On the internet,image tampering has become awidespread issue,leading to a series of adverse effects on the trustworthiness of image information.In response to this challenge,this paper proposes an image tampering loca...On the internet,image tampering has become awidespread issue,leading to a series of adverse effects on the trustworthiness of image information.In response to this challenge,this paper proposes an image tampering localization method based on dual-stream feature fusion.Our approach employs a dualstream encoder to simultaneously extract features from both the RGB stream and the noise stream,enabling the localization of forged regions.By introducing an attention mechanism,these two feature streams are fused,further enhancing the detection performance.Additionally,the Atrous Spatial Pyramid Pooling(ASPP)module is integrated to expand the receptive field and extract contextual information at different scales.Finally,the decoder generates a tamper region localization map.Experimental results demonstrate that the proposed method exhibits significant performance improvements on three widely used datasets,affirming its effectiveness in the field of image tampering detection.展开更多
In the era of big data, the dimensionality of data is increasing dramatically in many domains. To deal with high dimensionality, online feature selection becomes critical in big data mining. Recently, online selection...In the era of big data, the dimensionality of data is increasing dramatically in many domains. To deal with high dimensionality, online feature selection becomes critical in big data mining. Recently, online selection of dynamic features has received much attention. In situations where features arrive sequentially over time, we need to perform online feature selection upon feature arrivals. Meanwhile, considering grouped features, it is necessary to deal with features arriving by groups. To handle these challenges, some state-of- the-art methods for online feature selection have been proposed. In this paper, we first give a brief review of traditional feature selection approaches. Then we discuss specific problems of online feature selection with feature streams in detail. A comprehensive review of existing online feature selection methods is presented by comparing with each other. Finally, we discuss several open issues in online feature selection.展开更多
文摘On the internet,image tampering has become awidespread issue,leading to a series of adverse effects on the trustworthiness of image information.In response to this challenge,this paper proposes an image tampering localization method based on dual-stream feature fusion.Our approach employs a dualstream encoder to simultaneously extract features from both the RGB stream and the noise stream,enabling the localization of forged regions.By introducing an attention mechanism,these two feature streams are fused,further enhancing the detection performance.Additionally,the Atrous Spatial Pyramid Pooling(ASPP)module is integrated to expand the receptive field and extract contextual information at different scales.Finally,the decoder generates a tamper region localization map.Experimental results demonstrate that the proposed method exhibits significant performance improvements on three widely used datasets,affirming its effectiveness in the field of image tampering detection.
基金This work was supported in part by the National Key Research and Development Program of China （2016YFB 1000901）, the Program for Changjiang Scholars and Innovative Research Team in University （PCSIRT） of the Ministry of Education, China （IRT13059）, the National Basic Research Program （973 Program） of China （2013CB329604）, the Specialized Research Fund for the Doctoral Program of Higher Education （20130111110011）, and the National Natural Science Foundation of China （Grant Nos. 61273292, 61229301, 61503112, 61673152）.
文摘In the era of big data, the dimensionality of data is increasing dramatically in many domains. To deal with high dimensionality, online feature selection becomes critical in big data mining. Recently, online selection of dynamic features has received much attention. In situations where features arrive sequentially over time, we need to perform online feature selection upon feature arrivals. Meanwhile, considering grouped features, it is necessary to deal with features arriving by groups. To handle these challenges, some state-of- the-art methods for online feature selection have been proposed. In this paper, we first give a brief review of traditional feature selection approaches. Then we discuss specific problems of online feature selection with feature streams in detail. A comprehensive review of existing online feature selection methods is presented by comparing with each other. Finally, we discuss several open issues in online feature selection.
