Mutual information maximizing GAN inversion for real face with identity preservation

Recent generative adversarial networks (GANs) have yielded remarkable performance in face image synthesis. GAN inversion embeds an image into the latent space of a pretrained generator, enabling it to be used for real face manipulation. However, current inversion approaches for real faces suffer the dilemma of initialization collapse and identity loss. In this paper, we propose a hierarchical GAN inversion for real faces with identity preservation based on mutual information maximization. We first use a facial domain guaranteed initialization to avoid the initialization collapse. Furthermore, we prove that maximizing the mutual information between inverted faces and their identities is equivalent to minimizing the distance between identity features from inverted and original faces. Optimization for real face inversion with identity preservation is implemented on this mutual information-maximizing constraint. Extensive experimental results show that our approach outperforms state-of-the-art solutions for inverting and editing real faces, particularly in terms of face identity preservation.     

Multi-scale and multi-patch transformer for sandstorm image enhancement

Sandstorm is a meteorological phenomenon common in arid and semi-arid regions. A sandstorm can carry large volumes of sand unexpectedly, which leads to severe color deviations and significantly degraded visibility when an image is taken in such a scenario. However, existing image enhancement methods cannot enhance sandstorm images well due to the challenging degradations and the scarcity of sandstorm training data. In this paper, we propose a Transformer with rotary position embedding to perform sandstorm image enhancement via building multi-scale and multi-patch dependencies. Our key insights in this work are 1) a multi-scale Transformer can globally eliminate the color deviations of sandstorm images via aggregating global information, 2) a multi-patch Transformer can recover local details well via learning the spatial variant degradations, and 3) a U-shape Transformer with rotary position embedding as the core unit of multi-scale and multi-patch Transformer can effectively build the long-range dependencies. We also contribute a real-world Sandstorm Image Enhancement (SIE) dataset including 1,400 sandstorm images with different degrees of degradations and various scenes. Experiments performed on synthetic images and real-world sandstorm images demonstrate that our proposed method not only obtains visually pleasing results but also outperforms state-of-the-art methods qualitatively and quantitatively.     

Priority-MECE: A Mobile Edge Cloud Ecosystem Based on Priority Tasks Offloading

Mobile Networks and Applications - With the rapid development of Internet of things, the traditional city model is no longer applicable. Therefore, the emerging concept of smart city meets the...     

基于卷积神经网络的5G蜂窝网络无线定位方法

5G蜂窝网络发展迅猛，其覆盖面积将逐渐增大，因此使用5G蜂窝网络进行定位是有研究潜力的研究方向。本文提出一种新的深度学习技术来实现高效、高精度和低占用的定位，以代替传统指纹定位过程中繁重的指纹库生成以及距离计算。该方法建立了一个特殊的卷积神经网络，并根据5G天线信号的接收信号强度指示、相位和到达角等特征量，选择合适的输入数据格式构造样本组建训练集，对该卷积神经网络进行训练。训练得到的卷积神经网络可以替代指纹定位中的庞大指纹库，非常有利于直接在5G移动设备端实现定位。虽然卷积神经网络在训练过程中需要大量时间，但在训练完毕后直接进行分类定位的速度非常快，可以保障定位实现的实时性。本文所实现的卷积神经网络权重与偏置所占内存不到0.5 MB，且能够在实际应用环境中以95%的定位准确率以及0.1 m的平均定位精度实现高精度定位。     

Adaptive reversible data hiding for JPEG images with multiple two-dimensional histograms

Joint photographic experts group (JPEG) can provide good quality with small file size but also eliminate extensively the redundancies of images. Therefore, hiding data into JPEG images in terms of maintaining high visual quality at small file sizes has been a great challenge for researchers. In this paper, an adaptive reversible data hiding method for JPEG images containing multiple two-dimensional (2D) histograms is proposed. Adaptability is mainly reflected in three aspects. The first one is to preferentially select sharper histograms for data embedding after $K$ histograms are established by constructing the $k$th ($k\in \{1,2,\dots ,K\}$) histogram using the $k$th non-zero alternating current (AC) coefficient of all the quantized discrete cosine transform blocks. On the other hand, to fully exploit the strong correlation between coefficients of one histogram, the smoothness of each coefficient is estimated by a block smoothness estimator so that a sharply-distributed 2D-histogram is constructed by combining two coefficients with similar smoothness into a pair. The pair corresponding to low complexity is selected priorly for data embedding, leading to high embedding performance while maintaining low file size. Besides, we design multiple embedding strategies to adaptively select the embedding strategy for each 2D histogram. Experimental results demonstrate that the proposed method can achieve higher rate–distortion performance which maintaining lower file storage space, compared with previous studies.     

High Q×f values of Zn-Ni co-modified LiMg0.9Zn0.1-xNixPO4 microwave dielectric ceramics for 5G/6G LTCC modules

In this work, Zn-Ni co-modified LiMg_0.9Zn_0.1-xNi_xPO₄ (x = 0–0.1) microwave dielectric ceramics were fabricated using a solid state synthesis route. Rietveld refinement of the XRD data revealed that all ceramic samples have formed a single phase with olivine structure. SEM images showed that the samples have a dense microstructure, that agrees with the measured relative density of 97.73 %. Based on the complex chemical bond theory, Raman and infrared reflectance spectra, we postulate that ε_r is mainly affected by the ionic polarizability, lattice and bond energy, while P-O bond plays a decisive role in Q×f and τ_f value. Optimum properties of Q×f ~ 153,500 GHz, ε_r ~ 7.13 and τ_f ~ ?59 ppm/°C were achieved for the composition LiMg_0.9Zn_0.06Ni_0.04PO₄ sintered at 875 ℃ for 2 h. This set of properties makes these ceramics an excellent candidate for LTCC, wave-guide filters and antennas for 5 G/6 G communication applications.     

使能未来工厂的5G能力综述

5G系统将移动通信服务从移动电话、移动宽带和大规模机器通信扩展到新的应用领域，即所谓对通信服务有特殊要求的垂直领域。对使能未来工厂的5G能力进行了全面的分析总结，包括弹性网络架构、灵活频谱、超可靠低时延通信、时间敏感网络、安全和定位，而弹性网络架构又包括对网络切片、非公共网络、5G局域网和边缘计算的支持。希望从广度到深度，对相关的理论及技术应用做透彻、全面的梳理，对其挑战做清晰的总结，从而为相关研究和工程技术人员提供借鉴。     

A viable approach to prepare 3C-SiC coatings by thermal MOCVD using commercial grade precursors

A series of 3 C-SiC coatings were prepared by organometallic chemical vapor deposition (MOCVD) using precursor solution containing a varying proportion of commercial-grade hexamethyldisiloxane (HMDSO) and n-hexane. The phase composition, bonding state, and microstructure of 3 C-SiC coatings were studied in detail by grazing incidence X-ray diffraction (GIXRD), Raman spectroscopy, X-ray photoelectron spectroscopy (XPS), and scanning electron microscopy (SEM). The microstructure and mechanical properties of the optimal 3 C-SiC coating were characterized by scanning transmission electron microscopy (STEM) and nanoindentation, respectively. Our results revealed that the amount of undesired graphite phase can be significantly reduced in the 3 C-SiC coating by introducing hydrogen gas in the reaction chamber alongside increasing the ratio of HMDSO/n-hexane in the precursor mixture. The STEM results revealed that the optimal coating was predominantly composed of nano-crystalline 3 C-SiC grains alongside a small amount of amorphous graphite. The hardness and elastic modulus of the optimal coating were 38.19 GPa and 363.2 GPa, respectively.     

Electronic synaptic characteristics and simulation application of Ag/CeO2/Pt memristor

With the development of science and technology, artificial neural networks (ANNs) have become a research spot. Furthermore, two-terminal oxide memristors with adjustable resistance have attracted extensive attention due to their simple structure, low power consumption, and easy integration, among other attractive features. Additionally, among many oxides, ceria has exhibited good performance, such as longer retention and better stability in resistive devices; however, it was currently rarely used in artificial neural synapses. In this work, a self-designed Ag/CeO₂/Pt memristor was found to realize the slow transition between the high-resistance state (HRS) and low-resistance state (LRS) at a very small working voltage. It was also found to exhibit very good retention performance and cyclic characteristics. The conductivity of the device was analyzed by the current-voltage (I–V) characteristics curve. Furthermore, its artificial synaptic function was explored, and a series of neuromorphic systems simulations were carried out. Additionally, the relationships between the pulse sequence parameters and the resistance state of the device were explored, and an electrical signal simulation of Pavlov's dog experiment was designed. The findings demonstrated that the device could be used to realize the application of artificial neural synapse simulation.     

Cold sintered,temperature-stable CaSnSiO5-K2MoO4 composite microwave ceramics and its prototype microstrip patch antenna

Dense (1-x)wt%CaSnSiO₅-xwt%K₂MoO₄ (CSSO-KMO) composite ceramics were fabricated by the cold sintering process at 180 °C under 400 MPa for 60 min. X-ray diffraction, Energy dispersive X-ray and Raman spectroscopy confirmed that CSSO and KMO coexisted without intermediate phases. As KMO weight fraction increased, relative permittivity (ε_r) and temperature coefficient of resonant frequency (τ_f) decreased and the microwave quality factor (Q×f, where f is resonant frequency) increased. Near-zero τ_f (-0.5 ppm/°C) was obtained for 65 wt%CSSO-35 wt%KMO with ε_r ～ 9.2 and Q×f ～ 6240 GHz. No chemical reaction between ceramic composites and silver was observed, demonstrating potential for cofiring with Ag-paste. A prototype antenna was fabricated from 65 wt%CSSO-35 wt%KMO composite ceramic with a bandwidth of 144 MHz @ -10 dB, a gain of 5.7 dBi and a total efficiency of 88.4 % at 5.2 GHz, suitable for 5 G mobile communication systems.