Image encryption algorithm for synchronously updating Boolean networks based on matrix semi-tensor product theory

X Wang, S Gao - Information sciences, 2020‏ - Elsevier
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 …

Deep collaborative embedding for social image understanding

Z Li, J Tang, T Mei - IEEE transactions on pattern analysis and …, 2018‏ - ieeexplore.ieee.org
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 …

Triclustering algorithms for three-dimensional data analysis: a comprehensive survey

R Henriques, SC Madeira - ACM Computing Surveys (CSUR), 2018‏ - dl.acm.org
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 …

Weakly-supervised semantic guided hashing for social image retrieval

Z Li, J Tang, L Zhang, J Yang - International Journal of Computer Vision, 2020‏ - Springer
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 …

Deblurring images via dark channel prior

J Pan, D Sun, H Pfister, MH Yang - IEEE transactions on pattern …, 2017‏ - ieeexplore.ieee.org
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 …

Tensor completion algorithms in big data analytics

Q Song, H Ge, J Caverlee, X Hu - ACM Transactions on Knowledge …, 2019‏ - dl.acm.org
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 …

Towards non-iid image classification: A dataset and baselines

Y He, Z Shen, P Cui - Pattern Recognition, 2021‏ - Elsevier
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 …

Robust structured nonnegative matrix factorization for image representation

Z Li, J Tang, X He - IEEE transactions on neural networks and …, 2017‏ - ieeexplore.ieee.org
Dimensionality reduction has attracted increasing attention, because high-dimensional data
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

H Tang, Z Li, Z Peng, J Tang - Proceedings of the 28th ACM international …, 2020‏ - dl.acm.org
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 …

Semi-supervised local feature selection for data classification

Z Li, J Tang - Science China Information Sciences, 2021‏ - Springer
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 …