Pub Date : 2018-04-01DOI: 10.1109/ISACV.2018.8354031
Saloua El Motaki, Yahyaouy Ali, H. Gualous, J. Sabor
Ensuring an adaptable and interactive tools to analyze data objects is an advisable objective of machine learning algorithms. Many methods exist, and new methods, or improvements in existing ones are proposed regularly to deal with a variety of problems in different areas. We develop a variant of the well-known Possibilistic Fuzzy c-Means Clustering algorithm PFCM that takes into account the observer-biased framework, Possibilistic fuzzy c-means with focal point PFCMFP. the accuracy of the proposed method is verified by cluster validity measures. The experimental results have shown that the accuracy of the new method increases significantly, compared to the initial PFCM algorithm. To elaborate this study, we have used a dataset of individual household electric power consumption, that is accessed publicly at the UCI Machine Learning Repository.
{"title":"Possibilistic fuzzy C-means clustering under observer-biased framework","authors":"Saloua El Motaki, Yahyaouy Ali, H. Gualous, J. Sabor","doi":"10.1109/ISACV.2018.8354031","DOIUrl":"https://doi.org/10.1109/ISACV.2018.8354031","url":null,"abstract":"Ensuring an adaptable and interactive tools to analyze data objects is an advisable objective of machine learning algorithms. Many methods exist, and new methods, or improvements in existing ones are proposed regularly to deal with a variety of problems in different areas. We develop a variant of the well-known Possibilistic Fuzzy c-Means Clustering algorithm PFCM that takes into account the observer-biased framework, Possibilistic fuzzy c-means with focal point PFCMFP. the accuracy of the proposed method is verified by cluster validity measures. The experimental results have shown that the accuracy of the new method increases significantly, compared to the initial PFCM algorithm. To elaborate this study, we have used a dataset of individual household electric power consumption, that is accessed publicly at the UCI Machine Learning Repository.","PeriodicalId":184662,"journal":{"name":"2018 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129491386","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 : 2018-04-01DOI: 10.1109/ISACV.2018.8369043
Yuxi Hong, Chen Ling, Zuochang Ye
Soccer video scene and event classification are two essential tasks for the soccer video semantic analysis and have attracted many interests of researchers because of their importance and practicability. However most proposed methods solve these two tasks separately. In order to solve two tasks at the same time and improve the efficiency of video processing, we treat them as one end-to-end classification task. We introduce a new Soccer Video Scene and Event Dataset (SVSED) with six categories from the scenes and events, which contains 600 video clips. Then, we show that frame features extracted from pretrained CNN model of different categories are separable in 3-D space. Finally, we construct a CNN model for the classification task and deep transfer learning method is used for optimizing classification task result considering relative small training datasets. We fine-tuned several state-of-art CNN models and achieves accuracy above 89% within several minutes training.
{"title":"End-to-end soccer video scene and event classification with deep transfer learning","authors":"Yuxi Hong, Chen Ling, Zuochang Ye","doi":"10.1109/ISACV.2018.8369043","DOIUrl":"https://doi.org/10.1109/ISACV.2018.8369043","url":null,"abstract":"Soccer video scene and event classification are two essential tasks for the soccer video semantic analysis and have attracted many interests of researchers because of their importance and practicability. However most proposed methods solve these two tasks separately. In order to solve two tasks at the same time and improve the efficiency of video processing, we treat them as one end-to-end classification task. We introduce a new Soccer Video Scene and Event Dataset (SVSED) with six categories from the scenes and events, which contains 600 video clips. Then, we show that frame features extracted from pretrained CNN model of different categories are separable in 3-D space. Finally, we construct a CNN model for the classification task and deep transfer learning method is used for optimizing classification task result considering relative small training datasets. We fine-tuned several state-of-art CNN models and achieves accuracy above 89% within several minutes training.","PeriodicalId":184662,"journal":{"name":"2018 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130417544","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 : 2018-04-01DOI: 10.1109/ISACV.2018.8354055
M. Ameur, N. Idrissi, C. Daoui
Over the last years, image segmentation has evolved from a sub-discipline of computer science to a technique widely used in medical imaging, automated object recognition, and remote sensing. In this work, we present a recently Markovian model of image segmentation called Triplet Markov Chain with Independent Noise (TMC-IN), in this model, it assumes that its hidden process X is non-stationary. TMC-IN is used in this to segment some textured grey level and color images. To estimate the parameters, we use the iterative algorithm EM (Expectation-Maximization) and we apply MPM (Marginal Posteriori Mode) algorithm to estimate the result segmented image. In addition, we compare the obtained results by this model with those obtained by the stationary Hidden Markov Chain with Independent Noise (HMC-IN) model. Experimental results show that TMC-IN outperforms HMC-IN in all experiments.
{"title":"Triplet Markov chain in images segmentation","authors":"M. Ameur, N. Idrissi, C. Daoui","doi":"10.1109/ISACV.2018.8354055","DOIUrl":"https://doi.org/10.1109/ISACV.2018.8354055","url":null,"abstract":"Over the last years, image segmentation has evolved from a sub-discipline of computer science to a technique widely used in medical imaging, automated object recognition, and remote sensing. In this work, we present a recently Markovian model of image segmentation called Triplet Markov Chain with Independent Noise (TMC-IN), in this model, it assumes that its hidden process X is non-stationary. TMC-IN is used in this to segment some textured grey level and color images. To estimate the parameters, we use the iterative algorithm EM (Expectation-Maximization) and we apply MPM (Marginal Posteriori Mode) algorithm to estimate the result segmented image. In addition, we compare the obtained results by this model with those obtained by the stationary Hidden Markov Chain with Independent Noise (HMC-IN) model. Experimental results show that TMC-IN outperforms HMC-IN in all experiments.","PeriodicalId":184662,"journal":{"name":"2018 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123866737","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 : 2018-04-01DOI: 10.1109/ISACV.2018.8354052
I. Maach, Ahmed Azough, M. Meknassi
With the development of new approaches of interaction, virtual reality is distinguished by its ability to provide an unprecedented immersion for the user. Imperial cities, many of whose monuments remain out of reach for a large majority of tourists, are certainly in need of experimenting and deploying virtual tours to promote their tourism. This paper presents the work made to develop a use case of virtual reality in an interactive and multi-platform visit to a historical monument of the city of Fez. The aim of this work is to create 360-degree virtual tours of important or inaccessible areas such as the case of the mausoleum of Moulay Idriss, which is not accessible to non-muslims. using the most recent tools along with best practices and 3D rendering techniques.
{"title":"Development of a use case for virtual reality to visit a historical monument","authors":"I. Maach, Ahmed Azough, M. Meknassi","doi":"10.1109/ISACV.2018.8354052","DOIUrl":"https://doi.org/10.1109/ISACV.2018.8354052","url":null,"abstract":"With the development of new approaches of interaction, virtual reality is distinguished by its ability to provide an unprecedented immersion for the user. Imperial cities, many of whose monuments remain out of reach for a large majority of tourists, are certainly in need of experimenting and deploying virtual tours to promote their tourism. This paper presents the work made to develop a use case of virtual reality in an interactive and multi-platform visit to a historical monument of the city of Fez. The aim of this work is to create 360-degree virtual tours of important or inaccessible areas such as the case of the mausoleum of Moulay Idriss, which is not accessible to non-muslims. using the most recent tools along with best practices and 3D rendering techniques.","PeriodicalId":184662,"journal":{"name":"2018 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114372054","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 : 2018-04-01DOI: 10.1109/ISACV.2018.8354045
Fatima Zahra Ouadiay, Hamza Bouftaih, E. Bouyakhf, M. M. Himmi
Nowadays deep learning is considered as a trendy technique in the computer vision domain. It becomes a pioneer in its main tasks as object classification, object localization, and object detection. Therefore it gave amazing results and records. In this paper, we propose a new approach to identify and localize objects, simultaneously, in a given scene using Convolutional Neural Networks (CNNs). We propose an end-to-end approach for object detection and pose estimation by formulating bounding boxes containing the targeted object and their pose. Our method is based on two main steps, i) produce Bounding boxes on the training images for generating the pose coordinates of each object in the scene and, ii) detect and localize simultaneously each object present in image during the testing step. The contribution performance is assessed on two datasets, Washington RGB scene dataset and LIMIARF dataset that is constructed in our laboratory. We demonstrate that our proposal is able to obtain high precision and reasonable recall levels.
{"title":"Simultaneous object detection and localization using convolutional neural networks","authors":"Fatima Zahra Ouadiay, Hamza Bouftaih, E. Bouyakhf, M. M. Himmi","doi":"10.1109/ISACV.2018.8354045","DOIUrl":"https://doi.org/10.1109/ISACV.2018.8354045","url":null,"abstract":"Nowadays deep learning is considered as a trendy technique in the computer vision domain. It becomes a pioneer in its main tasks as object classification, object localization, and object detection. Therefore it gave amazing results and records. In this paper, we propose a new approach to identify and localize objects, simultaneously, in a given scene using Convolutional Neural Networks (CNNs). We propose an end-to-end approach for object detection and pose estimation by formulating bounding boxes containing the targeted object and their pose. Our method is based on two main steps, i) produce Bounding boxes on the training images for generating the pose coordinates of each object in the scene and, ii) detect and localize simultaneously each object present in image during the testing step. The contribution performance is assessed on two datasets, Washington RGB scene dataset and LIMIARF dataset that is constructed in our laboratory. We demonstrate that our proposal is able to obtain high precision and reasonable recall levels.","PeriodicalId":184662,"journal":{"name":"2018 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130116911","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 : 2018-04-01DOI: 10.1109/ISACV.2018.8354060
François Kasséné Gomis, M. Camara, I. Diop, S. M. Farssi, K. Tall, Birahime Diouf
Steganography is the art of hiding information in a cover (carrier) medium to obtain a stego-medium without any suspicion from a viewer who see that last one. Steganalysis is the opposite discipline. Its goal is to detect the presence of hidden information from a stego-medium. The medium can be an audio, video or image file. In this work, we focus on image file medium. Universal steganalysis is the detection of hidden data without knowing the algorithm used to embed the message inside the carrier. There are some methods of classification between stego and cover medium proposed in literature. In this paper, we propose a new universal steganalysis method based on unsupervised and supervised machine learning algorithms. Our method reduces the cover-source mismatch problem in the first stage and uses multiple linear regression in the second stage to predict the relative payload (in terms of bits per non-zero AC DCT coefficient) of the embedded message. With this measure, we can easily calculate the length of the embedded message. In our experiments, we got reliable models in all the clusters to predict the relative payload for cover-images and stego-images.
{"title":"Multiple linear regression for universal steganalysis of images","authors":"François Kasséné Gomis, M. Camara, I. Diop, S. M. Farssi, K. Tall, Birahime Diouf","doi":"10.1109/ISACV.2018.8354060","DOIUrl":"https://doi.org/10.1109/ISACV.2018.8354060","url":null,"abstract":"Steganography is the art of hiding information in a cover (carrier) medium to obtain a stego-medium without any suspicion from a viewer who see that last one. Steganalysis is the opposite discipline. Its goal is to detect the presence of hidden information from a stego-medium. The medium can be an audio, video or image file. In this work, we focus on image file medium. Universal steganalysis is the detection of hidden data without knowing the algorithm used to embed the message inside the carrier. There are some methods of classification between stego and cover medium proposed in literature. In this paper, we propose a new universal steganalysis method based on unsupervised and supervised machine learning algorithms. Our method reduces the cover-source mismatch problem in the first stage and uses multiple linear regression in the second stage to predict the relative payload (in terms of bits per non-zero AC DCT coefficient) of the embedded message. With this measure, we can easily calculate the length of the embedded message. In our experiments, we got reliable models in all the clusters to predict the relative payload for cover-images and stego-images.","PeriodicalId":184662,"journal":{"name":"2018 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114828293","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 : 2018-04-01DOI: 10.1109/ISACV.2018.8354029
Mohamed Dardor, Mohammed Chlyah, J. Boumhidi
Detecting incidents is the important step for efficient incident management which aims to minimize the impact of non-recurrent congestion. A little research has been performed to automatically detect incidents in urban arterials. This paper provides incident detection system based on Support Vector Machine (SVM) in urban traffic networks using “Original urban network scenario” and “Freeway like scenario”; moreover, for the best performance of the classifier we introduce an optimization using genetic algorithm (GA). The results show that Genetic Algorithm Support Vector Machine (GA-SVM) has a high classification accuracy and high detection performance with regard to the detection rate and false alarm. A comparative study confirms that the effectiveness of GA-SVM mainly for signalized urban roads scenario.
{"title":"Incident detection in signalized urban roads based on genetic algorithm and support vector machine","authors":"Mohamed Dardor, Mohammed Chlyah, J. Boumhidi","doi":"10.1109/ISACV.2018.8354029","DOIUrl":"https://doi.org/10.1109/ISACV.2018.8354029","url":null,"abstract":"Detecting incidents is the important step for efficient incident management which aims to minimize the impact of non-recurrent congestion. A little research has been performed to automatically detect incidents in urban arterials. This paper provides incident detection system based on Support Vector Machine (SVM) in urban traffic networks using “Original urban network scenario” and “Freeway like scenario”; moreover, for the best performance of the classifier we introduce an optimization using genetic algorithm (GA). The results show that Genetic Algorithm Support Vector Machine (GA-SVM) has a high classification accuracy and high detection performance with regard to the detection rate and false alarm. A comparative study confirms that the effectiveness of GA-SVM mainly for signalized urban roads scenario.","PeriodicalId":184662,"journal":{"name":"2018 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128627020","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 : 2018-04-01DOI: 10.1109/ISACV.2018.8354076
Sokhna Faye Bessane, M. Camara, Ibrahima Fall, A. Bah
Recent research often suggests ideas about quantitative or qualitative causal models of performance measurement systems. We also rely on some works that develop ideas on causal models of SMP. This research has highlighted two approaches in the study of causal models of performance measurement systems: the quantitative and qualitative approach. Indeed, the qualitative models lack precision and the qualitative models are confronted with problems of data collection in hierarchical level deployment. Therefore, it should be noted that the combination of these two methods is very rare or non-existent for the SMPs. Hence the idea of proposing a model that combines the two, because these approach also have certain limits. According to our studies we note a complementarity because to combine these two methods reinforces the richness and the validity of the results.
{"title":"Causal model of performance measurement systems by combining qualitative and quantitative models for robust results","authors":"Sokhna Faye Bessane, M. Camara, Ibrahima Fall, A. Bah","doi":"10.1109/ISACV.2018.8354076","DOIUrl":"https://doi.org/10.1109/ISACV.2018.8354076","url":null,"abstract":"Recent research often suggests ideas about quantitative or qualitative causal models of performance measurement systems. We also rely on some works that develop ideas on causal models of SMP. This research has highlighted two approaches in the study of causal models of performance measurement systems: the quantitative and qualitative approach. Indeed, the qualitative models lack precision and the qualitative models are confronted with problems of data collection in hierarchical level deployment. Therefore, it should be noted that the combination of these two methods is very rare or non-existent for the SMPs. Hence the idea of proposing a model that combines the two, because these approach also have certain limits. According to our studies we note a complementarity because to combine these two methods reinforces the richness and the validity of the results.","PeriodicalId":184662,"journal":{"name":"2018 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121554650","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 : 2018-04-01DOI: 10.1109/ISACV.2018.8354028
Mohammed Es-Sabry, N. El Akkad, M. Merras, A. Saaidi, K. Satori
In this work, we propose a method of cryptography of grayscale images. The principle of this approach is to encrypt any image (called the original image), into a sequence of N images whose (N-1) are generated randomly and the Nth image is determined from the original image and the (N-1) generated images. A key will be used in order to increase the security of the image transmitted to the receiver. The pixels of the original image are first converted into bits and then we use the shift bits operators to obtain a matrix, which will be used in the encryption procedure. All N images as well as the key used are needed in the decryption process, to obtain the source image. Experiments show the importance and quality of the approach that we proposed in terms of accuracy.
{"title":"Grayscale image encryption using shift bits operations","authors":"Mohammed Es-Sabry, N. El Akkad, M. Merras, A. Saaidi, K. Satori","doi":"10.1109/ISACV.2018.8354028","DOIUrl":"https://doi.org/10.1109/ISACV.2018.8354028","url":null,"abstract":"In this work, we propose a method of cryptography of grayscale images. The principle of this approach is to encrypt any image (called the original image), into a sequence of N images whose (N-1) are generated randomly and the Nth image is determined from the original image and the (N-1) generated images. A key will be used in order to increase the security of the image transmitted to the receiver. The pixels of the original image are first converted into bits and then we use the shift bits operators to obtain a matrix, which will be used in the encryption procedure. All N images as well as the key used are needed in the decryption process, to obtain the source image. Experiments show the importance and quality of the approach that we proposed in terms of accuracy.","PeriodicalId":184662,"journal":{"name":"2018 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115245554","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}
This paper details a comparative study in terms of compression capability, between our separable two-dimensional discrete orthogonal moments and the classical existing methods such as classical discrete orthogonal moments and DCT. In the current study, we aim to investigate the properties and the capabilities of the separable discrete moments in the image compression fields. The experimental results and analysis on several test images, show that separable discrete orthogonal moments can provide better image representation and favorable image compression performance than the traditional moments.
{"title":"Gray level image compression using a set of separable 2D discrete orthogonal moments based on Racah polynomials","authors":"Batioua Imad, Benouini Rachid, Zenkouar Khalid, El Fadili Hakim, Qjidaa Hassan","doi":"10.1109/ISACV.2018.8354015","DOIUrl":"https://doi.org/10.1109/ISACV.2018.8354015","url":null,"abstract":"This paper details a comparative study in terms of compression capability, between our separable two-dimensional discrete orthogonal moments and the classical existing methods such as classical discrete orthogonal moments and DCT. In the current study, we aim to investigate the properties and the capabilities of the separable discrete moments in the image compression fields. The experimental results and analysis on several test images, show that separable discrete orthogonal moments can provide better image representation and favorable image compression performance than the traditional moments.","PeriodicalId":184662,"journal":{"name":"2018 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115976950","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：