no code implementations • 18 Aug 2023 • Sherif Abdelfattah, Kathryn Kasmarik, Jiankun Hu
We propose a novel multi-objective reinforcement learning algorithm that can robustly evolve a convex coverage set of policies in an online manner in non-stationary environments.
no code implementations • 18 Aug 2023 • Sherif Abdelfattah, Kathryn Merrick, Jiankun Hu
In this work, intrinsically motivated reinforcement learning has been successfully deployed to evolve generic skill sets for learning hierarchical policies to solve multi-objective Markov decision processes.
no code implementations • 15 Jul 2022 • Xuefei Yin, Yanming Zhu, Yi Xie, Jiankun Hu
Case studies on the detection of SFDIAs on the benchmark smart grids show that the PowerFDNet achieved significant improvement compared with the state-of-the-art SFDIA detection methods.
no code implementations • 2 Jul 2022 • Yanming Zhu, Xuefei Yin, Xiuping Jia, Jiankun Hu
Latent fingerprints are important for identifying criminal suspects.
1 code implementation • 26 Jun 2022 • Yanming Zhu, Xuefei Yin, Jiankun Hu
In this paper, we propose a new method that formulates the latent fingerprint enhancement as a constrained fingerprint generation problem within a generative adversarial network (GAN) framework.
no code implementations • 16 Mar 2021 • Jue Zhang, Xiuping Jia, Jiankun Hu
First, a convolutional neural network is trained with positive and negative samples with image-level labels.
no code implementations • 29 Nov 2019 • Junpeng Zhang, Xiuping Jia, Jiankun Hu, Jocelyn Chanussot
O-LSD reformulates the batch-based low-rank matrix decomposition with the structured sparse penalty to its equivalent frame-wise separable counterpart, which then defines a stochastic optimization problem for online subspace basis estimation.
no code implementations • 26 Aug 2019 • Junpeng Zhang, Xiuping Jia, Jiankun Hu
It is integrated with structured sparsity regularization to achieve background subtraction in the developed method of Low-rank and Structured Sparse Decomposition (LSD).
no code implementations • 8 Oct 2018 • Meng Shen, Zelin Liao, Liehuang Zhu, Rashid Mijumbi, Xiaojiang Du, Jiankun Hu
Face liveness detection has become a widely used technique with a growing importance in various authentication scenarios to withstand spoofing attacks.
Cryptography and Security
no code implementations • 30 Mar 2017 • Senjian An, Farid Boussaid, Mohammed Bennamoun, Jiankun Hu
Similarly, for a residual net and a conventional rectifier net with the same structure except for the skip connections in the residual net, the corresponding single hidden layer representation of the residual net is much more complex than the corresponding single hidden layer representation of the conventional net.
no code implementations • 1 Jul 2014 • Jinwei Xu, Jiankun Hu, Xiuping Jia
Orientation field, representing the fingerprint ridge structure direction, plays a crucial role in fingerprint-related image processing tasks.
no code implementations • 26 Jun 2014 • Jinwei Xu, Jiankun Hu, Xiuping Jia
Latent fingerprint has the practical value to identify the suspects who have unintentionally left a trace of fingerprint in the crime scenes.