Pub Date : 2021-07-16DOI: 10.1109/PRML52754.2021.9520726
Wenming Han, Fangmei Chen, Fuming Sun
Facial beauty is related to different kinds of features, such as geometry, texture and expression. Geometric features are the most investigated ones, because 1) they have clear and interpretable definitions; 2) they do not change with face make-up, illumination and resolution; and 3) they can be used to guide the aesthetic plastic surgeries. Due to the high cost of 3D scanning, most existing works focus on 2D geometric features extracted from frontal face images. However, the profile information is neglected, which also plays an important role in facial beauty judgment. In this paper, we reconstruct 3D faces from 2D images using recent monocular 3D face reconstruction method. Then 22 anatomical landmarks are defined on the 3D face, and based on which totally 51 geometric features are extracted. Finally, we design experiments to evaluate the effectiveness of these features. The results show that ratio features are the most influential ones, and lips also affect facial beauty. Comparison between Asian and Caucasian shows that there are significant differences between different ethnic groups. For Asian faces, an angle feature related to face width and nose height has the highest ranking. For the Caucasian groups, the top-ranked features are length and ratio features, and the lip region plays an important role.
{"title":"Facial Beauty Study Based on 3D Geometric Features","authors":"Wenming Han, Fangmei Chen, Fuming Sun","doi":"10.1109/PRML52754.2021.9520726","DOIUrl":"https://doi.org/10.1109/PRML52754.2021.9520726","url":null,"abstract":"Facial beauty is related to different kinds of features, such as geometry, texture and expression. Geometric features are the most investigated ones, because 1) they have clear and interpretable definitions; 2) they do not change with face make-up, illumination and resolution; and 3) they can be used to guide the aesthetic plastic surgeries. Due to the high cost of 3D scanning, most existing works focus on 2D geometric features extracted from frontal face images. However, the profile information is neglected, which also plays an important role in facial beauty judgment. In this paper, we reconstruct 3D faces from 2D images using recent monocular 3D face reconstruction method. Then 22 anatomical landmarks are defined on the 3D face, and based on which totally 51 geometric features are extracted. Finally, we design experiments to evaluate the effectiveness of these features. The results show that ratio features are the most influential ones, and lips also affect facial beauty. Comparison between Asian and Caucasian shows that there are significant differences between different ethnic groups. For Asian faces, an angle feature related to face width and nose height has the highest ranking. For the Caucasian groups, the top-ranked features are length and ratio features, and the lip region plays an important role.","PeriodicalId":429603,"journal":{"name":"2021 IEEE 2nd International Conference on Pattern Recognition and Machine Learning (PRML)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128296253","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-16DOI: 10.1109/PRML52754.2021.9520387
Qingqing Zhao, Yue Xiao, Yunfei Long
Abusive language detection serves to ensure a compelling user experience via high-quality content. Different sub-categories of abusive language are closely related, with most aggressive comments containing personal attacks and toxic content and vice versa. We set a multi-task learning framework to detect different types of abusive content in a mental health forum to address this feature. Each classification task is treated as a subclass in a multi-class classification problem, with shared knowledge used for three related tasks: attack, aggression, and toxicity. Experimental results on three sub-types of Wikipedia abusive language datasets show that our framework can improve the net F1-score by 7.1%, 5.6%, and 2.7% in the attack, aggressive, and toxicity detection. Our experiments identified multi tasking framework act as an effective method in abusive language detection.
{"title":"Multi-task CNN for Abusive Language Detection","authors":"Qingqing Zhao, Yue Xiao, Yunfei Long","doi":"10.1109/PRML52754.2021.9520387","DOIUrl":"https://doi.org/10.1109/PRML52754.2021.9520387","url":null,"abstract":"Abusive language detection serves to ensure a compelling user experience via high-quality content. Different sub-categories of abusive language are closely related, with most aggressive comments containing personal attacks and toxic content and vice versa. We set a multi-task learning framework to detect different types of abusive content in a mental health forum to address this feature. Each classification task is treated as a subclass in a multi-class classification problem, with shared knowledge used for three related tasks: attack, aggression, and toxicity. Experimental results on three sub-types of Wikipedia abusive language datasets show that our framework can improve the net F1-score by 7.1%, 5.6%, and 2.7% in the attack, aggressive, and toxicity detection. Our experiments identified multi tasking framework act as an effective method in abusive language detection.","PeriodicalId":429603,"journal":{"name":"2021 IEEE 2nd International Conference on Pattern Recognition and Machine Learning (PRML)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134246238","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-16DOI: 10.1109/PRML52754.2021.9520702
Ma Xueli, Mijit Ablimit, A. Hamdulla
Aiming at the problems of low recognition rate and uneven distribution of language information in language identification tasks, a language recognition method based on the CNN-Bigru-Attention model is proposed. This method first extracts the spectrogram of audio signals and converts it into a gray-scale spectrogram as input, then uses CNN (convolutional neural network) to capture the local features, and extracts the temporal features through the Bigru (Bidirectional gated recurrent unit), and then local features and temporal features are passed to the attention mechanism layer to focus on the information related to the language features and suppress useless information. Finally the classes of language is output through the fully connected layer. Experiments on the Common voice dataset show that the method has achieved good results and improves the performance of language identification.
{"title":"Multiclass Language Identification Using CNN-Bigru-Attention Model on Spectrogram of Audio Signals","authors":"Ma Xueli, Mijit Ablimit, A. Hamdulla","doi":"10.1109/PRML52754.2021.9520702","DOIUrl":"https://doi.org/10.1109/PRML52754.2021.9520702","url":null,"abstract":"Aiming at the problems of low recognition rate and uneven distribution of language information in language identification tasks, a language recognition method based on the CNN-Bigru-Attention model is proposed. This method first extracts the spectrogram of audio signals and converts it into a gray-scale spectrogram as input, then uses CNN (convolutional neural network) to capture the local features, and extracts the temporal features through the Bigru (Bidirectional gated recurrent unit), and then local features and temporal features are passed to the attention mechanism layer to focus on the information related to the language features and suppress useless information. Finally the classes of language is output through the fully connected layer. Experiments on the Common voice dataset show that the method has achieved good results and improves the performance of language identification.","PeriodicalId":429603,"journal":{"name":"2021 IEEE 2nd International Conference on Pattern Recognition and Machine Learning (PRML)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116736870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-05-24DOI: 10.1101/2021.05.20.21257539
T. Oladunni, Justin Stephan, Lala Aicha Coulibaly
SARS-Cov-2 is not to be introduced anymore. The global pandemic that originated more than a year ago in Wuhan, China has claimed thousands of lives. Since the arrival of this plague, face mask has become part of our dressing code. The focus of this study is to design, develop and evaluate a COVID-19 fatality rate classifier at the county level. The proposed model predicts fatality rate as low, moderate, or high. This will help government and decision makers to improve mitigation strategy and provide measures to reduce the spread of the disease. Tourists and travelers will also find the work useful in planning of trips. Dataset for the experiment contained imbalanced fatality levels. Therefore, class imbalance was offset using SMOTE. Evaluation of the proposed model was based on precision, F1 score, accuracy, and ROC curve. Five learning algorithms were trained and evaluated. Experimental results showed the Bagging model has the best performance.
{"title":"COVID-19 Fatality Rate Classification Using Synthetic Minority Oversampling Technique (SMOTE) for Imbalanced Class","authors":"T. Oladunni, Justin Stephan, Lala Aicha Coulibaly","doi":"10.1101/2021.05.20.21257539","DOIUrl":"https://doi.org/10.1101/2021.05.20.21257539","url":null,"abstract":"SARS-Cov-2 is not to be introduced anymore. The global pandemic that originated more than a year ago in Wuhan, China has claimed thousands of lives. Since the arrival of this plague, face mask has become part of our dressing code. The focus of this study is to design, develop and evaluate a COVID-19 fatality rate classifier at the county level. The proposed model predicts fatality rate as low, moderate, or high. This will help government and decision makers to improve mitigation strategy and provide measures to reduce the spread of the disease. Tourists and travelers will also find the work useful in planning of trips. Dataset for the experiment contained imbalanced fatality levels. Therefore, class imbalance was offset using SMOTE. Evaluation of the proposed model was based on precision, F1 score, accuracy, and ROC curve. Five learning algorithms were trained and evaluated. Experimental results showed the Bagging model has the best performance.","PeriodicalId":429603,"journal":{"name":"2021 IEEE 2nd International Conference on Pattern Recognition and Machine Learning (PRML)","volume":"30 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120839221","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：