Aiming at the challenges associated with the absence of a labeled dataset for Yi characters and the complexity of Yi character detection and recognition,we present a deep learning-based approach for Yi character detec...Aiming at the challenges associated with the absence of a labeled dataset for Yi characters and the complexity of Yi character detection and recognition,we present a deep learning-based approach for Yi character detection and recognition.In the detection stage,an improved Differentiable Binarization Network(DBNet)framework is introduced to detect Yi characters,in which the Omni-dimensional Dynamic Convolution(ODConv)is combined with the ResNet-18 feature extraction module to obtain multi-dimensional complementary features,thereby improving the accuracy of Yi character detection.Then,the feature pyramid network fusion module is used to further extract Yi character image features,improving target recognition at different scales.Further,the previously generated feature map is passed through a head network to produce two maps:a probability map and an adaptive threshold map of the same size as the original map.These maps are then subjected to a differentiable binarization process,resulting in an approximate binarization map.This map helps to identify the boundaries of the text boxes.Finally,the text detection box is generated after the post-processing stage.In the recognition stage,an improved lightweight MobileNetV3 framework is used to recognize the detect character regions,where the original Squeeze-and-Excitation(SE)block is replaced by the efficient Shuffle Attention(SA)that integrates spatial and channel attention,improving the accuracy of Yi characters recognition.Meanwhile,the use of depth separable convolution and reversible residual structure can reduce the number of parameters and computation of the model,so that the model can better understand the contextual information and improve the accuracy of text recognition.The experimental results illustrate that the proposed method achieves good results in detecting and recognizing Yi characters,with detection and recognition accuracy rates of 97.5%and 96.8%,respectively.And also,we have compared the detection and recognition algorithms proposed in this paper with other typical algorithms.In these comparisons,the proposed model achieves better detection and recognition results with a certain reliability.展开更多
The renowned translator Yang Yi passed away in 2023.Many scholars argue that,influenced by their biological gender,female translators often employ translation methods in adherence to feminist translation or reflect ch...The renowned translator Yang Yi passed away in 2023.Many scholars argue that,influenced by their biological gender,female translators often employ translation methods in adherence to feminist translation or reflect characteristics typical of female translators.This study examines the translation of Wuthering Heights by Yang Yi,focusing on whether there is a definite influence of gender on translator behavior.While existing literature primarily analyzes Yang Yi’s work through a feminist lens,this research takes a broader approach.By considering the translator’s social background and translation practice,this paper challenges the assumption that her work strictly aligns with feminist translation theories.Instead,this study emphasizes the importance of considering diverse factors when interpreting translated works,moving beyond a singular gender-based standpoint.展开更多
Liangshan Prefecture in Sichuan province, China, has a high prevalence of HIV infection, which is reflective of a change in the mode of transmission from injection drug use （IDU） to heterosexual intercourse. However...Liangshan Prefecture in Sichuan province, China, has a high prevalence of HIV infection, which is reflective of a change in the mode of transmission from injection drug use （IDU） to heterosexual intercourse. However, few studies focus on HIV-related heterosexual risk behaviours among the majority Yi population. The objectives of this study were to explore the characteristics of an egocentric sexual network and estimate the prevalence of casual sexual behaviour. Yi villagers （n= 108）, aged 15-35 years, who reported having had sex within the previous year were interviewed as to their sexual behaviours and networks. In-depth interviews and focus group discussions provided supplementary information on sexual norms. Logistic regression analysis was used to calculate unadjusted odds ratios （ORs） and 95% confidence intervals （CIs）. Most of the respondents reported having had casual sex at some time in their life, and 66.7% reported multiple sexual partnerships. Only 21.3% reported ever having used a condom. During the study year, a total of 137 partners were involved in 153 sexual partnerships. Among the reported sexual partnerships, 67.3% originated from a casual sexual relationship. For network members in components of size ≥3, 56,9% were involved in concurrent sexual partnerships. Having never been married （OR： 2.11; 95% CI： 1.03-4.33） and younger age （OR： 0.89; 95% CI： 0.83-0.95） were both associated with being in a component of size ≥3. Size （OR： 2.99; 95% Ch 1.17-7.66）, pair （OR： 0.54; 95% Ch 0.039-0.74）, the number of weak components of the egocentric sexual network （OR- 30.04; 95% Ch 6.47-139.46） and gender （OR. 0. 19; 95% Ch. 0.06-0.67） were all associated with being in concurrent sexual partnerships. HIV-related interventions for the Yi ethnic minority in Sichuan province must therefore address concurrent sexual partnerships and promote condom use.展开更多
基金The work was supported by the National Natural Science Foundation of China(61972062,62306060)the Basic Research Project of Liaoning Province(2023JH2/101300191)+1 种基金the Liaoning Doctoral Research Start-Up Fund Project(2023-BS-078)the Dalian Academy of Social Sciences(2023dlsky028).
文摘Aiming at the challenges associated with the absence of a labeled dataset for Yi characters and the complexity of Yi character detection and recognition,we present a deep learning-based approach for Yi character detection and recognition.In the detection stage,an improved Differentiable Binarization Network(DBNet)framework is introduced to detect Yi characters,in which the Omni-dimensional Dynamic Convolution(ODConv)is combined with the ResNet-18 feature extraction module to obtain multi-dimensional complementary features,thereby improving the accuracy of Yi character detection.Then,the feature pyramid network fusion module is used to further extract Yi character image features,improving target recognition at different scales.Further,the previously generated feature map is passed through a head network to produce two maps:a probability map and an adaptive threshold map of the same size as the original map.These maps are then subjected to a differentiable binarization process,resulting in an approximate binarization map.This map helps to identify the boundaries of the text boxes.Finally,the text detection box is generated after the post-processing stage.In the recognition stage,an improved lightweight MobileNetV3 framework is used to recognize the detect character regions,where the original Squeeze-and-Excitation(SE)block is replaced by the efficient Shuffle Attention(SA)that integrates spatial and channel attention,improving the accuracy of Yi characters recognition.Meanwhile,the use of depth separable convolution and reversible residual structure can reduce the number of parameters and computation of the model,so that the model can better understand the contextual information and improve the accuracy of text recognition.The experimental results illustrate that the proposed method achieves good results in detecting and recognizing Yi characters,with detection and recognition accuracy rates of 97.5%and 96.8%,respectively.And also,we have compared the detection and recognition algorithms proposed in this paper with other typical algorithms.In these comparisons,the proposed model achieves better detection and recognition results with a certain reliability.
文摘The renowned translator Yang Yi passed away in 2023.Many scholars argue that,influenced by their biological gender,female translators often employ translation methods in adherence to feminist translation or reflect characteristics typical of female translators.This study examines the translation of Wuthering Heights by Yang Yi,focusing on whether there is a definite influence of gender on translator behavior.While existing literature primarily analyzes Yang Yi’s work through a feminist lens,this research takes a broader approach.By considering the translator’s social background and translation practice,this paper challenges the assumption that her work strictly aligns with feminist translation theories.Instead,this study emphasizes the importance of considering diverse factors when interpreting translated works,moving beyond a singular gender-based standpoint.
文摘Liangshan Prefecture in Sichuan province, China, has a high prevalence of HIV infection, which is reflective of a change in the mode of transmission from injection drug use （IDU） to heterosexual intercourse. However, few studies focus on HIV-related heterosexual risk behaviours among the majority Yi population. The objectives of this study were to explore the characteristics of an egocentric sexual network and estimate the prevalence of casual sexual behaviour. Yi villagers （n= 108）, aged 15-35 years, who reported having had sex within the previous year were interviewed as to their sexual behaviours and networks. In-depth interviews and focus group discussions provided supplementary information on sexual norms. Logistic regression analysis was used to calculate unadjusted odds ratios （ORs） and 95% confidence intervals （CIs）. Most of the respondents reported having had casual sex at some time in their life, and 66.7% reported multiple sexual partnerships. Only 21.3% reported ever having used a condom. During the study year, a total of 137 partners were involved in 153 sexual partnerships. Among the reported sexual partnerships, 67.3% originated from a casual sexual relationship. For network members in components of size ≥3, 56,9% were involved in concurrent sexual partnerships. Having never been married （OR： 2.11; 95% CI： 1.03-4.33） and younger age （OR： 0.89; 95% CI： 0.83-0.95） were both associated with being in a component of size ≥3. Size （OR： 2.99; 95% Ch 1.17-7.66）, pair （OR： 0.54; 95% Ch 0.039-0.74）, the number of weak components of the egocentric sexual network （OR- 30.04; 95% Ch 6.47-139.46） and gender （OR. 0. 19; 95% Ch. 0.06-0.67） were all associated with being in concurrent sexual partnerships. HIV-related interventions for the Yi ethnic minority in Sichuan province must therefore address concurrent sexual partnerships and promote condom use.
