Image has become an essential medium for expressing meaning and disseminating information.Many images are uploaded to the Internet,among which some are pornographic,causing adverse effects on public psychological heal...Image has become an essential medium for expressing meaning and disseminating information.Many images are uploaded to the Internet,among which some are pornographic,causing adverse effects on public psychological health.To create a clean and positive Internet environment,network enforcement agencies need an automatic and efficient pornographic image recognition tool.Previous studies on pornographic images mainly rely on convolutional neural networks(CNN).Because of CNN’s many parameters,they must rely on a large labeled training dataset,which takes work to build.To reduce the effect of the database on the recognition performance of pornographic images,many researchers view pornographic image recognition as a binary classification task.In actual application,when faced with pornographic images of various features,the performance and recognition accuracy of the network model often decrease.In addition,the pornographic content in images usually lies in several small-sized local regions,which are not a large proportion of the image.CNN,this kind of strong supervised learning method,usually cannot automatically focus on the pornographic area of the image,thus affecting the recognition accuracy of pornographic images.This paper established an image dataset with seven classes by crawling pornographic websites and Baidu Image Library.A weakly supervised pornographic image recognition method based on multiple instance learning(MIL)is proposed.The Squeeze and Extraction(SE)module is introduced in the feature extraction to strengthen the critical information and weaken the influence of non-key and useless information on the result of pornographic image recognition.To meet the requirements of the pooling layer operation in Multiple Instance Learning,we introduced the idea of an attention mechanism to weight and average instances.The experimental results show that the proposed method has better accuracy and F1 scores than other methods.展开更多
Enhancing the tunneling magneto-Seebeck(TMS) ratio and uncovering its underlying mechanism are greatly demanded in spin caloritronics.The magnitude and sign of the TMS effect depend on the type of atom and the stackin...Enhancing the tunneling magneto-Seebeck(TMS) ratio and uncovering its underlying mechanism are greatly demanded in spin caloritronics.The magnitude and sign of the TMS effect depend on the type of atom and the stacking order of atoms at the interfaces.Herein,we demonstrate that TMS ratios can be effectively manipulated by altering heterogonous or homogeneous interface through decoration on the CoFeSi(001) surface inserted on the MgO insulating layers.The maximum TMS ratio of pure Co_(2)/O termination is 4565% at 800 K.Notably,the TMS ratio of the FeSi/O termination has two peak values,of which the maximum could reach up to-3290% at 650 K.By comparing two different atom arrangements at the interface,we reveal that the sign and symbol of the TMS ratio can be controlled by the temperature and different atomic configurations at the Co_(2)FeSi/MgO interface.Furthermore,the spin-Seebeck coefficient up to ~150 μV/K is also possible when we select suitable terminations and temperatures.These findings will provide useful insights into how to control the sign and symbol of the TMS ratio and accordingly stimulate the development field of magneto-thermoelectric power and spin caloritronic devices based on the magneto-Seebeck effect in Heusler-based metallic multilayers.展开更多
基金This work is supported by the Academic Research Project of Henan Police College(Grant:HNJY-2021-QN-14 and HNJY202220)the Key Technology R&D Program of Henan Province(Grant:222102210041).
文摘Image has become an essential medium for expressing meaning and disseminating information.Many images are uploaded to the Internet,among which some are pornographic,causing adverse effects on public psychological health.To create a clean and positive Internet environment,network enforcement agencies need an automatic and efficient pornographic image recognition tool.Previous studies on pornographic images mainly rely on convolutional neural networks(CNN).Because of CNN’s many parameters,they must rely on a large labeled training dataset,which takes work to build.To reduce the effect of the database on the recognition performance of pornographic images,many researchers view pornographic image recognition as a binary classification task.In actual application,when faced with pornographic images of various features,the performance and recognition accuracy of the network model often decrease.In addition,the pornographic content in images usually lies in several small-sized local regions,which are not a large proportion of the image.CNN,this kind of strong supervised learning method,usually cannot automatically focus on the pornographic area of the image,thus affecting the recognition accuracy of pornographic images.This paper established an image dataset with seven classes by crawling pornographic websites and Baidu Image Library.A weakly supervised pornographic image recognition method based on multiple instance learning(MIL)is proposed.The Squeeze and Extraction(SE)module is introduced in the feature extraction to strengthen the critical information and weaken the influence of non-key and useless information on the result of pornographic image recognition.To meet the requirements of the pooling layer operation in Multiple Instance Learning,we introduced the idea of an attention mechanism to weight and average instances.The experimental results show that the proposed method has better accuracy and F1 scores than other methods.
基金supported by the National Natural Science Foundation of China (Grant No. 12104458)Foshan (Southern China) Institute for New Materials (Grant No. 2021AYF25021)。
文摘Enhancing the tunneling magneto-Seebeck(TMS) ratio and uncovering its underlying mechanism are greatly demanded in spin caloritronics.The magnitude and sign of the TMS effect depend on the type of atom and the stacking order of atoms at the interfaces.Herein,we demonstrate that TMS ratios can be effectively manipulated by altering heterogonous or homogeneous interface through decoration on the CoFeSi(001) surface inserted on the MgO insulating layers.The maximum TMS ratio of pure Co_(2)/O termination is 4565% at 800 K.Notably,the TMS ratio of the FeSi/O termination has two peak values,of which the maximum could reach up to-3290% at 650 K.By comparing two different atom arrangements at the interface,we reveal that the sign and symbol of the TMS ratio can be controlled by the temperature and different atomic configurations at the Co_(2)FeSi/MgO interface.Furthermore,the spin-Seebeck coefficient up to ~150 μV/K is also possible when we select suitable terminations and temperatures.These findings will provide useful insights into how to control the sign and symbol of the TMS ratio and accordingly stimulate the development field of magneto-thermoelectric power and spin caloritronic devices based on the magneto-Seebeck effect in Heusler-based metallic multilayers.
