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.     

Collaborative Distribution Alignment for 2D image-based 3D shape retrieval

Retrieving 3D shapes with 2D images has become a popular research area nowadays, and a great deal of work has been devoted to reducing the discrepancy between 3D shapes and 2D images to improve retrieval performance. However, most approaches ignore the semantic information and decision boundaries of the two domains, and cannot achieve both domain alignment and category alignment in one module. In this paper, a novel Collaborative Distribution Alignment (CDA) model is developed to address the above existing challenges. Specifically, we first adopt a dual-stream CNN, following a similarity guided constraint module, to generate discriminative embeddings for input 2D images and 3D shapes (described as multiple views). Subsequently, we explicitly introduce a joint domain-class alignment module to dynamically learn a class-discriminative and domain-agnostic feature space, which can narrow the distance between 2D image and 3D shape instances of the same underlying category, while pushing apart the instances from different categories. Furthermore, we apply a decision boundary refinement module to avoid generating class-ambiguity embeddings by dynamically adjusting inconsistencies between two discriminators. Extensive experiments and evaluations on two challenging benchmarks, MI3DOR and MI3DOR-2, demonstrate the superiority of the proposed CDA method for 2D image-based 3D shape retrieval task.     

Spatial–Temporal Fusion Based Path Planning for Source Seeking in Wireless Sensor Network

International Journal of Wireless Information Networks - Source seeking problem has been faced in many fields, especially in search and rescue applications. We proposed a virtual structure-based...     

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...     

IRS辅助的SWIPT系统中基于能效优先的波束成形设计与优化

以智能反射面(intelligent reflecting surface,IRS)辅助的无线携能通信(simultaneous wireless information and power transfer,SWIPT)系统为背景,研究了该系统中基于能效优先的多天线发送端有源波束成形与IRS无源波束成形联合设计与优化方法。以最大化接收端的最小能效为优化目标,构造在发送端功率、接收端能量阈值、IRS相移等多约束下的非线性优化问题,用交替方向乘子法(alternating direction method of multipliers,ADMM)求解。采用Dinkelbach算法转化目标函数,通过奇异值分解(singular value decomposition,SVD)和半定松弛(semi-definite relaxation,SDR)得到发送端有源波束成形向量。采用SDR得到IRS相移矩阵与反射波束成形向量。结果表明,该系统显著降低了系统能量收集(energy harvesting,EH)接收端的能量阈值。当系统总电路功耗为?15 dBm时,所提方案的用户能效为300 KB/J。当IRS反射阵源数与发送天线数均为最大值时,系统可达最大能效。     

Personalized broad learning system for facial expression

Multimedia Tools and Applications - Understanding human emotions through facial expressions is key enabling technology for interactive robots. Most approaches of facial expression recognition are...     

Modeling and design of 3-D MPPT for ultra low power RF energy harvesters

Radio-Frequency (RF) energy harvesting must cope with the limited availability and high variability of the energy source. In this paper, the modeling of an RF harvester for ultra low power environments is presented. A mathematical model based on theoretical analysis is developed. The model demonstrates that the maximum transferred power point is located in a three-dimensional space defined by the input capacitance, the output voltage, and the load resistance of the rectifier circuit. Moreover, the mathematical model returns results in substantial agreement with the SPICE simulation results, while guaranteeing a remarkable reduction of the required computation time. Furthermore, the paper reports the implementation of a mixed signal system for the 3-D MPPT, to be embedded in an RF harvester, in a 65 nm CMOS technology. The circuit exhibits a simulated power consumption lower than 100 nW, making this solution suitable for ultra low power harvesting.     

Convolutional neural network with adaptive inferential framework for skeleton-based action recognition

In the task of skeleton-based action recognition, CNN-based methods represent the skeleton data as a pseudo image for processing. However, it still remains as a critical issue of how to construct the pseudo image to model the spatial dependencies of the skeletal data. To address this issue, we propose a novel convolutional neural network with adaptive inferential framework (AIF-CNN) to exploit the dependencies among the skeleton joints. We particularly investigate several initialization strategies to make the AIF effective with each strategy introducing the different prior knowledge. Extensive experiments on the dataset of NTU RGB+D and Kinetics-Skeleton demonstrate that the performance is improved significantly by integrating the different prior information. The source code is available at: https://github.com/hhe-distance/AIF-CNN.