Image encryption algorithm for synchronously updating Boolean networks based on matrix semi-tensor product theory
This paper studies chaotic image encryption technology and an application of matrix semi-
tensor product theory, and a Boolean network encryption algorithm for a synchronous …
tensor product theory, and a Boolean network encryption algorithm for a synchronous …
Deep collaborative embedding for social image understanding
In this work, we investigate the problem of learning knowledge from the massive community-
contributed images with rich weakly-supervised context information, which can benefit …
contributed images with rich weakly-supervised context information, which can benefit …
Triclustering algorithms for three-dimensional data analysis: a comprehensive survey
Three-dimensional data are increasingly prevalent across biomedical and social domains.
Notable examples are gene-sample-time, individual-feature-time, or node-node-time data …
Notable examples are gene-sample-time, individual-feature-time, or node-node-time data …
Weakly-supervised semantic guided hashing for social image retrieval
Hashing has been widely investigated for large-scale image retrieval due to its search
effectiveness and computation efficiency. In this work, we propose a novel Semantic Guided …
effectiveness and computation efficiency. In this work, we propose a novel Semantic Guided …
Deblurring images via dark channel prior
We present an effective blind image deblurring algorithm based on the dark channel prior.
The motivation of this work is an interesting observation that the dark channel of blurred …
The motivation of this work is an interesting observation that the dark channel of blurred …
Tensor completion algorithms in big data analytics
Tensor completion is a problem of filling the missing or unobserved entries of partially
observed tensors. Due to the multidimensional character of tensors in describing complex …
observed tensors. Due to the multidimensional character of tensors in describing complex …
Towards non-iid image classification: A dataset and baselines
IID 2 hypothesis between training and testing data is the basis of numerous image
classification methods. Such property can hardly be guaranteed in practice where the Non …
classification methods. Such property can hardly be guaranteed in practice where the Non …
Robust structured nonnegative matrix factorization for image representation
Dimensionality reduction has attracted increasing attention, because high-dimensional data
have arisen naturally in numerous domains in recent years. As one popular dimensionality …
have arisen naturally in numerous domains in recent years. As one popular dimensionality …
Blockmix: meta regularization and self-calibrated inference for metric-based meta-learning
Most metric-based meta-learning methods learn only the sophisticated similarity metric for
few-shot classification, which may lead to the feature deterioration and unreliable prediction …
few-shot classification, which may lead to the feature deterioration and unreliable prediction …
Semi-supervised local feature selection for data classification
Conventional feature selection methods select the same feature subset for all classes, which
means that the selected features might work better for some classes than the others …
means that the selected features might work better for some classes than the others …