Search

We consider the problem of video snapshot compressive imaging (SCI), where sequential high-speed frames are modulated by different masks and captured by a single measurement. The underlying principle of reconstructing multi-frame images from only one single measurement is to solve an ill-posed problem. By combining optimization algorithms and neural networks, deep unfolding networks (DUNs) score tremendous achievements in solving inverse problems. In this paper, our proposed model is under the DUN framework and we propose a 3D Convolution-Transformer Mixture (CTM) module with a 3D efficient and scalable attention model plugged in, which helps fully learn the correlation between temporal and spatial dimensions by virtue of Transformer. To our best knowledge, this is the first time that Transformer is employed to video SCI reconstruction. Besides, to further investigate the high-frequency information during the reconstruction process which are neglected in previous studies, we introduce variance estimation characterizing the uncertainty on a pixel-by-pixel basis. Extensive experimental results demonstrate that our proposed method achieves state-of-the-art (SOTA) (with a 1.2dB gain in PSNR over previous SOTA algorithm) results. We will release the code.

The ability of snapshot compressive imaging (SCI) systems to efficiently capture high-dimensional (HD) data has led to an inverse problem, which consists of recovering the HD signal from the compressed and noisy measurement. While reconstruction algorithms grow fast to solve it with the recent advances of deep learning, the fundamental issue of accurate and stable recovery remains. To this end, we propose deep equilibrium models (DEQ) for video SCI, fusing data-driven regularization and stable convergence in a theoretically sound manner. Each equilibrium model implicitly learns a nonexpansive operator and analytically computes the fixed point, thus enabling unlimited iterative steps and infinite network depth with only a constant memory requirement in training and testing. Specifically, we demonstrate how DEQ can be applied to two existing models for video SCI reconstruction: recurrent neural networks (RNN) and Plug-and-Play (PnP) algorithms. On a variety of datasets and real data, both quantitative and qualitative evaluations of our results demonstrate the effectiveness and stability of our proposed method. The code and models are available at: https://github.com/IndigoPurple/DEQSCI ., 9 pages, 7 figures

We consider the reconstruction problem of video compressive sensing (VCS) under the deep unfolding/rolling structure. Yet, we aim to build a flexible and concise model using minimum stages. Different from existing deep unfolding networks used for inverse problems, where more stages are used for higher performance but without flexibility to different masks and scales, hereby we show that a 2-stage deep unfolding network can lead to the state-of-the-art (SOTA) results (with a 1.7dB gain in PSNR over the single stage model, RevSCI) in VCS. The proposed method possesses the properties of adaptation to new masks and ready to scale to large data without any additional training thanks to the advantages of deep unfolding. Furthermore, we extend the proposed model for color VCS to perform joint reconstruction and demosaicing. Experimental results demonstrate that our 2-stage model has also achieved SOTA on color VCS reconstruction, leading to a >2.3dB gain in PSNR over the previous SOTA algorithm based on plug-and-play framework, meanwhile speeds up the reconstruction by >17 times. In addition, we have found that our network is also flexible to the mask modulation and scale size for color VCS reconstruction so that a single trained network can be applied to different hardware systems. The code and models will be released to the public.

您好， 此附件是2022-2023最新简历， 谢谢您的宝贵时间和查阅。 Applicant：Siming_Zheng

Deal all, Hello, this is my English Curriculum Vitae and On-the-Spot Investigation photos. Thank you for your attention.

Supplementary materials

你好， 本资料是额外补充资料，若有兴趣可查阅。 附件为《青年文明号版本-员工郑思明 - 越秀物业电子期刊创刊》 谢谢你的关注。

We consider the image and video compression on resource limited platforms. An ultra low-cost image encoder, named Block Modulating Video Compression (BMVC) with an encoding complexity ${\cal O}(1)$ is proposed to be implemented on mobile platforms with low consumption of power and computation resources. We also develop two types of BMVC decoders, implemented by deep neural networks. The first BMVC decoder is based on the Plug-and-Play (PnP) algorithm, which is flexible to different compression ratios. And the second decoder is a memory efficient end-to-end convolutional neural network, which aims for real-time decoding. Extensive results on the high definition images and videos demonstrate the superior performance of the proposed codec and the robustness against bit quantization., Comment: 13 pages, 8 figures

We propose a mutual information-based sufficient representation learning (MSRL) approach, which uses the variational formulation of the mutual information and leverages the approximation power of deep neural networks. MSRL learns a sufficient representation with the maximum mutual information with the response and a user-selected distribution. It can easily handle multi-dimensional continuous or categorical response variables. MSRL is shown to be consistent in the sense that the conditional probability density function of the response variable given the learned representation converges to the conditional probability density function of the response variable given the predictor. Non-asymptotic error bounds for MSRL are also established under suitable conditions. To establish the error bounds, we derive a generalized Dudley's inequality for an order-two U-process indexed by deep neural networks, which may be of independent interest. We discuss how to determine the intrinsic dimension of the underlying data distribution. Moreover, we evaluate the performance of MSRL via extensive numerical experiments and real data analysis and demonstrate that MSRL outperforms some existing nonlinear sufficient dimension reduction methods., Comment: 43 pages, 6 figures and 5 tables

Dear all, This is my English Curriculum Vitae and On-the-Spot Investigation photos. Thank you for your attention.

Dear all, This is my Chinese Curriculum Vitae and On-the-Spot Investigation photos. Thank you for your attention.

Background: To explore the safety and feasibility of laparoscopic caudate lobe (CL) resection for the treatment of hepatolithiasis. Methods: A retrospective study of nine patients who received laparoscopic CL resection for treatment of hepatolithiasis in our hospital from January 2013 to April 2017. Of these cases, we studied the patients' demographic data, the operation time, blood loss, post-operative hospital stay, post-operative complications and prognosis. Results: All the nine cases are performed successfully; the post-operative recovery was symptom free except for one case of post-operative bile leakage. Among them, there were six cases of CL resection in combination with other lobe, three cases of separate CL resection, and three cases of whole CL resection. The average operative time was 310 min (Range: 180–450 min), the average intraoperative blood loss was 530 ml (Range: 100–1000 ml), average post-operative hospital stay was 9 days (Range: 6–13 days), average total hospital stay was 10 days (Range: 9–19 days). Intraoperative calculi exhaustion rate was 66.7% (6/9), which at the end of treatment was 88.9% (8/9). No cases had calculi recurrence. Conclusion: The application of laparoscopic CL resection is feasible and safe.

In recent years, mobile Internet has accelerated the proliferation of smart mobile development. The mobile payment, mobile security and privacy protection have become the focus of widespread attention. Iris recognition becomes a high-security authentication technology in these fields, it is widely used in distinct science fields in biometric authentication fields. The Convolutional Neural Network (CNN) is one of the mainstream deep learning approaches for image recognition, whereas its anti-noise ability is weak and needs a certain amount of memory to train in image classification tasks. Under these conditions we put forward a fine-tuning neural network model based on the Mask R-CNN and Inception V4 neural network model, which integrates every component in an overall system that combines the iris detection, extraction, and recognition function as an iris recognition system. The proposed framework has the characteristics of scalability and high availability; it not only can learn part-whole relationships of the iris image but also enhancing the robustness of the whole framework. Importantly, the proposed model can be trained using the different spectrum of samples, such as Visible Wavelength (VW) and Near Infrared (NIR) iris biometric databases. The recognition average accuracy of 99.10% is achieved while executing in the mobile edge calculation device of the Jetson Nano., Comment: This is the second revision for updating the formation, logical and image captions

The Curie temperature of an anisotropic Heisenberg mixed spin system (S = 1, σ = 1 2 ) was calculated in the presence of uniaxial anisotropy, D, and biquadratic exchange, J'. The Green function decoupling theory was used. Because of the characteristic of the system some new Green functions were introduced to obtain the required equations. The behavior of the Curie temperature, Tc as a function of d, J' and the exchange anisotropy α, was investigated. It was found that the influence of the biquadratic exchange on the Curie temperature is very small when α is in the 0.5–0.6 range.

The magnetic properties of a diluted anisotropic Heisenberg spin S = 1 ferromagnet are discussed by use of a simple method. The Curie temperatures for different values of concentration p of magnetic atoms and anisotropy η are calculated. The magnetization vs. temperature curves for various p and η are drawn.

The Heisenberg ferromagnet with the biquadratic exchange interaction is studied. The low temperature expansion of magnetization, the Curie temperature and the susceptibility at high temperatures are obtained.

The effect of crystal-field anisotropy on the Curie temperature is studied in an S = 1 anisotropic Heisenberg-Ising ferromagnet. The Green function technique with a Callen-type approximation is used. The results show that, when the correlations between spins of nearest neighbouring sites are taken into account, the change in the Curie temperature with crystal-field anisotropy is not so great as that calculated in the random phase approximation.