structure lines within cartoon images.Traditional edge detection methods are mainly based on gradients. These methods perform poorly in the face of compression artifacts and spatially-varying line colors,which cause gradient values to become unreliable. This paper presents the first approach to extract structure lines in cartoons based on regions. Our method starts by segmenting an image into regions, and then classifies them as edge regions and non-edge regions. Our second main contribution comprises three measures to estimate the likelihood of a region being a non-edge region.These measure darkness, local contrast, and shape.Since the likelihoods become unreliable as regions become smaller, we further classify regions using both likelihoods and the relationships to neighboring regions via a graph-cut formulation. Our method has been evaluated on a wide variety of cartoon images, and convincing results are obtained in all cases.展开更多
The centric position of the body in cognition has long been the paradigm for theories of embodiment; its research, however, has two limitations: 1) many studies have primarily worked on a specific, single dimension of...The centric position of the body in cognition has long been the paradigm for theories of embodiment; its research, however, has two limitations: 1) many studies have primarily worked on a specific, single dimension of the body, lacking a dynamic and comprehensive perspective; 2) the multimodal nature of embodied cognition has been tremendously underestimated, particularly in terms of the multimodal representation of physical signs. In view of the above two problems, the present research, with news cartoons as its research objects, takes a multi-layered perspective to view the semiosis of physical signs, for the role of the "body"amid the semiotization process might differ on different layers of representation. The author argues that: 1) on the formal layer, physical signs, which depend on perceptual senses, are realized by virtue of embodied simulation, which can help divert interpreters' attention from the form to the cognitive content; 2) on the conceptual layer, the semiotization of physical signs can be considered as a modularization process, absorbing modules from different sources and then being integrated as a whole, which can be explained by metonymy and multimodal metaphor theory; 3) on the contextual layer, the referent of the "body" is believed to be gradually replaced by its contextual symbolic meaning, which, by nature, arises from the reinterpretation of physical signs in specific cognitive situations.展开更多
Visual illustration transformation from real-world to cartoon images is one of the famous and challenging tasks in computer vision.Image-to-image translation from real-world to cartoon domains poses issues such as a l...Visual illustration transformation from real-world to cartoon images is one of the famous and challenging tasks in computer vision.Image-to-image translation from real-world to cartoon domains poses issues such as a lack of paired training samples,lack of good image translation,low feature extraction from the previous domain images,and lack of high-quality image translation from the traditional generator algorithms.To solve the above-mentioned issues,paired independent model,high-quality dataset,Bayesian-based feature extractor,and an improved generator must be proposed.In this study,we propose a high-quality dataset to reduce the effect of paired training samples on the model’s performance.We use a Bayesian Very Deep Convolutional Network(VGG)-based feature extractor to improve the performance of the standard feature extractor because Bayesian inference regu-larizes weights well.The generator from the Cartoon Generative Adversarial Network(GAN)is modified by introducing a depthwise convolution layer and channel attention mechanism to improve the performance of the original generator.We have used the Fréchet inception distance(FID)score and user preference score to evaluate the performance of the model.The FID scores obtained for the generated cartoon and real-world images are 107 and 76 for the TCC style,and 137 and 57 for the Hayao style,respectively.User preference score is also calculated to evaluate the quality of generated images and our proposed model acquired a high preference score compared to other models.We achieved stunning results in producing high-quality cartoon images,demonstrating the proposed model’s effectiveness in transferring style between authentic images and cartoon images.展开更多
文摘This study looks at the interaction between the process of intersemiosis and resemiosis in multimodality. The importance of both phases is widely acknowledged as part of the meaning making process but many practical studies focus on the first rather than the second. In particular this study looks at two groups of images about gender relations in Saudi Arabia following the post-2017 reforms of the male guardianship laws. One group are mostly made up of photographs and the second group of cartoons and posters. One important finding is that the latter tend to be less ambiguous in their semiotic structure than the former. In particular, there are instances in the first group where a standard study of intersemiosis indicates low modality but the image may be seen as inherently plausible by many observers. This suggests that while resemiosis can be applied to a single image it may be more appropriate as a tool when applied to an overall news article or set of images. In the same way that not all individual semiotic modes are complementary in how they build meaning, then it is possible for different images to be supportive, contradictory or unclear when studied in isolation.
文摘The main purpose of our paper is to identify and analyse the underlying stereotype attributes concerning accountant,accounting and users through cartoons.Doing so,we aim to capture insights of how this spectrum of society perceives actors involved on accounting issues.Our study also differs from others as our period of analysis is long,79 years,from 1925 to 2003.As we have the advantage of a long period and a popular non-professional database,we can work with multiple actors as accountant,accounting and users,instead of focusing on single one.And the richness of database also allowed splitting these main actors in 7 actors.In order to capture stereotype nuances of multiple actors from a cartoon database,we use discourse analysis method that has been used on other studies of identity but not to study accounting issues.As cartoons are composed by images and texts to give a message,it is richer to analyze discourse beyond images and texts.Our results are mainly consistent with previous studies although we found some different results when considering different periods of time as well new findings about tax actors such as taxpayers,tax agent and tax accounting.
文摘The present paper examines the vocabulary contained in the British animated programme Peppa Pig and investigates whether this vocabulary is highly frequent but also appropriate for beginner learners of English.It also examines if there is any formulaic language in it.Comparison with the BNC wordlist,the CYLET and EVP wordlists for beginners suggests that one fifth of the English vocabulary contained in the show is highly frequent and that a small amount of it overlaps with the proposed vocabulary lists of CYLET and EVP for A1 level.Therefore,the majority of the vocabulary contained in the show is mainly infrequent but still appropriate while the in-depth analysis of selective episodes showed amplitude of formulaic language in the show and plenty repetition of it.
文摘Is this sort of thing inevitable,as China opens her doors to the outside?Are these cartoons therefore to be simply filed away under the harmless excuse of"cultural exchange?"To be fair,Japan has its own fears about Western cultural imperialism,but a few people in China,more threatened by Astroboy than Sony,feel that measures must be taken to man Chi-na's cultural barricades and resist the invasion.Look at what happened to Peking opera,they warmn.Because children are inheritors of the great cultural tradition and the hope of any country,they must not be sacrificed to the Transformers or the Flower Fairy Lady.
文摘"And do you,Allison,promise not to share your password with anyone but Roger..."Your X-ray shows a broken arm.You have two choices.I can fix it for$850,or I can just photoshop the X-ray for$8.50.
文摘China＇s booming animation industry reaches a turning point THE success of Pleasant Goat and Big Big Wolf has made Chinese investors realize that producing a moneymaking blockbuster does not require overpriced movie stars or gorgeous actresses,or even a real person.Since its debut in 2005.the 2D cartoon TV series attracted viewers with stories about clever lambs outwitting clumsy wolves,and was soon made into five films,garnering ticket revenues of over 700 million yuan（$114 million）. A great number of animated characters are now following in the footsteps of these goats and wolves and making their way onto Chinese screens.
基金support from the China Ministry of Education,its Humanities and Social Sciences Fund,for the project"A Cognitive Critical Study of Multimodal Discourses of Energy Public Opinion"(grant number:21YJA740055).
文摘The present paper explores how the issue of the current energy crisis in the wake of the Covid-19 and Ukraine war was constructed by political cartoons.Adopting Critical Multimodal Metaphor Scenario Analysis,this paper focuses on the DISEASE metaphor scenario,one of the most recurring scenarios in political cartoons on this topic,and specifically emphasizes how the METHOD OF TREATMENT,one of the structural elements in the scenario,is represented.The analysis reveals that two predominant scenarios cOnstitute the representations of the METHOD OF TREATMENT:NARCOTIC Scenario and MEDICINE scenario.They differ in entailments:one frames fossil energy as detrimental narcotic while the other frames it as therapeutic medicine.By means of the two scenarios,these cartoons convey strong criticism of the major involvers in the energy crisis,namely,the E.U.,Russia,and the U.S.The cartoons make full use of the dynamic interplay of visual and/or verbal metonymy,metaphor,and narrative to elicit associations,assumptions and evaluations in the viewers,helping facilitate understanding and constructing a view of the crisis reality.The present analysis sheds light on the way cartoonists reshape the public point of view in the framing of specific event(s).
文摘Until recently,the study of language and meaning of cartoons,the media discourses they generate,and their analysis as a creative means of exploring meaning-making processes as semiotic resources have not received much scholarly attention in Nigeria.Although cartoons that involve the use of satire and humour as visual representations of reality have gained prominence across many media platforms in Nigeria,only a few scholars have examined this from a social semiotics perspective.This has created a gap in the literature,thus creating room for a para-digm shift in the field of social semiotics.This study explores the semiotics of car-toons in selected Nigerian newspapers to examine the meaning-making resources employed in the visual representation of ASUU strikes in Nigeria.The study,there-fore,examines how cartoonists manipulate symbols,signs,and other semiotic resources to convey specific meanings through visual and textual representations.The study adopts a qualitative research design;data comprising cartoons sourced from selected Vanguard Newspapers and websites are analyzed using Kress and Van Leeuwen's visual semiotics and interpreted from the standpoints of Halliday's Systematic Functional Linguistics(SFL)approach and O'Halloran's position on metaphorical constructions of meaning.Here,metaphorical manipulation and rep-resentation of visual elements in the selected cartoons are interrogated.Findings from the study show the use of semiotic resources in the portrayer of reality in the context of the seemingly intractable ASUU strikes and their consequences on aca-demic activities in Nigeria.This scholarly intervention deserves attention as it significantly contributes to the field of social semiotics through its visual represen-tation in portraying challenges faced by the educational systems in Nigeria vis-a-vis poorgovernment funding.
文摘Most children have become so addicted to TV, because there is precious little else they do for fun. Part of that enjoyment, in China, is the many cartoon programs available for young viewers, a large number of which are foreign productions. But that's all about to change. Foreign cartoons can no longer be screened during prime time viewing. Now millions of upset parents and children are questioning a new
文摘Do You Know My Woik?One night a hotel caught fire,and the peoplewho were staying in it ran out in their night clothes.Two men stood outside and looked at the fire."Before l came out,"said one,"I ran into someof the rooms and found a lot of money.People don’tthink of money when they’re afraid.When anyoneleaves paper money in a fire,the fire burns it.So Itook all the bills that I couht find.No one will bepoorer because I took them.""You don’t know my work,"said the other.
文摘Begging for DimesSon:Dad,give me a dime.Father:Son,don’t you think you’re getting too big to beforever begging for dimes?Son:I guess you’re right,Dad.Give me a dollar,will you?
文摘The Only ExampleMr.Henry Beecher entered school and found severalletters awaiting him.He opened one and found it containedthe single word"FOOL".Quietly and with seriousness he an-nounced to students the fact in these words:"I have known many an example of a man writing a let-ter and forgetting to sign his name, but this is the only exam-ple I have ever known of a man signing his name and forget-ting to write the letter."
基金The graphic design of the Cartoon Series and the publication of this manuscript have been funded by a grant provided by the UK Research and Innovation Strategic Priorities Fund and HEIF Rescaling Fund through London Metropolitan University,UK.
文摘The devastating effects of the COVID-19 pandemic have acutely shown the need for maintaining robust international and national systems for biological security and ensuring that life sciences are used only for peaceful purposes.Life science stakeholders can play an important role in safeguarding scientific and technological advances in biology and related fields against accidental or deliberate misuse,not least because they are on the frontlines of driving innovation.In this paper,we argue that enhancing awareness and understanding of the risk of deliberate disease is essential for effective biological security.We first discuss the issue of‘dual use’in science and technology as it relates to disarmament and non-proliferation of weapons of mass destruction.Second,we review how scientist engagement with dual-use risks has been addressed in the context of the Biological and Toxin Weapons Convention(BTWC).Third,we report on the development of an innovative awarenessraising tool,a cartoon series,that can be used for engaging life science stakeholders with BTWC issues.Finally,we outline a set of practical considerations for promoting sustainable life science engagement with the BTWC.
基金supported by National Natural Science Foundation of China (Nos. 61272293 and 61103120)Shenzhen Basic Research Project (No. JCYJ20120619152326448)+2 种基金Shenzhen Nanshan Innovative Institution Establishment Fund (No. KC2013ZDZJ0007A)the Research Grants Council of the Hong Kong Special Administrative Region under RGC General Research Fund (No. CUHK 417913)Guangzhou Novo Program of Science & Technology (No. 0501-330)
文摘Cartoons are a worldwide popular visual entertainment medium with a long history. Nowadays,with the boom of electronic devices, there is an increasing need to digitize old classic cartoons as a basis for further editing, including deformation,colorization, etc. To perform such editing, it is essential to extract the structure lines within cartoon images.Traditional edge detection methods are mainly based on gradients. These methods perform poorly in the face of compression artifacts and spatially-varying line colors,which cause gradient values to become unreliable. This paper presents the first approach to extract structure lines in cartoons based on regions. Our method starts by segmenting an image into regions, and then classifies them as edge regions and non-edge regions. Our second main contribution comprises three measures to estimate the likelihood of a region being a non-edge region.These measure darkness, local contrast, and shape.Since the likelihoods become unreliable as regions become smaller, we further classify regions using both likelihoods and the relationships to neighboring regions via a graph-cut formulation. Our method has been evaluated on a wide variety of cartoon images, and convincing results are obtained in all cases.
文摘The centric position of the body in cognition has long been the paradigm for theories of embodiment; its research, however, has two limitations: 1) many studies have primarily worked on a specific, single dimension of the body, lacking a dynamic and comprehensive perspective; 2) the multimodal nature of embodied cognition has been tremendously underestimated, particularly in terms of the multimodal representation of physical signs. In view of the above two problems, the present research, with news cartoons as its research objects, takes a multi-layered perspective to view the semiosis of physical signs, for the role of the "body"amid the semiotization process might differ on different layers of representation. The author argues that: 1) on the formal layer, physical signs, which depend on perceptual senses, are realized by virtue of embodied simulation, which can help divert interpreters' attention from the form to the cognitive content; 2) on the conceptual layer, the semiotization of physical signs can be considered as a modularization process, absorbing modules from different sources and then being integrated as a whole, which can be explained by metonymy and multimodal metaphor theory; 3) on the contextual layer, the referent of the "body" is believed to be gradually replaced by its contextual symbolic meaning, which, by nature, arises from the reinterpretation of physical signs in specific cognitive situations.
文摘Visual illustration transformation from real-world to cartoon images is one of the famous and challenging tasks in computer vision.Image-to-image translation from real-world to cartoon domains poses issues such as a lack of paired training samples,lack of good image translation,low feature extraction from the previous domain images,and lack of high-quality image translation from the traditional generator algorithms.To solve the above-mentioned issues,paired independent model,high-quality dataset,Bayesian-based feature extractor,and an improved generator must be proposed.In this study,we propose a high-quality dataset to reduce the effect of paired training samples on the model’s performance.We use a Bayesian Very Deep Convolutional Network(VGG)-based feature extractor to improve the performance of the standard feature extractor because Bayesian inference regu-larizes weights well.The generator from the Cartoon Generative Adversarial Network(GAN)is modified by introducing a depthwise convolution layer and channel attention mechanism to improve the performance of the original generator.We have used the Fréchet inception distance(FID)score and user preference score to evaluate the performance of the model.The FID scores obtained for the generated cartoon and real-world images are 107 and 76 for the TCC style,and 137 and 57 for the Hayao style,respectively.User preference score is also calculated to evaluate the quality of generated images and our proposed model acquired a high preference score compared to other models.We achieved stunning results in producing high-quality cartoon images,demonstrating the proposed model’s effectiveness in transferring style between authentic images and cartoon images.
