Pub Date : 2020-09-26DOI: 10.1007/978-3-030-71804-6_1
Slim Hamdi, H. Snoussi, M. Abid
{"title":"Fine-Tuning a Pre-trained CAE for Deep One Class Anomaly Detection in Video Footage","authors":"Slim Hamdi, H. Snoussi, M. Abid","doi":"10.1007/978-3-030-71804-6_1","DOIUrl":"https://doi.org/10.1007/978-3-030-71804-6_1","url":null,"abstract":"","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47851462","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 : 2020-04-01DOI: 10.16451/J.CNKI.ISSN1003-6059.202004002
薛峰, 刘凯, 王东, 张浩博
In singular value decomposition++(SVD++),inner product of user and item feature vector is regarded as user′s rating of items.However,inner product cannot capture the high-order nonlinear relationship between the user and the item.In addition,the contribution of different interactive items cannot be distinguished when user′s implicit feedback is incorporated in SVD++.A recommendation algorithm based on deep neural network and weighted implicit feedback is proposed to solve the two problems.Deep neural network is adopted to model the relationship between the user and the object and attention mechanism is utilized to calculate the weight of historical interactive items in modeling user′s implicit feedback.Experiments on public datasets verify the effectiveness of the proposed algorithm.
{"title":"Personalized Recommendation Algorithm Based on Deep Neural Network and Weighted Implicit Feedback","authors":"薛峰, 刘凯, 王东, 张浩博","doi":"10.16451/J.CNKI.ISSN1003-6059.202004002","DOIUrl":"https://doi.org/10.16451/J.CNKI.ISSN1003-6059.202004002","url":null,"abstract":"In singular value decomposition++(SVD++),inner product of user and item feature vector is regarded as user′s rating of items.However,inner product cannot capture the high-order nonlinear relationship between the user and the item.In addition,the contribution of different interactive items cannot be distinguished when user′s implicit feedback is incorporated in SVD++.A recommendation algorithm based on deep neural network and weighted implicit feedback is proposed to solve the two problems.Deep neural network is adopted to model the relationship between the user and the object and attention mechanism is utilized to calculate the weight of historical interactive items in modeling user′s implicit feedback.Experiments on public datasets verify the effectiveness of the proposed algorithm.","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43112688","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 : 2020-04-01DOI: 10.16451/J.CNKI.ISSN1003-6059.202004005
付利华, 卢中山, 孙晓威, 赵宇, 张博
While low-resolution face images are reconstructed via deep learning based super-resolution reconstruction method,some problems emerge,such as blurred reconstructed images and obvious difference between reconstructed images and real images.Aiming at these problems,a face super-resolution reconstruction method fusing reference image is proposed to reconstruct low-resolution human face images effectively.The multi-scale features of reference image are extracted by reference image feature extraction subnet to retain the detail information of key parts and remove the redundant information,such as facial contour and facial expression.Based on the multi-scale features of reference image,the step-by-step super-resolution main network fills the features to low-resolution face image step by step.Finally,the high-resolution face image is generated.Experiments on datasets indicate that the proposed method reconstructs low-resolution face images effectively with good robustness.
{"title":"Face Super-Resolution Reconstruction Method Fusing Reference Image","authors":"付利华, 卢中山, 孙晓威, 赵宇, 张博","doi":"10.16451/J.CNKI.ISSN1003-6059.202004005","DOIUrl":"https://doi.org/10.16451/J.CNKI.ISSN1003-6059.202004005","url":null,"abstract":"While low-resolution face images are reconstructed via deep learning based super-resolution reconstruction method,some problems emerge,such as blurred reconstructed images and obvious difference between reconstructed images and real images.Aiming at these problems,a face super-resolution reconstruction method fusing reference image is proposed to reconstruct low-resolution human face images effectively.The multi-scale features of reference image are extracted by reference image feature extraction subnet to retain the detail information of key parts and remove the redundant information,such as facial contour and facial expression.Based on the multi-scale features of reference image,the step-by-step super-resolution main network fills the features to low-resolution face image step by step.Finally,the high-resolution face image is generated.Experiments on datasets indicate that the proposed method reconstructs low-resolution face images effectively with good robustness.","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44010598","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 : 2020-04-01DOI: 10.16451/J.CNKI.ISSN1003-6059.202004001
王晓莉, 叶东毅
Long tail effect and excessive out-of-vocabulary(OOV)words in social media texts result in severe feature sparsity and reduce classification accuracy.To solve the problem,a social media text classification method based on character-word feature self-attention learning is proposed.Global features are constructed at the character level to learn attention weight distribution,and the existing multi-head attention mechanism is improved to reduce parameter scale and computational complexity.To further analyze character-word feature fusion,OOV sensitivity is proposed to measure the impact of OOV words on different types of features.Experiments on several social media text classification tasks indicate that the effectiveness and classification accuracy of the proposed method are obviously improved in terms of fusing word features and character features.Moreover,the quantitative results of OOV vocabulary sensitivity index verify the feasiblity and effectiveness of the proposed method.
{"title":"Social Media Text Classification Method Based on Character-Word Feature Self-attention Learning","authors":"王晓莉, 叶东毅","doi":"10.16451/J.CNKI.ISSN1003-6059.202004001","DOIUrl":"https://doi.org/10.16451/J.CNKI.ISSN1003-6059.202004001","url":null,"abstract":"Long tail effect and excessive out-of-vocabulary(OOV)words in social media texts result in severe feature sparsity and reduce classification accuracy.To solve the problem,a social media text classification method based on character-word feature self-attention learning is proposed.Global features are constructed at the character level to learn attention weight distribution,and the existing multi-head attention mechanism is improved to reduce parameter scale and computational complexity.To further analyze character-word feature fusion,OOV sensitivity is proposed to measure the impact of OOV words on different types of features.Experiments on several social media text classification tasks indicate that the effectiveness and classification accuracy of the proposed method are obviously improved in terms of fusing word features and character features.Moreover,the quantitative results of OOV vocabulary sensitivity index verify the feasiblity and effectiveness of the proposed method.","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47533068","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 : 2020-04-01DOI: 10.16451/J.CNKI.ISSN1003-6059.202004006
陈浩, 李永强, 冯远静
The reasoning ability of most existing dynamic knowledge map reasoning methods under the same time and multiple relationships is limited.Aiming at this problem,a method of dynamic knowledge graph inference based on multi-relational cyclic events(Multi-Net)is proposed.The improved multi-relational proximity aggregator is employed to fuse target entity neighborhood information to obtain more accurate representation of entity neighborhood vector,and Multi-Net is simplified by optimizing information fusion,and the ability to handle the conflict of relations between two entities in a specific scope is improved by adding the relationship prediction task to Multi-Net.Experiments of entity prediction and relationship prediction on large real datasets indicate that Multi-Net improves the reasoning ability of dynamic knowledge maps effectively.
{"title":"Dynamic Knowledge Graph Inference Based on Multiple Relational Cyclic Events","authors":"陈浩, 李永强, 冯远静","doi":"10.16451/J.CNKI.ISSN1003-6059.202004006","DOIUrl":"https://doi.org/10.16451/J.CNKI.ISSN1003-6059.202004006","url":null,"abstract":"The reasoning ability of most existing dynamic knowledge map reasoning methods under the same time and multiple relationships is limited.Aiming at this problem,a method of dynamic knowledge graph inference based on multi-relational cyclic events(Multi-Net)is proposed.The improved multi-relational proximity aggregator is employed to fuse target entity neighborhood information to obtain more accurate representation of entity neighborhood vector,and Multi-Net is simplified by optimizing information fusion,and the ability to handle the conflict of relations between two entities in a specific scope is improved by adding the relationship prediction task to Multi-Net.Experiments of entity prediction and relationship prediction on large real datasets indicate that Multi-Net improves the reasoning ability of dynamic knowledge maps effectively.","PeriodicalId":34917,"journal":{"name":"模式识别与人工智能","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41403201","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：