Institution
Nanjing University of Science and Technology
Education•Nanjing, China•
About: Nanjing University of Science and Technology is a education organization based out in Nanjing, China. It is known for research contribution in the topics: Control theory & Catalysis. The organization has 31581 authors who have published 36390 publications receiving 525474 citations. The organization is also known as: Nánjīng Lǐgōng Dàxué & Nánlǐgōng.
Papers published on a yearly basis
Papers
More filters
••
14 Jun 2020TL;DR: A temporal sharpness prior to constrain the deep CNN model to help the latent frame restoration and it is shown that exploring the domain knowledge of video deblurring is able to make the deepCNN model more compact and efficient.
Abstract: We present a simple and effective deep convolutional neural network (CNN) model for video deblurring. The proposed algorithm mainly consists of optical flow estimation from intermediate latent frames and latent frame restoration steps. It first develops a deep CNN model to estimate optical flow from intermediate latent frames and then restores the latent frames based on the estimated optical flow. To better explore the temporal information from videos, we develop a temporal sharpness prior to constrain the deep CNN model to help the latent frame restoration. We develop an effective cascaded training approach and jointly train the proposed CNN model in an end-to-end manner. We show that exploring the domain knowledge of video deblurring is able to make the deep CNN model more compact and efficient. Extensive experimental results show that the proposed algorithm performs favorably against state-of-the-art methods on the benchmark datasets as well as real-world videos.
118 citations
••
TL;DR: A novel method to improve KPCA-based feature extraction is developed, which is the first one that is methodologically consistent with K PCA.
118 citations
••
18 Jun 2018
TL;DR: Zhang et al. as discussed by the authors proposed a data-driven discriminative prior to distinguish whether an input image is clear or not, which can be embedded into the maximum a posterior (MAP) framework.
Abstract: We present an effective blind image deblurring method based on a data-driven discriminative prior. Our work is motivated by the fact that a good image prior should favor clear images over blurred ones. In this work, we formulate the image prior as a binary classifier which can be achieved by a deep convolutional neural network (CNN). The learned prior is able to distinguish whether an input image is clear or not. Embedded into the maximum a posterior (MAP) framework, it helps blind deblurring in various scenarios, including natural, face, text, and low-illumination images. However, it is difficult to optimize the deblurring method with the learned image prior as it involves a non-linear CNN. Therefore, we develop an efficient numerical approach based on the half-quadratic splitting method and gradient decent algorithm to solve the proposed model. Furthermore, the proposed model can be easily extended to non-uniform deblurring. Both qualitative and quantitative experimental results show that our method performs favorably against state-of-the-art algorithms as well as domain-specific image deblurring approaches.
118 citations
••
TL;DR: In this article, diverse methods toward blue perovskite nanocrystals are summarized, as well as the intrinsic origin of low stability and poor optical properties are discussed, and strategies to improve their performance and stability and critical challenges that severely limit the stability and performances of blue pervskite NCs are discussed.
Abstract: Lead halide perovskites are potential candidates for wide-color-gamut display applications. Recently, red and green light-emitting diodes (LEDs) based on these materials have achieved external quantum efficiency (EQE) of over 20%, while the blue devices lag behind them severely because of a much lower photoluminescence quantum yield (PL QY) and inferior stability. Blue perovskite nanocrystals (NCs) are promising active materials for high-efficiency devices; however, they are reported to exhibit low defect tolerance and suffer from troublesome ion migration behavior. Though some good ideas have been proposed to overcome these problems, the present results are still unsatisfactory. In this Perspective, diverse methods toward blue perovskite NCs are summarized, as well as the intrinsic origin of low stability and poor optical properties. Then, strategies to improve their performance and stability and critical challenges that severely limit the stability and performances of blue perovskite NCs are discussed. ...
118 citations
••
TL;DR: A survey of dictionary learning algorithms for face recognition is provided to understand the profiles of this subject and to grasp the theoretical rationales and potentials as well as their applicability to different cases of face recognition.
Abstract: During the past several years, as one of the most successful applications of sparse coding and dictionary learning, dictionary-based face recognition has received significant attention. Although some surveys of sparse coding and dictionary learning have been reported, there is no specialized survey concerning dictionary learning algorithms for face recognition. This paper provides a survey of dictionary learning algorithms for face recognition. To provide a comprehensive overview, we not only categorize existing dictionary learning algorithms for face recognition but also present details of each category. Since the number of atoms has an important impact on classification performance, we also review the algorithms for selecting the number of atoms. Specifically, we select six typical dictionary learning algorithms with different numbers of atoms to perform experiments on face databases. In summary, this paper provides a broad view of dictionary learning algorithms for face recognition and advances study in this field. It is very useful for readers to understand the profiles of this subject and to grasp the theoretical rationales and potentials as well as their applicability to different cases of face recognition.
118 citations
Authors
Showing all 31818 results
Name | H-index | Papers | Citations |
---|---|---|---|
Jian Yang | 142 | 1818 | 111166 |
Liming Dai | 141 | 781 | 82937 |
Hui Li | 135 | 2982 | 105903 |
Jian Zhou | 128 | 3007 | 91402 |
Shuicheng Yan | 123 | 810 | 66192 |
Zidong Wang | 122 | 914 | 50717 |
Xin Wang | 121 | 1503 | 64930 |
Xuan Zhang | 119 | 1530 | 65398 |
Zhenyu Zhang | 118 | 1167 | 64887 |
Xin Li | 114 | 2778 | 71389 |
Zeshui Xu | 113 | 752 | 48543 |
Xiaoming Li | 113 | 1932 | 72445 |
Chunhai Fan | 112 | 702 | 51735 |
H. Vincent Poor | 109 | 2116 | 67723 |
Qian Wang | 108 | 2148 | 65557 |